diff --git a/crates/goose-acp/tests/common_tests/mod.rs b/crates/goose-acp/tests/common_tests/mod.rs index e6a4fd26ee..7305b7b8f6 100644 --- a/crates/goose-acp/tests/common_tests/mod.rs +++ b/crates/goose-acp/tests/common_tests/mod.rs @@ -163,14 +163,14 @@ pub async fn run_model_list() { "o3-mini-2025-01-31", "o1", "o1-2024-12-17", - "gpt-4o-mini", - "gpt-4o-mini-2024-07-18", - "o4-mini-deep-research", - "o4-mini-deep-research-2025-06-26", "gpt-4o", "gpt-4o-2024-05-13", "gpt-4o-2024-08-06", "gpt-4o-2024-11-20", + "gpt-4o-mini", + "gpt-4o-mini-2024-07-18", + "o4-mini-deep-research", + "o4-mini-deep-research-2025-06-26", "gpt-4", "gpt-4-0613", "gpt-4-turbo", diff --git a/crates/goose-cli/src/commands/configure.rs b/crates/goose-cli/src/commands/configure.rs index d1d5a634d8..e4fa7d980f 100644 --- a/crates/goose-cli/src/commands/configure.rs +++ b/crates/goose-cli/src/commands/configure.rs @@ -1969,6 +1969,7 @@ fn add_provider() -> anyhow::Result<()> { supports_streaming: Some(supports_streaming), headers, requires_auth, + catalog_provider_id: None, })?; cliclack::outro(format!("Custom provider added: {}", display_name))?; diff --git a/crates/goose-server/src/openapi.rs b/crates/goose-server/src/openapi.rs index e128289bad..374d08939f 100644 --- a/crates/goose-server/src/openapi.rs +++ b/crates/goose-server/src/openapi.rs @@ -354,6 +354,8 @@ derive_utoipa!(Icon as IconSchema); super::routes::config_management::get_custom_provider, super::routes::config_management::update_custom_provider, super::routes::config_management::remove_custom_provider, + super::routes::config_management::get_provider_catalog, + super::routes::config_management::get_provider_catalog_template, super::routes::config_management::check_provider, super::routes::config_management::set_config_provider, super::routes::config_management::configure_provider_oauth, @@ -450,6 +452,10 @@ derive_utoipa!(Icon as IconSchema); super::routes::config_management::ToolPermission, super::routes::config_management::UpsertPermissionsQuery, super::routes::config_management::UpdateCustomProviderRequest, + goose::providers::catalog::ProviderCatalogEntry, + goose::providers::catalog::ProviderTemplate, + goose::providers::catalog::ModelTemplate, + goose::providers::catalog::ModelCapabilities, super::routes::config_management::CheckProviderRequest, super::routes::config_management::SetProviderRequest, super::routes::config_management::ModelInfoQuery, diff --git a/crates/goose-server/src/routes/config_management.rs b/crates/goose-server/src/routes/config_management.rs index 032d55e980..6063b40e37 100644 --- a/crates/goose-server/src/routes/config_management.rs +++ b/crates/goose-server/src/routes/config_management.rs @@ -15,6 +15,10 @@ use goose::model::ModelConfig; use goose::providers::auto_detect::detect_provider_from_api_key; use goose::providers::base::{ProviderMetadata, ProviderType}; use goose::providers::canonical::maybe_get_canonical_model; +use goose::providers::catalog::{ + get_provider_template, get_providers_by_format, ProviderCatalogEntry, ProviderFormat, + ProviderTemplate, +}; use goose::providers::create_with_default_model; use goose::providers::providers as get_providers; use goose::{ @@ -94,6 +98,8 @@ pub struct UpdateCustomProviderRequest { pub headers: Option>, #[serde(default = "default_requires_auth")] pub requires_auth: bool, + #[serde(default)] + pub catalog_provider_id: Option, } fn default_requires_auth() -> bool { @@ -648,6 +654,7 @@ pub async fn create_custom_provider( supports_streaming: request.supports_streaming, headers: request.headers, requires_auth: request.requires_auth, + catalog_provider_id: request.catalog_provider_id, }, )?; @@ -718,6 +725,7 @@ pub async fn update_custom_provider( supports_streaming: request.supports_streaming, headers: request.headers, requires_auth: request.requires_auth, + catalog_provider_id: request.catalog_provider_id, }, )?; @@ -770,6 +778,54 @@ pub async fn set_config_provider( Ok(()) } +#[utoipa::path( + get, + path = "/config/provider-catalog", + params( + ("format" = Option, Query, description = "Filter by provider format (openai, anthropic, ollama)") + ), + responses( + (status = 200, description = "Provider catalog retrieved successfully", body = [ProviderCatalogEntry]), + (status = 400, description = "Invalid format parameter") + ) +)] +pub async fn get_provider_catalog( + axum::extract::Query(params): axum::extract::Query>, +) -> Result>, ErrorResponse> { + let format_str = params.get("format").map(|s| s.as_str()).unwrap_or("openai"); + + let format = format_str.parse::().map_err(|_| { + ErrorResponse::bad_request(format!( + "Invalid format '{}'. Must be one of: openai, anthropic, ollama", + format_str + )) + })?; + + let providers = get_providers_by_format(format).await; + Ok(Json(providers)) +} + +#[utoipa::path( + get, + path = "/config/provider-catalog/{id}", + params( + ("id" = String, Path, description = "Provider ID from models.dev") + ), + responses( + (status = 200, description = "Provider template retrieved successfully", body = ProviderTemplate), + (status = 404, description = "Provider not found in catalog") + ) +)] +pub async fn get_provider_catalog_template( + Path(id): Path, +) -> Result, ErrorResponse> { + let template = get_provider_template(&id).ok_or_else(|| { + ErrorResponse::not_found(format!("Provider '{}' not found in catalog", id)) + })?; + + Ok(Json(template)) +} + #[utoipa::path( post, path = "/config/providers/{name}/oauth", @@ -836,6 +892,11 @@ pub fn routes(state: Arc) -> Router { .route("/config/extensions/{name}", delete(remove_extension)) .route("/config/providers", get(providers)) .route("/config/providers/{name}/models", get(get_provider_models)) + .route("/config/provider-catalog", get(get_provider_catalog)) + .route( + "/config/provider-catalog/{id}", + get(get_provider_catalog_template), + ) .route("/config/detect-provider", post(detect_provider)) .route("/config/slash_commands", get(get_slash_commands)) .route( diff --git a/crates/goose/src/config/declarative_providers.rs b/crates/goose/src/config/declarative_providers.rs index fb0f83d185..de95bfdee3 100644 --- a/crates/goose/src/config/declarative_providers.rs +++ b/crates/goose/src/config/declarative_providers.rs @@ -42,6 +42,8 @@ pub struct DeclarativeProviderConfig { pub supports_streaming: Option, #[serde(default = "default_requires_auth")] pub requires_auth: bool, + #[serde(default)] + pub catalog_provider_id: Option, } fn default_requires_auth() -> bool { @@ -102,6 +104,7 @@ pub struct CreateCustomProviderParams { pub supports_streaming: Option, pub headers: Option>, pub requires_auth: bool, + pub catalog_provider_id: Option, } #[derive(Debug, Clone)] @@ -115,6 +118,7 @@ pub struct UpdateCustomProviderParams { pub supports_streaming: Option, pub headers: Option>, pub requires_auth: bool, + pub catalog_provider_id: Option, } pub fn create_custom_provider( @@ -154,6 +158,7 @@ pub fn create_custom_provider( timeout_seconds: None, supports_streaming: params.supports_streaming, requires_auth: params.requires_auth, + catalog_provider_id: params.catalog_provider_id, }; let custom_providers_dir = custom_providers_dir(); @@ -215,6 +220,7 @@ pub fn update_custom_provider(params: UpdateCustomProviderParams) -> Result<()> timeout_seconds: existing_config.timeout_seconds, supports_streaming: params.supports_streaming, requires_auth: params.requires_auth, + catalog_provider_id: params.catalog_provider_id, }; let file_path = custom_providers_dir().join(format!("{}.json", updated_config.name)); diff --git a/crates/goose/src/providers/canonical/build_canonical_models.rs b/crates/goose/src/providers/canonical/build_canonical_models.rs index a955c13353..652f176378 100644 --- a/crates/goose/src/providers/canonical/build_canonical_models.rs +++ b/crates/goose/src/providers/canonical/build_canonical_models.rs @@ -18,6 +18,17 @@ use serde_json::Value; use std::collections::{BTreeMap, BTreeSet, HashMap}; use std::path::PathBuf; +#[derive(Debug, Clone, Serialize, Deserialize)] +struct ProviderMetadata { + pub id: String, + pub display_name: String, + pub npm: Option, + pub api: Option, + pub doc: Option, + pub env: Vec, + pub model_count: usize, +} + const MODELS_DEV_API_URL: &str = "https://models.dev/api.json"; const DEFAULT_CONTEXT_LIMIT: usize = 128_000; const SEPARATOR: &str = @@ -25,21 +36,9 @@ const SEPARATOR: &str = const SUBSEPARATOR: &str = "--------------------------------------------------------------------------------"; -const ALLOWED_PROVIDERS: &[&str] = &[ - "anthropic", - "google", - "openai", - "openrouter", - "llama", - "mistral", - "xai", - "deepseek", - "cohere", - "azure", - "amazon-bedrock", - "venice", - "google-vertex", -]; +fn is_compatible_provider(npm: &str) -> bool { + npm.contains("openai") || npm.contains("anthropic") || npm.contains("ollama") +} fn normalize_provider_name(provider: &str) -> &str { match provider { @@ -366,12 +365,7 @@ fn process_model( model_id: &str, model_data: &Value, normalized_provider: &str, -) -> Result> { - let cost_data = match model_data.get("cost") { - Some(c) if !c.is_null() => c, - _ => return Ok(None), - }; - +) -> Result<(String, CanonicalModel)> { let name = model_data["name"] .as_str() .with_context(|| format!("Model {} missing name", model_id))?; @@ -383,11 +377,19 @@ fn process_model( output: parse_modalities(model_data, "output"), }; - let cost = Pricing { - input: cost_data.get("input").and_then(|v| v.as_f64()), - output: cost_data.get("output").and_then(|v| v.as_f64()), - cache_read: cost_data.get("cache_read").and_then(|v| v.as_f64()), - cache_write: cost_data.get("cache_write").and_then(|v| v.as_f64()), + let cost = match model_data.get("cost") { + Some(c) if !c.is_null() => Pricing { + input: c.get("input").and_then(|v| v.as_f64()), + output: c.get("output").and_then(|v| v.as_f64()), + cache_read: c.get("cache_read").and_then(|v| v.as_f64()), + cache_write: c.get("cache_write").and_then(|v| v.as_f64()), + }, + _ => Pricing { + input: None, + output: None, + cache_read: None, + cache_write: None, + }, }; let limit = Limit { @@ -428,7 +430,73 @@ fn process_model( .unwrap_or(model_id) .to_string(); - Ok(Some((model_name, canonical_model))) + Ok((model_name, canonical_model)) +} + +fn collect_provider_metadata( + providers_obj: &serde_json::Map, +) -> Vec { + let mut metadata_list = Vec::new(); + + for (provider_id, provider_data) in providers_obj { + let npm = match provider_data.get("npm").and_then(|v| v.as_str()) { + Some(n) if !n.is_empty() => n, + _ => continue, + }; + + if !is_compatible_provider(npm) { + continue; + } + + let api = provider_data + .get("api") + .and_then(|v| v.as_str()) + .map(String::from); + + if api.is_none() { + continue; + } + + let normalized_provider = normalize_provider_name(provider_id).to_string(); + let doc = provider_data + .get("doc") + .and_then(|v| v.as_str()) + .map(String::from); + let env = provider_data + .get("env") + .and_then(|v| v.as_array()) + .map(|arr| { + arr.iter() + .filter_map(|v| v.as_str()) + .map(String::from) + .collect() + }) + .unwrap_or_default(); + let display_name = provider_data + .get("name") + .and_then(|v| v.as_str()) + .unwrap_or(provider_id) + .to_string(); + let model_count = provider_data + .get("models") + .and_then(|v| v.as_object()) + .map(|models| models.len()) + .unwrap_or(0); + + metadata_list.push(ProviderMetadata { + id: normalized_provider, + display_name, + npm: Some(npm.to_string()), + api, + doc, + env, + model_count, + }); + + println!(" Added {} ({}) - {} models", provider_id, npm, model_count); + } + + metadata_list } async fn build_canonical_models() -> Result<()> { @@ -441,28 +509,25 @@ async fn build_canonical_models() -> Result<()> { let mut registry = CanonicalModelRegistry::new(); let mut total_models = 0; - for provider_key in ALLOWED_PROVIDERS { - if let Some(provider_data) = providers_obj.get(*provider_key) { - let models = provider_data["models"] - .as_object() - .with_context(|| format!("Provider {} missing models object", provider_key))?; + for (provider_key, provider_data) in providers_obj { + let models = match provider_data.get("models").and_then(|v| v.as_object()) { + Some(m) => m, + None => continue, + }; - let normalized_provider = normalize_provider_name(provider_key); + let normalized_provider = normalize_provider_name(provider_key); - println!( - "\nProcessing {} ({} models)...", - normalized_provider, - models.len() - ); + println!( + "\nProcessing {} ({} models)...", + normalized_provider, + models.len() + ); - for (model_id, model_data) in models { - if let Some((model_name, canonical_model)) = - process_model(model_id, model_data, normalized_provider)? - { - registry.register(normalized_provider, &model_name, canonical_model); - total_models += 1; - } - } + for (model_id, model_data) in models { + let (model_name, canonical_model) = + process_model(model_id, model_data, normalized_provider)?; + registry.register(normalized_provider, &model_name, canonical_model); + total_models += 1; } } @@ -474,6 +539,18 @@ async fn build_canonical_models() -> Result<()> { output_path.display() ); + println!("\n\nCollecting provider metadata from models.dev..."); + let provider_metadata_list = collect_provider_metadata(providers_obj); + + let provider_metadata_path = data_file_path("provider_metadata.json"); + let provider_metadata_json = serde_json::to_string_pretty(&provider_metadata_list)?; + std::fs::write(&provider_metadata_path, provider_metadata_json)?; + println!( + "✓ Wrote {} providers metadata to {}", + provider_metadata_list.len(), + provider_metadata_path.display() + ); + Ok(()) } diff --git a/crates/goose/src/providers/canonical/data/canonical_mapping_report.json b/crates/goose/src/providers/canonical/data/canonical_mapping_report.json index 3d928d316f..4256a5c734 100644 --- a/crates/goose/src/providers/canonical/data/canonical_mapping_report.json +++ b/crates/goose/src/providers/canonical/data/canonical_mapping_report.json @@ -1,5 +1,5 @@ { - "timestamp": "2026-02-13T17:38:00.310507+00:00", + "timestamp": "2026-02-23T18:23:49.176777+00:00", "unmapped_models": [ { "provider": "anthropic", @@ -65,6 +65,10 @@ "provider": "databricks", "model": "databricks-bge-large-en" }, + { + "provider": "databricks", + "model": "databricks-gemini-3-1-pro" + }, { "provider": "databricks", "model": "databricks-gemini-3-flash" @@ -101,6 +105,14 @@ "provider": "databricks", "model": "databricks-meta-llama-3-1-8b-instruct" }, + { + "provider": "databricks", + "model": "databricks-qwen3-embedding-0-6b" + }, + { + "provider": "databricks", + "model": "databricks-qwen3-next-80b-a3b-instruct" + }, { "provider": "databricks", "model": "dummy-model-ml-gp-endpoint" @@ -323,7 +335,11 @@ }, { "provider": "google", - "model": "gemini-exp-1206" + "model": "gemini-3.1-pro-preview" + }, + { + "provider": "google", + "model": "gemini-3.1-pro-preview-customtools" }, { "provider": "google", @@ -365,18 +381,10 @@ "provider": "google", "model": "imagen-4.0-generate-001" }, - { - "provider": "google", - "model": "imagen-4.0-generate-preview-06-06" - }, { "provider": "google", "model": "imagen-4.0-ultra-generate-001" }, - { - "provider": "google", - "model": "imagen-4.0-ultra-generate-preview-06-06" - }, { "provider": "google", "model": "nano-banana-pro-preview" @@ -573,10 +581,6 @@ "provider": "openai", "model": "babbage:ft-square-2023-02-28-14-48-38" }, - { - "provider": "openai", - "model": "chatgpt-4o-latest" - }, { "provider": "openai", "model": "chatgpt-image-latest" @@ -1529,6 +1533,30 @@ "provider": "openai", "model": "ft:gpt-4.1-mini-2025-04-14:square::BwjlIMor:ckpt-step-1018" }, + { + "provider": "openai", + "model": "ft:gpt-4.1-mini-2025-04-14:square:plat-completion:DAHA8Zfx:ckpt-step-58" + }, + { + "provider": "openai", + "model": "ft:gpt-4.1-mini-2025-04-14:square:plat-completion:DAHA9OcK" + }, + { + "provider": "openai", + "model": "ft:gpt-4.1-mini-2025-04-14:square:plat-completion:DAHA9hzA:ckpt-step-116" + }, + { + "provider": "openai", + "model": "ft:gpt-4.1-mini-2025-04-14:square:plat-ft:DA58ZIKa:ckpt-step-912" + }, + { + "provider": "openai", + "model": "ft:gpt-4.1-mini-2025-04-14:square:plat-ft:DA58a3A7:ckpt-step-1824" + }, + { + "provider": "openai", + "model": "ft:gpt-4.1-mini-2025-04-14:square:plat-ft:DA58aFG0" + }, { "provider": "openai", "model": "ft:gpt-4.1-nano-2025-04-14:square:qliao-plathelp-v1:CRNAywx8" @@ -2681,6 +2709,10 @@ "provider": "openai", "model": "gpt-audio" }, + { + "provider": "openai", + "model": "gpt-audio-1.5" + }, { "provider": "openai", "model": "gpt-audio-2025-08-28" @@ -2713,6 +2745,10 @@ "provider": "openai", "model": "gpt-realtime" }, + { + "provider": "openai", + "model": "gpt-realtime-1.5" + }, { "provider": "openai", "model": "gpt-realtime-2025-08-28" @@ -2769,14 +2805,58 @@ "provider": "openrouter", "model": "ai21/jamba-large-1.7" }, + { + "provider": "openrouter", + "model": "aion-labs/aion-1.0" + }, + { + "provider": "openrouter", + "model": "aion-labs/aion-1.0-mini" + }, + { + "provider": "openrouter", + "model": "aion-labs/aion-rp-llama-3.1-8b" + }, + { + "provider": "openrouter", + "model": "alfredpros/codellama-7b-instruct-solidity" + }, { "provider": "openrouter", "model": "alibaba/tongyi-deepresearch-30b-a3b" }, + { + "provider": "openrouter", + "model": "allenai/molmo-2-8b" + }, + { + "provider": "openrouter", + "model": "allenai/olmo-2-0325-32b-instruct" + }, + { + "provider": "openrouter", + "model": "allenai/olmo-3-32b-think" + }, + { + "provider": "openrouter", + "model": "allenai/olmo-3-7b-instruct" + }, + { + "provider": "openrouter", + "model": "allenai/olmo-3-7b-think" + }, { "provider": "openrouter", "model": "allenai/olmo-3.1-32b-instruct" }, + { + "provider": "openrouter", + "model": "allenai/olmo-3.1-32b-think" + }, + { + "provider": "openrouter", + "model": "alpindale/goliath-120b" + }, { "provider": "openrouter", "model": "amazon/nova-2-lite-v1" @@ -2799,16 +2879,24 @@ }, { "provider": "openrouter", - "model": "anthropic/claude-3-haiku" - }, - { - "provider": "openrouter", - "model": "anthropic/claude-3.5-sonnet" + "model": "anthracite-org/magnum-v4-72b" }, { "provider": "openrouter", "model": "anthropic/claude-3.7-sonnet:thinking" }, + { + "provider": "openrouter", + "model": "arcee-ai/coder-large" + }, + { + "provider": "openrouter", + "model": "arcee-ai/maestro-reasoning" + }, + { + "provider": "openrouter", + "model": "arcee-ai/spotlight" + }, { "provider": "openrouter", "model": "arcee-ai/trinity-mini" @@ -2821,10 +2909,22 @@ "provider": "openrouter", "model": "baidu/ernie-4.5-21b-a3b" }, + { + "provider": "openrouter", + "model": "baidu/ernie-4.5-21b-a3b-thinking" + }, + { + "provider": "openrouter", + "model": "baidu/ernie-4.5-300b-a47b" + }, { "provider": "openrouter", "model": "baidu/ernie-4.5-vl-28b-a3b" }, + { + "provider": "openrouter", + "model": "baidu/ernie-4.5-vl-424b-a47b" + }, { "provider": "openrouter", "model": "bytedance-seed/seed-1.6" @@ -2835,15 +2935,15 @@ }, { "provider": "openrouter", - "model": "cohere/command-r-08-2024" + "model": "bytedance/ui-tars-1.5-7b" }, { "provider": "openrouter", - "model": "cohere/command-r-plus-08-2024" + "model": "cohere/command-a" }, { "provider": "openrouter", - "model": "deepseek/deepseek-chat" + "model": "deepcogito/cogito-v2.1-671b" }, { "provider": "openrouter", @@ -2853,10 +2953,22 @@ "provider": "openrouter", "model": "deepseek/deepseek-r1-0528" }, + { + "provider": "openrouter", + "model": "deepseek/deepseek-r1-distill-qwen-32b" + }, { "provider": "openrouter", "model": "deepseek/deepseek-v3.2-exp" }, + { + "provider": "openrouter", + "model": "eleutherai/llemma_7b" + }, + { + "provider": "openrouter", + "model": "essentialai/rnj-1-instruct" + }, { "provider": "openrouter", "model": "google/gemini-2.0-flash-lite-001" @@ -2865,6 +2977,26 @@ "provider": "openrouter", "model": "google/gemini-2.5-pro-preview" }, + { + "provider": "openrouter", + "model": "google/gemini-3-pro-image-preview" + }, + { + "provider": "openrouter", + "model": "google/gemini-3.1-pro-preview" + }, + { + "provider": "openrouter", + "model": "google/gemma-2-27b-it" + }, + { + "provider": "openrouter", + "model": "gryphe/mythomax-l2-13b" + }, + { + "provider": "openrouter", + "model": "ibm-granite/granite-4.0-h-micro" + }, { "provider": "openrouter", "model": "inception/mercury" @@ -2873,14 +3005,46 @@ "provider": "openrouter", "model": "inception/mercury-coder" }, + { + "provider": "openrouter", + "model": "inflection/inflection-3-pi" + }, + { + "provider": "openrouter", + "model": "inflection/inflection-3-productivity" + }, { "provider": "openrouter", "model": "kwaipilot/kat-coder-pro" }, + { + "provider": "openrouter", + "model": "liquid/lfm-2.2-6b" + }, + { + "provider": "openrouter", + "model": "liquid/lfm2-8b-a1b" + }, + { + "provider": "openrouter", + "model": "mancer/weaver" + }, + { + "provider": "openrouter", + "model": "meituan/longcat-flash-chat" + }, + { + "provider": "openrouter", + "model": "meta-llama/llama-3-70b-instruct" + }, { "provider": "openrouter", "model": "meta-llama/llama-3-8b-instruct" }, + { + "provider": "openrouter", + "model": "meta-llama/llama-3.1-405b" + }, { "provider": "openrouter", "model": "meta-llama/llama-3.1-405b-instruct" @@ -2895,7 +3059,11 @@ }, { "provider": "openrouter", - "model": "meta-llama/llama-3.3-70b-instruct" + "model": "meta-llama/llama-3.2-1b-instruct" + }, + { + "provider": "openrouter", + "model": "meta-llama/llama-3.2-3b-instruct" }, { "provider": "openrouter", @@ -2907,7 +3075,27 @@ }, { "provider": "openrouter", - "model": "minimax/minimax-m2.5" + "model": "meta-llama/llama-guard-2-8b" + }, + { + "provider": "openrouter", + "model": "meta-llama/llama-guard-3-8b" + }, + { + "provider": "openrouter", + "model": "meta-llama/llama-guard-4-12b" + }, + { + "provider": "openrouter", + "model": "microsoft/phi-4" + }, + { + "provider": "openrouter", + "model": "microsoft/wizardlm-2-8x22b" + }, + { + "provider": "openrouter", + "model": "minimax/minimax-m2-her" }, { "provider": "openrouter", @@ -2915,31 +3103,19 @@ }, { "provider": "openrouter", - "model": "mistralai/ministral-3b-2512" + "model": "mistralai/mistral-7b-instruct" }, { "provider": "openrouter", - "model": "mistralai/ministral-8b-2512" + "model": "mistralai/mistral-7b-instruct-v0.1" }, { "provider": "openrouter", - "model": "mistralai/mistral-large" + "model": "mistralai/mistral-7b-instruct-v0.2" }, { "provider": "openrouter", - "model": "mistralai/mistral-large-2407" - }, - { - "provider": "openrouter", - "model": "mistralai/mistral-large-2411" - }, - { - "provider": "openrouter", - "model": "mistralai/mistral-large-2512" - }, - { - "provider": "openrouter", - "model": "mistralai/mistral-nemo" + "model": "mistralai/mistral-7b-instruct-v0.3" }, { "provider": "openrouter", @@ -2967,11 +3143,23 @@ }, { "provider": "openrouter", - "model": "mistralai/pixtral-large-2411" + "model": "mistralai/voxtral-small-24b-2507" }, { "provider": "openrouter", - "model": "mistralai/voxtral-small-24b-2507" + "model": "morph/morph-v3-fast" + }, + { + "provider": "openrouter", + "model": "morph/morph-v3-large" + }, + { + "provider": "openrouter", + "model": "neversleep/llama-3.1-lumimaid-8b" + }, + { + "provider": "openrouter", + "model": "neversleep/noromaid-20b" }, { "provider": "openrouter", @@ -2979,12 +3167,24 @@ }, { "provider": "openrouter", - "model": "nousresearch/deephermes-3-mistral-24b-preview" + "model": "nousresearch/hermes-2-pro-llama-3-8b" + }, + { + "provider": "openrouter", + "model": "nousresearch/hermes-3-llama-3.1-405b" + }, + { + "provider": "openrouter", + "model": "nousresearch/hermes-3-llama-3.1-70b" }, { "provider": "openrouter", "model": "nvidia/llama-3.1-nemotron-70b-instruct" }, + { + "provider": "openrouter", + "model": "nvidia/llama-3.1-nemotron-ultra-253b-v1" + }, { "provider": "openrouter", "model": "nvidia/llama-3.3-nemotron-super-49b-v1.5" @@ -2995,11 +3195,7 @@ }, { "provider": "openrouter", - "model": "openai/gpt-3.5-turbo" - }, - { - "provider": "openrouter", - "model": "openai/gpt-3.5-turbo-0613" + "model": "nvidia/nemotron-nano-12b-v2-vl" }, { "provider": "openrouter", @@ -3007,48 +3203,28 @@ }, { "provider": "openrouter", - "model": "openai/gpt-4" - }, - { - "provider": "openrouter", - "model": "openai/gpt-4-0314" + "model": "openai/gpt-3.5-turbo-instruct" }, { "provider": "openrouter", "model": "openai/gpt-4-1106-preview" }, - { - "provider": "openrouter", - "model": "openai/gpt-4-turbo" - }, { "provider": "openrouter", "model": "openai/gpt-4-turbo-preview" }, - { - "provider": "openrouter", - "model": "openai/gpt-4.1-nano" - }, - { - "provider": "openrouter", - "model": "openai/gpt-4o" - }, - { - "provider": "openrouter", - "model": "openai/gpt-4o-2024-05-13" - }, - { - "provider": "openrouter", - "model": "openai/gpt-4o-2024-08-06" - }, - { - "provider": "openrouter", - "model": "openai/gpt-4o-2024-11-20" - }, { "provider": "openrouter", "model": "openai/gpt-4o-audio-preview" }, + { + "provider": "openrouter", + "model": "openai/gpt-4o-mini-search-preview" + }, + { + "provider": "openrouter", + "model": "openai/gpt-4o-search-preview" + }, { "provider": "openrouter", "model": "openai/gpt-4o:extended" @@ -3059,51 +3235,55 @@ }, { "provider": "openrouter", - "model": "openai/o1" + "model": "openai/gpt-audio" }, { "provider": "openrouter", - "model": "openai/o3" - }, - { - "provider": "openrouter", - "model": "openai/o3-deep-research" - }, - { - "provider": "openrouter", - "model": "openai/o3-mini" + "model": "openai/gpt-audio-mini" }, { "provider": "openrouter", "model": "openai/o3-mini-high" }, - { - "provider": "openrouter", - "model": "openai/o3-pro" - }, - { - "provider": "openrouter", - "model": "openai/o4-mini-deep-research" - }, { "provider": "openrouter", "model": "openai/o4-mini-high" }, { "provider": "openrouter", - "model": "openrouter/aurora-alpha" + "model": "opengvlab/internvl3-78b" }, { "provider": "openrouter", "model": "openrouter/auto" }, + { + "provider": "openrouter", + "model": "openrouter/bodybuilder" + }, { "provider": "openrouter", "model": "openrouter/free" }, { "provider": "openrouter", - "model": "prime-intellect/intellect-3" + "model": "perplexity/sonar" + }, + { + "provider": "openrouter", + "model": "perplexity/sonar-deep-research" + }, + { + "provider": "openrouter", + "model": "perplexity/sonar-pro" + }, + { + "provider": "openrouter", + "model": "perplexity/sonar-pro-search" + }, + { + "provider": "openrouter", + "model": "perplexity/sonar-reasoning-pro" }, { "provider": "openrouter", @@ -3113,6 +3293,10 @@ "provider": "openrouter", "model": "qwen/qwen-2.5-7b-instruct" }, + { + "provider": "openrouter", + "model": "qwen/qwen-2.5-vl-7b-instruct" + }, { "provider": "openrouter", "model": "qwen/qwen-max" @@ -3137,6 +3321,18 @@ "provider": "openrouter", "model": "qwen/qwen-vl-max" }, + { + "provider": "openrouter", + "model": "qwen/qwen-vl-plus" + }, + { + "provider": "openrouter", + "model": "qwen/qwen2.5-coder-7b-instruct" + }, + { + "provider": "openrouter", + "model": "qwen/qwen2.5-vl-32b-instruct" + }, { "provider": "openrouter", "model": "qwen/qwen3-14b" @@ -3157,10 +3353,6 @@ "provider": "openrouter", "model": "qwen/qwen3-32b" }, - { - "provider": "openrouter", - "model": "qwen/qwen3-4b" - }, { "provider": "openrouter", "model": "qwen/qwen3-8b" @@ -3209,6 +3401,14 @@ "provider": "openrouter", "model": "qwen/qwq-32b" }, + { + "provider": "openrouter", + "model": "raifle/sorcererlm-8x22b" + }, + { + "provider": "openrouter", + "model": "relace/relace-apply-3" + }, { "provider": "openrouter", "model": "relace/relace-search" @@ -3217,22 +3417,42 @@ "provider": "openrouter", "model": "sao10k/l3-euryale-70b" }, + { + "provider": "openrouter", + "model": "sao10k/l3-lunaris-8b" + }, + { + "provider": "openrouter", + "model": "sao10k/l3.1-70b-hanami-x1" + }, { "provider": "openrouter", "model": "sao10k/l3.1-euryale-70b" }, { "provider": "openrouter", - "model": "stepfun/step-3.5-flash" + "model": "sao10k/l3.3-euryale-70b" }, { "provider": "openrouter", - "model": "stepfun/step-3.5-flash:free" + "model": "switchpoint/router" + }, + { + "provider": "openrouter", + "model": "tencent/hunyuan-a13b-instruct" + }, + { + "provider": "openrouter", + "model": "thedrummer/cydonia-24b-v4.1" }, { "provider": "openrouter", "model": "thedrummer/rocinante-12b" }, + { + "provider": "openrouter", + "model": "thedrummer/skyfall-36b-v2" + }, { "provider": "openrouter", "model": "thedrummer/unslopnemo-12b" @@ -3243,12 +3463,16 @@ }, { "provider": "openrouter", - "model": "tngtech/tng-r1t-chimera" + "model": "undi95/remm-slerp-l2-13b" }, { "provider": "openrouter", "model": "upstage/solar-pro-3:free" }, + { + "provider": "openrouter", + "model": "writer/palmyra-x5" + }, { "provider": "openrouter", "model": "z-ai/glm-4-32b" @@ -3258,8 +3482,32 @@ "model": "z-ai/glm-4.6v" }, { - "provider": "openrouter", - "model": "z-ai/glm-5" + "provider": "tetrate", + "model": "chatgpt-4o-latest" + }, + { + "provider": "tetrate", + "model": "deepinfra/BAAI/bge-base-en-v1.5" + }, + { + "provider": "tetrate", + "model": "deepinfra/BAAI/bge-en-icl" + }, + { + "provider": "tetrate", + "model": "deepinfra/BAAI/bge-large-en-v1.5" + }, + { + "provider": "tetrate", + "model": "deepinfra/BAAI/bge-m3" + }, + { + "provider": "tetrate", + "model": "deepinfra/BAAI/bge-m3-multi" + }, + { + "provider": "tetrate", + "model": "deepinfra/Gryphe/MythoMax-L2-13b" }, { "provider": "tetrate", @@ -3273,10 +3521,18 @@ "provider": "tetrate", "model": "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B" }, + { + "provider": "tetrate", + "model": "deepinfra/PaddlePaddle/PaddleOCR-VL-0.9B" + }, { "provider": "tetrate", "model": "deepinfra/Qwen/Qwen2.5-72B-Instruct" }, + { + "provider": "tetrate", + "model": "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct" + }, { "provider": "tetrate", "model": "deepinfra/Qwen/Qwen3-14B" @@ -3305,6 +3561,30 @@ "provider": "tetrate", "model": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo" }, + { + "provider": "tetrate", + "model": "deepinfra/Qwen/Qwen3-Embedding-0.6B" + }, + { + "provider": "tetrate", + "model": "deepinfra/Qwen/Qwen3-Embedding-0.6B-batch" + }, + { + "provider": "tetrate", + "model": "deepinfra/Qwen/Qwen3-Embedding-4B" + }, + { + "provider": "tetrate", + "model": "deepinfra/Qwen/Qwen3-Embedding-4B-batch" + }, + { + "provider": "tetrate", + "model": "deepinfra/Qwen/Qwen3-Embedding-8B" + }, + { + "provider": "tetrate", + "model": "deepinfra/Qwen/Qwen3-Embedding-8B-batch" + }, { "provider": "tetrate", "model": "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct" @@ -3317,6 +3597,26 @@ "provider": "tetrate", "model": "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct" }, + { + "provider": "tetrate", + "model": "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo" + }, + { + "provider": "tetrate", + "model": "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2" + }, + { + "provider": "tetrate", + "model": "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3" + }, + { + "provider": "tetrate", + "model": "deepinfra/allenai/olmOCR-2-7B-1025" + }, + { + "provider": "tetrate", + "model": "deepinfra/deepseek-ai/DeepSeek-OCR" + }, { "provider": "tetrate", "model": "deepinfra/deepseek-ai/DeepSeek-R1-0528" @@ -3325,6 +3625,10 @@ "provider": "tetrate", "model": "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo" }, + { + "provider": "tetrate", + "model": "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B" + }, { "provider": "tetrate", "model": "deepinfra/deepseek-ai/DeepSeek-V3" @@ -3345,6 +3649,10 @@ "provider": "tetrate", "model": "deepinfra/deepseek-ai/DeepSeek-V3.2" }, + { + "provider": "tetrate", + "model": "deepinfra/google/embeddinggemma-300m" + }, { "provider": "tetrate", "model": "deepinfra/google/gemini-2.0-flash-001" @@ -3361,6 +3669,26 @@ "provider": "tetrate", "model": "deepinfra/google/gemma-3-4b-it" }, + { + "provider": "tetrate", + "model": "deepinfra/intfloat/e5-base-v2" + }, + { + "provider": "tetrate", + "model": "deepinfra/intfloat/e5-large-v2" + }, + { + "provider": "tetrate", + "model": "deepinfra/intfloat/multilingual-e5-large" + }, + { + "provider": "tetrate", + "model": "deepinfra/intfloat/multilingual-e5-large-instruct" + }, + { + "provider": "tetrate", + "model": "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct" + }, { "provider": "tetrate", "model": "deepinfra/meta-llama/Llama-3.2-3B-Instruct" @@ -3369,6 +3697,10 @@ "provider": "tetrate", "model": "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo" }, + { + "provider": "tetrate", + "model": "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8" + }, { "provider": "tetrate", "model": "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct" @@ -3393,6 +3725,14 @@ "provider": "tetrate", "model": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo" }, + { + "provider": "tetrate", + "model": "deepinfra/microsoft/WizardLM-2-8x22B" + }, + { + "provider": "tetrate", + "model": "deepinfra/microsoft/phi-4" + }, { "provider": "tetrate", "model": "deepinfra/mistralai/Mistral-Nemo-Instruct-2407" @@ -3425,6 +3765,10 @@ "provider": "tetrate", "model": "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5" }, + { + "provider": "tetrate", + "model": "deepinfra/nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL" + }, { "provider": "tetrate", "model": "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2" @@ -3445,6 +3789,46 @@ "provider": "tetrate", "model": "deepinfra/openai/gpt-oss-20b" }, + { + "provider": "tetrate", + "model": "deepinfra/sentence-transformers/all-MiniLM-L12-v2" + }, + { + "provider": "tetrate", + "model": "deepinfra/sentence-transformers/all-MiniLM-L6-v2" + }, + { + "provider": "tetrate", + "model": "deepinfra/sentence-transformers/all-mpnet-base-v2" + }, + { + "provider": "tetrate", + "model": "deepinfra/sentence-transformers/clip-ViT-B-32" + }, + { + "provider": "tetrate", + "model": "deepinfra/sentence-transformers/clip-ViT-B-32-multilingual-v1" + }, + { + "provider": "tetrate", + "model": "deepinfra/sentence-transformers/multi-qa-mpnet-base-dot-v1" + }, + { + "provider": "tetrate", + "model": "deepinfra/sentence-transformers/paraphrase-MiniLM-L6-v2" + }, + { + "provider": "tetrate", + "model": "deepinfra/shibing624/text2vec-base-chinese" + }, + { + "provider": "tetrate", + "model": "deepinfra/thenlper/gte-base" + }, + { + "provider": "tetrate", + "model": "deepinfra/thenlper/gte-large" + }, { "provider": "tetrate", "model": "deepinfra/zai-org/GLM-4.6" @@ -3465,6 +3849,26 @@ "provider": "tetrate", "model": "gemini-2.0-flash-lite-001" }, + { + "provider": "tetrate", + "model": "gemini-robotics-er-1.5-preview" + }, + { + "provider": "tetrate", + "model": "gpt-4o-mini-search-preview" + }, + { + "provider": "tetrate", + "model": "gpt-4o-mini-search-preview-2025-03-11" + }, + { + "provider": "tetrate", + "model": "gpt-4o-search-preview" + }, + { + "provider": "tetrate", + "model": "gpt-4o-search-preview-2025-03-11" + }, { "provider": "tetrate", "model": "groq/llama-3.1-8b-instant" @@ -3497,6 +3901,18 @@ "provider": "tetrate", "model": "groq/qwen/qwen3-32b" }, + { + "provider": "tetrate", + "model": "text-embedding-3-large" + }, + { + "provider": "tetrate", + "model": "text-embedding-3-small" + }, + { + "provider": "tetrate", + "model": "text-embedding-ada-002" + }, { "provider": "tetrate", "model": "xai/grok-3-beta" @@ -3536,14 +3952,6 @@ ], "all_mappings": { "anthropic": [ - { - "provider_model": "claude-3-5-haiku-20241022", - "canonical_model": "anthropic/claude-3.5-haiku" - }, - { - "provider_model": "claude-3-7-sonnet-20250219", - "canonical_model": "anthropic/claude-3.7-sonnet" - }, { "provider_model": "claude-3-haiku-20240307", "canonical_model": "anthropic/claude-3-haiku" @@ -3575,6 +3983,10 @@ { "provider_model": "claude-sonnet-4-5-20250929", "canonical_model": "anthropic/claude-sonnet-4.5" + }, + { + "provider_model": "claude-sonnet-4-6", + "canonical_model": "anthropic/claude-sonnet-4.6" } ], "aws_bedrock": [], @@ -3632,6 +4044,10 @@ "provider_model": "databricks-claude-sonnet-4-5", "canonical_model": "anthropic/claude-sonnet-4.5" }, + { + "provider_model": "databricks-claude-sonnet-4-6", + "canonical_model": "anthropic/claude-sonnet-4.6" + }, { "provider_model": "databricks-gemini-2-5-flash", "canonical_model": "google/gemini-2.5-flash" @@ -3856,6 +4272,10 @@ "provider_model": "kgoose-claude-haiku-4-5", "canonical_model": "anthropic/claude-haiku-4.5" }, + { + "provider_model": "kgoose-claude-opus-4-6", + "canonical_model": "anthropic/claude-opus-4.6" + }, { "provider_model": "kgoose-claude-sonnet-4-5", "canonical_model": "anthropic/claude-sonnet-4.5" @@ -3987,10 +4407,6 @@ "provider_model": "gemini-2.5-flash-lite-preview-09-2025", "canonical_model": "google/gemini-2.5-flash-lite-preview-09" }, - { - "provider_model": "gemini-2.5-flash-preview-09-2025", - "canonical_model": "google/gemini-2.5-flash-preview-09" - }, { "provider_model": "gemini-2.5-flash-preview-tts", "canonical_model": "google/gemini-2.5-flash-preview-tts" @@ -4271,10 +4687,18 @@ } ], "openrouter": [ + { + "provider_model": "anthropic/claude-3-haiku", + "canonical_model": "anthropic/claude-3-haiku" + }, { "provider_model": "anthropic/claude-3.5-haiku", "canonical_model": "openrouter/anthropic/claude-3.5-haiku" }, + { + "provider_model": "anthropic/claude-3.5-sonnet", + "canonical_model": "anthropic/claude-3.5-sonnet" + }, { "provider_model": "anthropic/claude-3.7-sonnet", "canonical_model": "openrouter/anthropic/claude-3.7-sonnet" @@ -4307,6 +4731,10 @@ "provider_model": "anthropic/claude-sonnet-4.5", "canonical_model": "openrouter/anthropic/claude-sonnet-4.5" }, + { + "provider_model": "anthropic/claude-sonnet-4.6", + "canonical_model": "anthropic/claude-sonnet-4.6" + }, { "provider_model": "arcee-ai/trinity-large-preview:free", "canonical_model": "openrouter/arcee-ai/trinity-large-preview:free" @@ -4315,6 +4743,26 @@ "provider_model": "arcee-ai/trinity-mini:free", "canonical_model": "openrouter/arcee-ai/trinity-mini:free" }, + { + "provider_model": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free", + "canonical_model": "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition:free" + }, + { + "provider_model": "cohere/command-r-08-2024", + "canonical_model": "cohere/command-r-08" + }, + { + "provider_model": "cohere/command-r-plus-08-2024", + "canonical_model": "cohere/command-r-plus-08" + }, + { + "provider_model": "cohere/command-r7b-12-2024", + "canonical_model": "cohere/command-r7b-12" + }, + { + "provider_model": "deepseek/deepseek-chat", + "canonical_model": "deepseek/deepseek-chat" + }, { "provider_model": "deepseek/deepseek-chat-v3-0324", "canonical_model": "openrouter/deepseek/deepseek-chat-v3" @@ -4323,6 +4771,14 @@ "provider_model": "deepseek/deepseek-chat-v3.1", "canonical_model": "openrouter/deepseek/deepseek-chat-v3.1" }, + { + "provider_model": "deepseek/deepseek-r1-0528:free", + "canonical_model": "openrouter/deepseek/deepseek-r1-0528:free" + }, + { + "provider_model": "deepseek/deepseek-r1-distill-llama-70b", + "canonical_model": "openrouter/deepseek/deepseek-r1-distill-llama-70b" + }, { "provider_model": "deepseek/deepseek-v3.1-terminus", "canonical_model": "openrouter/deepseek/deepseek-v3.1-terminus" @@ -4335,6 +4791,10 @@ "provider_model": "deepseek/deepseek-v3.2", "canonical_model": "openrouter/deepseek/deepseek-v3.2" }, + { + "provider_model": "deepseek/deepseek-v3.2-speciale", + "canonical_model": "openrouter/deepseek/deepseek-v3.2-speciale" + }, { "provider_model": "google/gemini-2.0-flash-001", "canonical_model": "openrouter/google/gemini-2.0-flash-001" @@ -4343,6 +4803,10 @@ "provider_model": "google/gemini-2.5-flash", "canonical_model": "openrouter/google/gemini-2.5-flash" }, + { + "provider_model": "google/gemini-2.5-flash-image", + "canonical_model": "google/gemini-2.5-flash-image" + }, { "provider_model": "google/gemini-2.5-flash-lite", "canonical_model": "openrouter/google/gemini-2.5-flash-lite" @@ -4351,10 +4815,6 @@ "provider_model": "google/gemini-2.5-flash-lite-preview-09-2025", "canonical_model": "openrouter/google/gemini-2.5-flash-lite-preview-09" }, - { - "provider_model": "google/gemini-2.5-flash-preview-09-2025", - "canonical_model": "openrouter/google/gemini-2.5-flash-preview-09" - }, { "provider_model": "google/gemini-2.5-pro", "canonical_model": "openrouter/google/gemini-2.5-pro" @@ -4371,6 +4831,18 @@ "provider_model": "google/gemini-3-pro-preview", "canonical_model": "openrouter/google/gemini-3-pro-preview" }, + { + "provider_model": "google/gemma-2-9b-it", + "canonical_model": "openrouter/google/gemma-2-9b-it" + }, + { + "provider_model": "google/gemma-3-12b-it", + "canonical_model": "openrouter/google/gemma-3-12b-it" + }, + { + "provider_model": "google/gemma-3-12b-it:free", + "canonical_model": "openrouter/google/gemma-3-12b-it:free" + }, { "provider_model": "google/gemma-3-27b-it", "canonical_model": "openrouter/google/gemma-3-27b-it" @@ -4379,10 +4851,54 @@ "provider_model": "google/gemma-3-27b-it:free", "canonical_model": "openrouter/google/gemma-3-27b-it:free" }, + { + "provider_model": "google/gemma-3-4b-it", + "canonical_model": "openrouter/google/gemma-3-4b-it" + }, + { + "provider_model": "google/gemma-3-4b-it:free", + "canonical_model": "openrouter/google/gemma-3-4b-it:free" + }, + { + "provider_model": "google/gemma-3n-e2b-it:free", + "canonical_model": "openrouter/google/gemma-3n-e2b-it:free" + }, + { + "provider_model": "google/gemma-3n-e4b-it", + "canonical_model": "openrouter/google/gemma-3n-e4b-it" + }, + { + "provider_model": "google/gemma-3n-e4b-it:free", + "canonical_model": "openrouter/google/gemma-3n-e4b-it:free" + }, + { + "provider_model": "liquid/lfm-2.5-1.2b-instruct:free", + "canonical_model": "openrouter/liquid/lfm-2.5-1.2b-instruct:free" + }, + { + "provider_model": "liquid/lfm-2.5-1.2b-thinking:free", + "canonical_model": "openrouter/liquid/lfm-2.5-1.2b-thinking:free" + }, + { + "provider_model": "meta-llama/llama-3.2-11b-vision-instruct", + "canonical_model": "openrouter/meta-llama/llama-3.2-11b-vision-instruct" + }, + { + "provider_model": "meta-llama/llama-3.2-3b-instruct:free", + "canonical_model": "openrouter/meta-llama/llama-3.2-3b-instruct:free" + }, + { + "provider_model": "meta-llama/llama-3.3-70b-instruct", + "canonical_model": "meta-llama/llama-3.3-70b-instruct" + }, { "provider_model": "meta-llama/llama-3.3-70b-instruct:free", "canonical_model": "openrouter/meta-llama/llama-3.3-70b-instruct:free" }, + { + "provider_model": "minimax/minimax-01", + "canonical_model": "openrouter/minimax/minimax-01" + }, { "provider_model": "minimax/minimax-m1", "canonical_model": "openrouter/minimax/minimax-m1" @@ -4395,6 +4911,10 @@ "provider_model": "minimax/minimax-m2.1", "canonical_model": "openrouter/minimax/minimax-m2.1" }, + { + "provider_model": "minimax/minimax-m2.5", + "canonical_model": "openrouter/minimax/minimax-m2.5" + }, { "provider_model": "mistralai/codestral-2508", "canonical_model": "openrouter/mistralai/codestral" @@ -4411,6 +4931,30 @@ "provider_model": "mistralai/devstral-small", "canonical_model": "openrouter/mistralai/devstral-small" }, + { + "provider_model": "mistralai/ministral-3b-2512", + "canonical_model": "mistralai/ministral-3b" + }, + { + "provider_model": "mistralai/ministral-8b-2512", + "canonical_model": "mistralai/ministral-8b" + }, + { + "provider_model": "mistralai/mistral-large", + "canonical_model": "mistralai/mistral-large" + }, + { + "provider_model": "mistralai/mistral-large-2407", + "canonical_model": "mistralai/mistral-large" + }, + { + "provider_model": "mistralai/mistral-large-2411", + "canonical_model": "mistralai/mistral-large" + }, + { + "provider_model": "mistralai/mistral-large-2512", + "canonical_model": "mistralai/mistral-large" + }, { "provider_model": "mistralai/mistral-medium-3", "canonical_model": "openrouter/mistralai/mistral-medium-3" @@ -4419,6 +4963,10 @@ "provider_model": "mistralai/mistral-medium-3.1", "canonical_model": "openrouter/mistralai/mistral-medium-3.1" }, + { + "provider_model": "mistralai/mistral-nemo", + "canonical_model": "mistralai/mistral-nemo" + }, { "provider_model": "mistralai/mistral-small-3.1-24b-instruct", "canonical_model": "openrouter/mistralai/mistral-small-3.1-24b-instruct" @@ -4427,6 +4975,10 @@ "provider_model": "mistralai/mistral-small-3.2-24b-instruct", "canonical_model": "openrouter/mistralai/mistral-small-3.2-24b-instruct" }, + { + "provider_model": "mistralai/pixtral-large-2411", + "canonical_model": "mistralai/pixtral-large" + }, { "provider_model": "moonshotai/kimi-k2", "canonical_model": "openrouter/moonshotai/kimi-k2" @@ -4447,6 +4999,14 @@ "provider_model": "moonshotai/kimi-k2.5", "canonical_model": "openrouter/moonshotai/kimi-k2.5" }, + { + "provider_model": "nousresearch/hermes-3-llama-3.1-405b:free", + "canonical_model": "openrouter/nousresearch/hermes-3-llama-3.1-405b:free" + }, + { + "provider_model": "nousresearch/hermes-4-405b", + "canonical_model": "openrouter/nousresearch/hermes-4-405b" + }, { "provider_model": "nousresearch/hermes-4-70b", "canonical_model": "openrouter/nousresearch/hermes-4-70b" @@ -4467,6 +5027,26 @@ "provider_model": "nvidia/nemotron-nano-9b-v2:free", "canonical_model": "openrouter/nvidia/nemotron-nano-9b-v2:free" }, + { + "provider_model": "openai/gpt-3.5-turbo", + "canonical_model": "openai/gpt-3.5-turbo" + }, + { + "provider_model": "openai/gpt-3.5-turbo-0613", + "canonical_model": "openai/gpt-3.5-turbo" + }, + { + "provider_model": "openai/gpt-4", + "canonical_model": "openai/gpt-4" + }, + { + "provider_model": "openai/gpt-4-0314", + "canonical_model": "openai/gpt-4" + }, + { + "provider_model": "openai/gpt-4-turbo", + "canonical_model": "openai/gpt-4-turbo" + }, { "provider_model": "openai/gpt-4.1", "canonical_model": "openrouter/openai/gpt-4.1" @@ -4475,6 +5055,26 @@ "provider_model": "openai/gpt-4.1-mini", "canonical_model": "openrouter/openai/gpt-4.1-mini" }, + { + "provider_model": "openai/gpt-4.1-nano", + "canonical_model": "openai/gpt-4.1-nano" + }, + { + "provider_model": "openai/gpt-4o", + "canonical_model": "openai/gpt-4o" + }, + { + "provider_model": "openai/gpt-4o-2024-05-13", + "canonical_model": "openai/gpt-4o" + }, + { + "provider_model": "openai/gpt-4o-2024-08-06", + "canonical_model": "openai/gpt-4o" + }, + { + "provider_model": "openai/gpt-4o-2024-11-20", + "canonical_model": "openai/gpt-4o" + }, { "provider_model": "openai/gpt-4o-mini", "canonical_model": "openrouter/openai/gpt-4o-mini" @@ -4487,6 +5087,10 @@ "provider_model": "openai/gpt-5", "canonical_model": "openrouter/openai/gpt-5" }, + { + "provider_model": "openai/gpt-5-chat", + "canonical_model": "openrouter/openai/gpt-5-chat" + }, { "provider_model": "openai/gpt-5-codex", "canonical_model": "openrouter/openai/gpt-5-codex" @@ -4567,10 +5171,50 @@ "provider_model": "openai/gpt-oss-safeguard-20b", "canonical_model": "openrouter/openai/gpt-oss-safeguard-20b" }, + { + "provider_model": "openai/o1", + "canonical_model": "openai/o1" + }, + { + "provider_model": "openai/o1-pro", + "canonical_model": "openai/o1-pro" + }, + { + "provider_model": "openai/o3", + "canonical_model": "openai/o3" + }, + { + "provider_model": "openai/o3-deep-research", + "canonical_model": "openai/o3-deep-research" + }, + { + "provider_model": "openai/o3-mini", + "canonical_model": "openai/o3-mini" + }, + { + "provider_model": "openai/o3-pro", + "canonical_model": "openai/o3-pro" + }, { "provider_model": "openai/o4-mini", "canonical_model": "openrouter/openai/o4-mini" }, + { + "provider_model": "openai/o4-mini-deep-research", + "canonical_model": "openai/o4-mini-deep-research" + }, + { + "provider_model": "prime-intellect/intellect-3", + "canonical_model": "openrouter/prime-intellect/intellect-3" + }, + { + "provider_model": "qwen/qwen-2.5-coder-32b-instruct", + "canonical_model": "openrouter/qwen/qwen-2.5-coder-32b-instruct" + }, + { + "provider_model": "qwen/qwen2.5-vl-72b-instruct", + "canonical_model": "openrouter/qwen/qwen2.5-vl-72b-instruct" + }, { "provider_model": "qwen/qwen3-235b-a22b-thinking-2507", "canonical_model": "openrouter/qwen/qwen3-235b-a22b-thinking" @@ -4624,8 +5268,20 @@ "canonical_model": "openrouter/qwen/qwen3-next-80b-a3b-thinking" }, { - "provider_model": "tngtech/tng-r1t-chimera:free", - "canonical_model": "openrouter/tngtech/tng-r1t-chimera:free" + "provider_model": "qwen/qwen3.5-397b-a17b", + "canonical_model": "openrouter/qwen/qwen3.5-397b-a17b" + }, + { + "provider_model": "qwen/qwen3.5-plus-02-15", + "canonical_model": "openrouter/qwen/qwen3.5-plus-02-15" + }, + { + "provider_model": "stepfun/step-3.5-flash", + "canonical_model": "openrouter/stepfun/step-3.5-flash" + }, + { + "provider_model": "stepfun/step-3.5-flash:free", + "canonical_model": "openrouter/stepfun/step-3.5-flash:free" }, { "provider_model": "x-ai/grok-3", @@ -4694,6 +5350,10 @@ { "provider_model": "z-ai/glm-4.7-flash", "canonical_model": "openrouter/z-ai/glm-4.7-flash" + }, + { + "provider_model": "z-ai/glm-5", + "canonical_model": "openrouter/z-ai/glm-5" } ], "tetrate": [ @@ -4773,6 +5433,10 @@ "provider_model": "claude-sonnet-4-5-20250929", "canonical_model": "anthropic/claude-sonnet-4.5" }, + { + "provider_model": "claude-sonnet-4-6", + "canonical_model": "anthropic/claude-sonnet-4.6" + }, { "provider_model": "deepinfra/anthropic/claude-3-7-sonnet-latest", "canonical_model": "anthropic/claude-3.7-sonnet" @@ -4825,6 +5489,30 @@ "provider_model": "gemini-3-pro-preview", "canonical_model": "google/gemini-3-pro-preview" }, + { + "provider_model": "gemini-embedding-001", + "canonical_model": "google/gemini-embedding-001" + }, + { + "provider_model": "gpt-3.5-turbo", + "canonical_model": "openai/gpt-3.5-turbo" + }, + { + "provider_model": "gpt-3.5-turbo-0125", + "canonical_model": "openai/gpt-3.5-turbo" + }, + { + "provider_model": "gpt-3.5-turbo-1106", + "canonical_model": "openai/gpt-3.5-turbo" + }, + { + "provider_model": "gpt-4", + "canonical_model": "openai/gpt-4" + }, + { + "provider_model": "gpt-4-0613", + "canonical_model": "openai/gpt-4" + }, { "provider_model": "gpt-4-turbo", "canonical_model": "openai/gpt-4-turbo" @@ -5087,18 +5775,6 @@ ] }, "mapped_models": [ - { - "provider": "anthropic", - "model": "claude-3-5-haiku-20241022", - "canonical": "anthropic/claude-3.5-haiku", - "recommended": true - }, - { - "provider": "anthropic", - "model": "claude-3-7-sonnet-20250219", - "canonical": "anthropic/claude-3.7-sonnet", - "recommended": true - }, { "provider": "anthropic", "model": "claude-3-haiku-20240307", @@ -5147,6 +5823,12 @@ "canonical": "anthropic/claude-sonnet-4.5", "recommended": true }, + { + "provider": "anthropic", + "model": "claude-sonnet-4-6", + "canonical": "anthropic/claude-sonnet-4.6", + "recommended": true + }, { "provider": "databricks", "model": "claude-3-5-haiku", @@ -5225,6 +5907,12 @@ "canonical": "anthropic/claude-sonnet-4.5", "recommended": true }, + { + "provider": "databricks", + "model": "databricks-claude-sonnet-4-6", + "canonical": "anthropic/claude-sonnet-4.6", + "recommended": true + }, { "provider": "databricks", "model": "databricks-gemini-2-5-flash", @@ -5439,13 +6127,13 @@ "provider": "databricks", "model": "gpt-3-5-turbo", "canonical": "openai/gpt-3.5-turbo", - "recommended": true + "recommended": false }, { "provider": "databricks", "model": "gpt-3-5-turbo-0125", "canonical": "openai/gpt-3.5-turbo", - "recommended": true + "recommended": false }, { "provider": "databricks", @@ -5561,6 +6249,12 @@ "canonical": "anthropic/claude-haiku-4.5", "recommended": true }, + { + "provider": "databricks", + "model": "kgoose-claude-opus-4-6", + "canonical": "anthropic/claude-opus-4.6", + "recommended": true + }, { "provider": "databricks", "model": "kgoose-claude-sonnet-4-5", @@ -5685,13 +6379,13 @@ "provider": "databricks", "model": "o1-mini", "canonical": "openai/o1-mini", - "recommended": true + "recommended": false }, { "provider": "databricks", "model": "o1-preview", "canonical": "openai/o1-preview", - "recommended": true + "recommended": false }, { "provider": "databricks", @@ -5739,7 +6433,7 @@ "provider": "google", "model": "gemini-2.5-flash-image", "canonical": "google/gemini-2.5-flash-image", - "recommended": true + "recommended": false }, { "provider": "google", @@ -5753,17 +6447,11 @@ "canonical": "google/gemini-2.5-flash-lite-preview-09", "recommended": true }, - { - "provider": "google", - "model": "gemini-2.5-flash-preview-09-2025", - "canonical": "google/gemini-2.5-flash-preview-09", - "recommended": true - }, { "provider": "google", "model": "gemini-2.5-flash-preview-tts", "canonical": "google/gemini-2.5-flash-preview-tts", - "recommended": true + "recommended": false }, { "provider": "google", @@ -5775,7 +6463,7 @@ "provider": "google", "model": "gemini-2.5-pro-preview-tts", "canonical": "google/gemini-2.5-pro-preview-tts", - "recommended": true + "recommended": false }, { "provider": "google", @@ -5793,7 +6481,7 @@ "provider": "google", "model": "gemini-embedding-001", "canonical": "google/gemini-embedding-001", - "recommended": true + "recommended": false }, { "provider": "google", @@ -5811,19 +6499,19 @@ "provider": "openai", "model": "gpt-3.5-turbo", "canonical": "openai/gpt-3.5-turbo", - "recommended": true + "recommended": false }, { "provider": "openai", "model": "gpt-3.5-turbo-0125", "canonical": "openai/gpt-3.5-turbo", - "recommended": true + "recommended": false }, { "provider": "openai", "model": "gpt-3.5-turbo-1106", "canonical": "openai/gpt-3.5-turbo", - "recommended": true + "recommended": false }, { "provider": "openai", @@ -5943,7 +6631,7 @@ "provider": "openai", "model": "gpt-5-chat-latest", "canonical": "openai/gpt-5-chat", - "recommended": true + "recommended": false }, { "provider": "openai", @@ -6159,18 +6847,24 @@ "provider": "openai", "model": "text-embedding-3-large", "canonical": "openai/text-embedding-3-large", - "recommended": true + "recommended": false }, { "provider": "openai", "model": "text-embedding-3-small", "canonical": "openai/text-embedding-3-small", - "recommended": true + "recommended": false }, { "provider": "openai", "model": "text-embedding-ada-002", "canonical": "openai/text-embedding-ada-002", + "recommended": false + }, + { + "provider": "openrouter", + "model": "anthropic/claude-3-haiku", + "canonical": "anthropic/claude-3-haiku", "recommended": true }, { @@ -6179,6 +6873,12 @@ "canonical": "openrouter/anthropic/claude-3.5-haiku", "recommended": true }, + { + "provider": "openrouter", + "model": "anthropic/claude-3.5-sonnet", + "canonical": "anthropic/claude-3.5-sonnet", + "recommended": true + }, { "provider": "openrouter", "model": "anthropic/claude-3.7-sonnet", @@ -6227,6 +6927,12 @@ "canonical": "openrouter/anthropic/claude-sonnet-4.5", "recommended": true }, + { + "provider": "openrouter", + "model": "anthropic/claude-sonnet-4.6", + "canonical": "anthropic/claude-sonnet-4.6", + "recommended": true + }, { "provider": "openrouter", "model": "arcee-ai/trinity-large-preview:free", @@ -6239,11 +6945,41 @@ "canonical": "openrouter/arcee-ai/trinity-mini:free", "recommended": true }, + { + "provider": "openrouter", + "model": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free", + "canonical": "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition:free", + "recommended": false + }, + { + "provider": "openrouter", + "model": "cohere/command-r-08-2024", + "canonical": "cohere/command-r-08", + "recommended": true + }, + { + "provider": "openrouter", + "model": "cohere/command-r-plus-08-2024", + "canonical": "cohere/command-r-plus-08", + "recommended": true + }, + { + "provider": "openrouter", + "model": "cohere/command-r7b-12-2024", + "canonical": "cohere/command-r7b-12", + "recommended": true + }, + { + "provider": "openrouter", + "model": "deepseek/deepseek-chat", + "canonical": "deepseek/deepseek-chat", + "recommended": true + }, { "provider": "openrouter", "model": "deepseek/deepseek-chat-v3-0324", "canonical": "openrouter/deepseek/deepseek-chat-v3", - "recommended": true + "recommended": false }, { "provider": "openrouter", @@ -6251,6 +6987,18 @@ "canonical": "openrouter/deepseek/deepseek-chat-v3.1", "recommended": true }, + { + "provider": "openrouter", + "model": "deepseek/deepseek-r1-0528:free", + "canonical": "openrouter/deepseek/deepseek-r1-0528:free", + "recommended": false + }, + { + "provider": "openrouter", + "model": "deepseek/deepseek-r1-distill-llama-70b", + "canonical": "openrouter/deepseek/deepseek-r1-distill-llama-70b", + "recommended": false + }, { "provider": "openrouter", "model": "deepseek/deepseek-v3.1-terminus", @@ -6269,6 +7017,12 @@ "canonical": "openrouter/deepseek/deepseek-v3.2", "recommended": true }, + { + "provider": "openrouter", + "model": "deepseek/deepseek-v3.2-speciale", + "canonical": "openrouter/deepseek/deepseek-v3.2-speciale", + "recommended": true + }, { "provider": "openrouter", "model": "google/gemini-2.0-flash-001", @@ -6281,6 +7035,12 @@ "canonical": "openrouter/google/gemini-2.5-flash", "recommended": true }, + { + "provider": "openrouter", + "model": "google/gemini-2.5-flash-image", + "canonical": "google/gemini-2.5-flash-image", + "recommended": false + }, { "provider": "openrouter", "model": "google/gemini-2.5-flash-lite", @@ -6293,12 +7053,6 @@ "canonical": "openrouter/google/gemini-2.5-flash-lite-preview-09", "recommended": true }, - { - "provider": "openrouter", - "model": "google/gemini-2.5-flash-preview-09-2025", - "canonical": "openrouter/google/gemini-2.5-flash-preview-09", - "recommended": true - }, { "provider": "openrouter", "model": "google/gemini-2.5-pro", @@ -6323,6 +7077,24 @@ "canonical": "openrouter/google/gemini-3-pro-preview", "recommended": true }, + { + "provider": "openrouter", + "model": "google/gemma-2-9b-it", + "canonical": "openrouter/google/gemma-2-9b-it", + "recommended": false + }, + { + "provider": "openrouter", + "model": "google/gemma-3-12b-it", + "canonical": "openrouter/google/gemma-3-12b-it", + "recommended": false + }, + { + "provider": "openrouter", + "model": "google/gemma-3-12b-it:free", + "canonical": "openrouter/google/gemma-3-12b-it:free", + "recommended": false + }, { "provider": "openrouter", "model": "google/gemma-3-27b-it", @@ -6335,12 +7107,78 @@ "canonical": "openrouter/google/gemma-3-27b-it:free", "recommended": true }, + { + "provider": "openrouter", + "model": "google/gemma-3-4b-it", + "canonical": "openrouter/google/gemma-3-4b-it", + "recommended": false + }, + { + "provider": "openrouter", + "model": "google/gemma-3-4b-it:free", + "canonical": "openrouter/google/gemma-3-4b-it:free", + "recommended": false + }, + { + "provider": "openrouter", + "model": "google/gemma-3n-e2b-it:free", + "canonical": "openrouter/google/gemma-3n-e2b-it:free", + "recommended": false + }, + { + "provider": "openrouter", + "model": "google/gemma-3n-e4b-it", + "canonical": "openrouter/google/gemma-3n-e4b-it", + "recommended": false + }, + { + "provider": "openrouter", + "model": "google/gemma-3n-e4b-it:free", + "canonical": "openrouter/google/gemma-3n-e4b-it:free", + "recommended": false + }, + { + "provider": "openrouter", + "model": "liquid/lfm-2.5-1.2b-instruct:free", + "canonical": "openrouter/liquid/lfm-2.5-1.2b-instruct:free", + "recommended": false + }, + { + "provider": "openrouter", + "model": "liquid/lfm-2.5-1.2b-thinking:free", + "canonical": "openrouter/liquid/lfm-2.5-1.2b-thinking:free", + "recommended": false + }, + { + "provider": "openrouter", + "model": "meta-llama/llama-3.2-11b-vision-instruct", + "canonical": "openrouter/meta-llama/llama-3.2-11b-vision-instruct", + "recommended": false + }, + { + "provider": "openrouter", + "model": "meta-llama/llama-3.2-3b-instruct:free", + "canonical": "openrouter/meta-llama/llama-3.2-3b-instruct:free", + "recommended": false + }, + { + "provider": "openrouter", + "model": "meta-llama/llama-3.3-70b-instruct", + "canonical": "meta-llama/llama-3.3-70b-instruct", + "recommended": true + }, { "provider": "openrouter", "model": "meta-llama/llama-3.3-70b-instruct:free", "canonical": "openrouter/meta-llama/llama-3.3-70b-instruct:free", "recommended": true }, + { + "provider": "openrouter", + "model": "minimax/minimax-01", + "canonical": "openrouter/minimax/minimax-01", + "recommended": true + }, { "provider": "openrouter", "model": "minimax/minimax-m1", @@ -6359,6 +7197,12 @@ "canonical": "openrouter/minimax/minimax-m2.1", "recommended": true }, + { + "provider": "openrouter", + "model": "minimax/minimax-m2.5", + "canonical": "openrouter/minimax/minimax-m2.5", + "recommended": true + }, { "provider": "openrouter", "model": "mistralai/codestral-2508", @@ -6383,6 +7227,42 @@ "canonical": "openrouter/mistralai/devstral-small", "recommended": true }, + { + "provider": "openrouter", + "model": "mistralai/ministral-3b-2512", + "canonical": "mistralai/ministral-3b", + "recommended": true + }, + { + "provider": "openrouter", + "model": "mistralai/ministral-8b-2512", + "canonical": "mistralai/ministral-8b", + "recommended": true + }, + { + "provider": "openrouter", + "model": "mistralai/mistral-large", + "canonical": "mistralai/mistral-large", + "recommended": true + }, + { + "provider": "openrouter", + "model": "mistralai/mistral-large-2407", + "canonical": "mistralai/mistral-large", + "recommended": true + }, + { + "provider": "openrouter", + "model": "mistralai/mistral-large-2411", + "canonical": "mistralai/mistral-large", + "recommended": true + }, + { + "provider": "openrouter", + "model": "mistralai/mistral-large-2512", + "canonical": "mistralai/mistral-large", + "recommended": true + }, { "provider": "openrouter", "model": "mistralai/mistral-medium-3", @@ -6395,6 +7275,12 @@ "canonical": "openrouter/mistralai/mistral-medium-3.1", "recommended": true }, + { + "provider": "openrouter", + "model": "mistralai/mistral-nemo", + "canonical": "mistralai/mistral-nemo", + "recommended": true + }, { "provider": "openrouter", "model": "mistralai/mistral-small-3.1-24b-instruct", @@ -6407,6 +7293,12 @@ "canonical": "openrouter/mistralai/mistral-small-3.2-24b-instruct", "recommended": true }, + { + "provider": "openrouter", + "model": "mistralai/pixtral-large-2411", + "canonical": "mistralai/pixtral-large", + "recommended": true + }, { "provider": "openrouter", "model": "moonshotai/kimi-k2", @@ -6437,6 +7329,18 @@ "canonical": "openrouter/moonshotai/kimi-k2.5", "recommended": true }, + { + "provider": "openrouter", + "model": "nousresearch/hermes-3-llama-3.1-405b:free", + "canonical": "openrouter/nousresearch/hermes-3-llama-3.1-405b:free", + "recommended": false + }, + { + "provider": "openrouter", + "model": "nousresearch/hermes-4-405b", + "canonical": "openrouter/nousresearch/hermes-4-405b", + "recommended": true + }, { "provider": "openrouter", "model": "nousresearch/hermes-4-70b", @@ -6467,6 +7371,36 @@ "canonical": "openrouter/nvidia/nemotron-nano-9b-v2:free", "recommended": true }, + { + "provider": "openrouter", + "model": "openai/gpt-3.5-turbo", + "canonical": "openai/gpt-3.5-turbo", + "recommended": false + }, + { + "provider": "openrouter", + "model": "openai/gpt-3.5-turbo-0613", + "canonical": "openai/gpt-3.5-turbo", + "recommended": false + }, + { + "provider": "openrouter", + "model": "openai/gpt-4", + "canonical": "openai/gpt-4", + "recommended": true + }, + { + "provider": "openrouter", + "model": "openai/gpt-4-0314", + "canonical": "openai/gpt-4", + "recommended": true + }, + { + "provider": "openrouter", + "model": "openai/gpt-4-turbo", + "canonical": "openai/gpt-4-turbo", + "recommended": true + }, { "provider": "openrouter", "model": "openai/gpt-4.1", @@ -6479,6 +7413,36 @@ "canonical": "openrouter/openai/gpt-4.1-mini", "recommended": true }, + { + "provider": "openrouter", + "model": "openai/gpt-4.1-nano", + "canonical": "openai/gpt-4.1-nano", + "recommended": true + }, + { + "provider": "openrouter", + "model": "openai/gpt-4o", + "canonical": "openai/gpt-4o", + "recommended": true + }, + { + "provider": "openrouter", + "model": "openai/gpt-4o-2024-05-13", + "canonical": "openai/gpt-4o", + "recommended": true + }, + { + "provider": "openrouter", + "model": "openai/gpt-4o-2024-08-06", + "canonical": "openai/gpt-4o", + "recommended": true + }, + { + "provider": "openrouter", + "model": "openai/gpt-4o-2024-11-20", + "canonical": "openai/gpt-4o", + "recommended": true + }, { "provider": "openrouter", "model": "openai/gpt-4o-mini", @@ -6497,6 +7461,12 @@ "canonical": "openrouter/openai/gpt-5", "recommended": true }, + { + "provider": "openrouter", + "model": "openai/gpt-5-chat", + "canonical": "openrouter/openai/gpt-5-chat", + "recommended": false + }, { "provider": "openrouter", "model": "openai/gpt-5-codex", @@ -6617,12 +7587,72 @@ "canonical": "openrouter/openai/gpt-oss-safeguard-20b", "recommended": true }, + { + "provider": "openrouter", + "model": "openai/o1", + "canonical": "openai/o1", + "recommended": true + }, + { + "provider": "openrouter", + "model": "openai/o1-pro", + "canonical": "openai/o1-pro", + "recommended": true + }, + { + "provider": "openrouter", + "model": "openai/o3", + "canonical": "openai/o3", + "recommended": true + }, + { + "provider": "openrouter", + "model": "openai/o3-deep-research", + "canonical": "openai/o3-deep-research", + "recommended": true + }, + { + "provider": "openrouter", + "model": "openai/o3-mini", + "canonical": "openai/o3-mini", + "recommended": true + }, + { + "provider": "openrouter", + "model": "openai/o3-pro", + "canonical": "openai/o3-pro", + "recommended": true + }, { "provider": "openrouter", "model": "openai/o4-mini", "canonical": "openrouter/openai/o4-mini", "recommended": true }, + { + "provider": "openrouter", + "model": "openai/o4-mini-deep-research", + "canonical": "openai/o4-mini-deep-research", + "recommended": true + }, + { + "provider": "openrouter", + "model": "prime-intellect/intellect-3", + "canonical": "openrouter/prime-intellect/intellect-3", + "recommended": true + }, + { + "provider": "openrouter", + "model": "qwen/qwen-2.5-coder-32b-instruct", + "canonical": "openrouter/qwen/qwen-2.5-coder-32b-instruct", + "recommended": false + }, + { + "provider": "openrouter", + "model": "qwen/qwen2.5-vl-72b-instruct", + "canonical": "openrouter/qwen/qwen2.5-vl-72b-instruct", + "recommended": false + }, { "provider": "openrouter", "model": "qwen/qwen3-235b-a22b-thinking-2507", @@ -6703,8 +7733,26 @@ }, { "provider": "openrouter", - "model": "tngtech/tng-r1t-chimera:free", - "canonical": "openrouter/tngtech/tng-r1t-chimera:free", + "model": "qwen/qwen3.5-397b-a17b", + "canonical": "openrouter/qwen/qwen3.5-397b-a17b", + "recommended": true + }, + { + "provider": "openrouter", + "model": "qwen/qwen3.5-plus-02-15", + "canonical": "openrouter/qwen/qwen3.5-plus-02-15", + "recommended": true + }, + { + "provider": "openrouter", + "model": "stepfun/step-3.5-flash", + "canonical": "openrouter/stepfun/step-3.5-flash", + "recommended": true + }, + { + "provider": "openrouter", + "model": "stepfun/step-3.5-flash:free", + "canonical": "openrouter/stepfun/step-3.5-flash:free", "recommended": true }, { @@ -6777,7 +7825,7 @@ "provider": "openrouter", "model": "z-ai/glm-4.5-air:free", "canonical": "openrouter/z-ai/glm-4.5-air:free", - "recommended": true + "recommended": false }, { "provider": "openrouter", @@ -6809,6 +7857,12 @@ "canonical": "openrouter/z-ai/glm-4.7-flash", "recommended": true }, + { + "provider": "openrouter", + "model": "z-ai/glm-5", + "canonical": "openrouter/z-ai/glm-5", + "recommended": true + }, { "provider": "tetrate", "model": "claude-3-5-haiku-20241022", @@ -6923,6 +7977,12 @@ "canonical": "anthropic/claude-sonnet-4.5", "recommended": true }, + { + "provider": "tetrate", + "model": "claude-sonnet-4-6", + "canonical": "anthropic/claude-sonnet-4.6", + "recommended": true + }, { "provider": "tetrate", "model": "deepinfra/anthropic/claude-3-7-sonnet-latest", @@ -7001,6 +8061,42 @@ "canonical": "google/gemini-3-pro-preview", "recommended": true }, + { + "provider": "tetrate", + "model": "gemini-embedding-001", + "canonical": "google/gemini-embedding-001", + "recommended": false + }, + { + "provider": "tetrate", + "model": "gpt-3.5-turbo", + "canonical": "openai/gpt-3.5-turbo", + "recommended": false + }, + { + "provider": "tetrate", + "model": "gpt-3.5-turbo-0125", + "canonical": "openai/gpt-3.5-turbo", + "recommended": false + }, + { + "provider": "tetrate", + "model": "gpt-3.5-turbo-1106", + "canonical": "openai/gpt-3.5-turbo", + "recommended": false + }, + { + "provider": "tetrate", + "model": "gpt-4", + "canonical": "openai/gpt-4", + "recommended": true + }, + { + "provider": "tetrate", + "model": "gpt-4-0613", + "canonical": "openai/gpt-4", + "recommended": true + }, { "provider": "tetrate", "model": "gpt-4-turbo", @@ -7101,7 +8197,7 @@ "provider": "tetrate", "model": "gpt-5-chat-latest", "canonical": "openai/gpt-5-chat", - "recommended": true + "recommended": false }, { "provider": "tetrate", @@ -7387,15 +8483,15 @@ } ], "model_counts": { - "anthropic": 12, + "anthropic": 11, "aws_bedrock": 0, "azure_openai": 0, - "databricks": 163, + "databricks": 168, "gcp_vertex_ai": 0, - "google": 45, - "openai": 652, - "openrouter": 230, - "tetrate": 151, + "google": 43, + "openai": 659, + "openrouter": 337, + "tetrate": 207, "venice": 0, "xai": 13 }, @@ -7414,6 +8510,11 @@ "anthropic/claude-sonnet-4", "anthropic/claude-sonnet-4.0", "anthropic/claude-sonnet-4.5", + "anthropic/claude-sonnet-4.6", + "cohere/command-r-08", + "cohere/command-r-plus-08", + "cohere/command-r7b-12", + "deepseek/deepseek-chat", "google/gemini-1.5-flash", "google/gemini-1.5-pro", "google/gemini-2.0-flash", @@ -7432,6 +8533,11 @@ "google/gemini-flash", "google/gemini-flash-lite", "meta-llama/llama-3.3-70b-instruct", + "mistralai/ministral-3b", + "mistralai/ministral-8b", + "mistralai/mistral-large", + "mistralai/mistral-nemo", + "mistralai/pixtral-large", "openai/gpt-3.5-turbo", "openai/gpt-4", "openai/gpt-4-turbo", @@ -7479,26 +8585,43 @@ "openrouter/anthropic/claude-sonnet-4.5", "openrouter/arcee-ai/trinity-large-preview:free", "openrouter/arcee-ai/trinity-mini:free", + "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition:free", "openrouter/deepseek/deepseek-chat-v3", "openrouter/deepseek/deepseek-chat-v3.1", + "openrouter/deepseek/deepseek-r1-0528:free", + "openrouter/deepseek/deepseek-r1-distill-llama-70b", "openrouter/deepseek/deepseek-v3.1-terminus", "openrouter/deepseek/deepseek-v3.1-terminus:exacto", "openrouter/deepseek/deepseek-v3.2", + "openrouter/deepseek/deepseek-v3.2-speciale", "openrouter/google/gemini-2.0-flash-001", "openrouter/google/gemini-2.5-flash", "openrouter/google/gemini-2.5-flash-lite", "openrouter/google/gemini-2.5-flash-lite-preview-09", - "openrouter/google/gemini-2.5-flash-preview-09", "openrouter/google/gemini-2.5-pro", "openrouter/google/gemini-2.5-pro-preview-05-06", "openrouter/google/gemini-3-flash-preview", "openrouter/google/gemini-3-pro-preview", + "openrouter/google/gemma-2-9b-it", + "openrouter/google/gemma-3-12b-it", + "openrouter/google/gemma-3-12b-it:free", "openrouter/google/gemma-3-27b-it", "openrouter/google/gemma-3-27b-it:free", + "openrouter/google/gemma-3-4b-it", + "openrouter/google/gemma-3-4b-it:free", + "openrouter/google/gemma-3n-e2b-it:free", + "openrouter/google/gemma-3n-e4b-it", + "openrouter/google/gemma-3n-e4b-it:free", + "openrouter/liquid/lfm-2.5-1.2b-instruct:free", + "openrouter/liquid/lfm-2.5-1.2b-thinking:free", + "openrouter/meta-llama/llama-3.2-11b-vision-instruct", + "openrouter/meta-llama/llama-3.2-3b-instruct:free", "openrouter/meta-llama/llama-3.3-70b-instruct:free", + "openrouter/minimax/minimax-01", "openrouter/minimax/minimax-m1", "openrouter/minimax/minimax-m2", "openrouter/minimax/minimax-m2.1", + "openrouter/minimax/minimax-m2.5", "openrouter/mistralai/codestral", "openrouter/mistralai/devstral", "openrouter/mistralai/devstral-medium", @@ -7511,6 +8634,8 @@ "openrouter/moonshotai/kimi-k2-0905:exacto", "openrouter/moonshotai/kimi-k2-thinking", "openrouter/moonshotai/kimi-k2.5", + "openrouter/nousresearch/hermes-3-llama-3.1-405b:free", + "openrouter/nousresearch/hermes-4-405b", "openrouter/nousresearch/hermes-4-70b", "openrouter/nvidia/nemotron-3-nano-30b-a3b:free", "openrouter/nvidia/nemotron-nano-12b-v2-vl:free", @@ -7520,6 +8645,7 @@ "openrouter/openai/gpt-4.1-mini", "openrouter/openai/gpt-4o-mini", "openrouter/openai/gpt-5", + "openrouter/openai/gpt-5-chat", "openrouter/openai/gpt-5-codex", "openrouter/openai/gpt-5-image", "openrouter/openai/gpt-5-mini", @@ -7541,6 +8667,9 @@ "openrouter/openai/gpt-oss-20b:free", "openrouter/openai/gpt-oss-safeguard-20b", "openrouter/openai/o4-mini", + "openrouter/prime-intellect/intellect-3", + "openrouter/qwen/qwen-2.5-coder-32b-instruct", + "openrouter/qwen/qwen2.5-vl-72b-instruct", "openrouter/qwen/qwen3-235b-a22b-thinking", "openrouter/qwen/qwen3-30b-a3b-instruct", "openrouter/qwen/qwen3-30b-a3b-thinking", @@ -7554,7 +8683,10 @@ "openrouter/qwen/qwen3-next-80b-a3b-instruct", "openrouter/qwen/qwen3-next-80b-a3b-instruct:free", "openrouter/qwen/qwen3-next-80b-a3b-thinking", - "openrouter/tngtech/tng-r1t-chimera:free", + "openrouter/qwen/qwen3.5-397b-a17b", + "openrouter/qwen/qwen3.5-plus-02-15", + "openrouter/stepfun/step-3.5-flash", + "openrouter/stepfun/step-3.5-flash:free", "openrouter/x-ai/grok-3", "openrouter/x-ai/grok-3-beta", "openrouter/x-ai/grok-3-mini", @@ -7572,6 +8704,7 @@ "openrouter/z-ai/glm-4.6:exacto", "openrouter/z-ai/glm-4.7", "openrouter/z-ai/glm-4.7-flash", + "openrouter/z-ai/glm-5", "x-ai/grok-2-vision", "x-ai/grok-3", "x-ai/grok-3-fast", diff --git a/crates/goose/src/providers/canonical/data/canonical_models.json b/crates/goose/src/providers/canonical/data/canonical_models.json index 0d2320e517..4d46e28f22 100644 --- a/crates/goose/src/providers/canonical/data/canonical_models.json +++ b/crates/goose/src/providers/canonical/data/canonical_models.json @@ -1,4 +1,7895 @@ [ + { + "id": "302ai/MiniMax-M1", + "name": "MiniMax-M1", + "family": "minimax", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-16", + "last_updated": "2025-06-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.132, + "output": 1.254 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "302ai/MiniMax-M2", + "name": "MiniMax-M2", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-26", + "last_updated": "2025-10-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.33, + "output": 1.32 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "302ai/MiniMax-M2.1", + "name": "MiniMax-M2.1", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-19", + "last_updated": "2025-12-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 1000000, + "output": 131072 + } + }, + { + "id": "302ai/chatgpt-4o", + "name": "chatgpt-4o-latest", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-08-08", + "last_updated": "2024-08-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 15.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "302ai/claude-haiku-4.5", + "name": "claude-haiku-4-5-20251001", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-10-16", + "last_updated": "2025-10-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "302ai/claude-opus-4.1", + "name": "claude-opus-4-1-20250805", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "302ai/claude-opus-4.1-20250805-thinking", + "name": "claude-opus-4-1-20250805-thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-05-27", + "last_updated": "2025-05-27", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "302ai/claude-opus-4.5", + "name": "claude-opus-4-5-20251101", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-11-25", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "302ai/claude-opus-4.5-20251101-thinking", + "name": "claude-opus-4-5-20251101-thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-11-25", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "302ai/claude-sonnet-4.5", + "name": "claude-sonnet-4-5-20250929", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "302ai/claude-sonnet-4.5-20250929-thinking", + "name": "claude-sonnet-4-5-20250929-thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "302ai/deepseek-chat", + "name": "Deepseek-Chat", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-11-29", + "last_updated": "2024-11-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 0.43 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "302ai/deepseek-reasoner", + "name": "Deepseek-Reasoner", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 0.43 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "302ai/deepseek-v3.2", + "name": "deepseek-v3.2", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 0.43 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "302ai/deepseek-v3.2-thinking", + "name": "DeepSeek-V3.2-Thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 0.43 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "302ai/doubao-seed-1.6-thinking-250715", + "name": "doubao-seed-1-6-thinking-250715", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-15", + "last_updated": "2025-07-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.121, + "output": 1.21 + }, + "limit": { + "context": 256000, + "output": 16000 + } + }, + { + "id": "302ai/doubao-seed-1.6-vision-250815", + "name": "doubao-seed-1-6-vision-250815", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.114, + "output": 1.143 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "302ai/doubao-seed-1.8-251215", + "name": "doubao-seed-1-8-251215", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-18", + "last_updated": "2025-12-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.114, + "output": 0.286 + }, + "limit": { + "context": 224000, + "output": 64000 + } + }, + { + "id": "302ai/doubao-seed-code-preview-251028", + "name": "doubao-seed-code-preview-251028", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-11", + "last_updated": "2025-11-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.17, + "output": 1.14 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "302ai/gemini-2.0-flash-lite", + "name": "gemini-2.0-flash-lite", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2025-06-16", + "last_updated": "2025-06-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.3 + }, + "limit": { + "context": 2000000, + "output": 8192 + } + }, + { + "id": "302ai/gemini-2.5-flash", + "name": "gemini-2.5-flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "302ai/gemini-2.5-flash-image", + "name": "gemini-2.5-flash-image", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-10-08", + "last_updated": "2025-10-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 30.0 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "302ai/gemini-2.5-flash-lite-preview-09", + "name": "gemini-2.5-flash-lite-preview-09-2025", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-09-26", + "last_updated": "2025-09-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "302ai/gemini-2.5-flash-nothink", + "name": "gemini-2.5-flash-nothink", + "family": "gemini-flash", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-24", + "last_updated": "2025-06-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "302ai/gemini-2.5-flash-preview-09", + "name": "gemini-2.5-flash-preview-09-2025", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-09-26", + "last_updated": "2025-09-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "302ai/gemini-2.5-pro", + "name": "gemini-2.5-pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "302ai/gemini-3-flash-preview", + "name": "gemini-3-flash-preview", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-12-18", + "last_updated": "2025-12-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "302ai/gemini-3-pro-image-preview", + "name": "gemini-3-pro-image-preview", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-11-20", + "last_updated": "2025-11-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 120.0 + }, + "limit": { + "context": 32768, + "output": 64000 + } + }, + { + "id": "302ai/gemini-3-pro-preview", + "name": "gemini-3-pro-preview", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "302ai/glm-4.5", + "name": "GLM-4.5", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-29", + "last_updated": "2025-07-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.286, + "output": 1.142 + }, + "limit": { + "context": 128000, + "output": 98304 + } + }, + { + "id": "302ai/glm-4.5v", + "name": "GLM-4.5V", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-29", + "last_updated": "2025-07-29", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 0.86 + }, + "limit": { + "context": 64000, + "output": 16384 + } + }, + { + "id": "302ai/glm-4.6", + "name": "glm-4.6", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.286, + "output": 1.142 + }, + "limit": { + "context": 200000, + "output": 131072 + } + }, + { + "id": "302ai/glm-4.6v", + "name": "GLM-4.6V", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.145, + "output": 0.43 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "302ai/glm-4.7", + "name": "glm-4.7", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.286, + "output": 1.142 + }, + "limit": { + "context": 200000, + "output": 131072 + } + }, + { + "id": "302ai/gpt-4.1", + "name": "gpt-4.1", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "302ai/gpt-4.1-mini", + "name": "gpt-4.1-mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.6 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "302ai/gpt-4.1-nano", + "name": "gpt-4.1-nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "302ai/gpt-4o", + "name": "gpt-4o", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-05-13", + "last_updated": "2024-05-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "302ai/gpt-5", + "name": "gpt-5", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-08", + "last_updated": "2025-08-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "302ai/gpt-5-mini", + "name": "gpt-5-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-08", + "last_updated": "2025-08-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "302ai/gpt-5-pro", + "name": "gpt-5-pro", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-10-08", + "last_updated": "2025-10-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 120.0 + }, + "limit": { + "context": 400000, + "output": 272000 + } + }, + { + "id": "302ai/gpt-5-thinking", + "name": "gpt-5-thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-08", + "last_updated": "2025-08-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "302ai/gpt-5.1", + "name": "gpt-5.1", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "302ai/gpt-5.1-chat", + "name": "gpt-5.1-chat-latest", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "302ai/gpt-5.2", + "name": "gpt-5.2", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-12-12", + "last_updated": "2025-12-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "302ai/gpt-5.2-chat", + "name": "gpt-5.2-chat-latest", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-12-12", + "last_updated": "2025-12-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "302ai/grok-4-fast", + "name": "grok-4-fast-reasoning", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "302ai/grok-4-fast-non", + "name": "grok-4-fast-non-reasoning", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "302ai/grok-4.1", + "name": "grok-4.1", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 10.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "302ai/grok-4.1-fast", + "name": "grok-4-1-fast-reasoning", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-11-20", + "last_updated": "2025-11-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "302ai/grok-4.1-fast-non", + "name": "grok-4-1-fast-non-reasoning", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-11-20", + "last_updated": "2025-11-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "302ai/kimi-k2-0905-preview", + "name": "kimi-k2-0905-preview", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.632, + "output": 2.53 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "302ai/kimi-k2-thinking", + "name": "kimi-k2-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.575, + "output": 2.3 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "302ai/kimi-k2-thinking-turbo", + "name": "kimi-k2-thinking-turbo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.265, + "output": 9.119 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "302ai/ministral-14b", + "name": "ministral-14b-2512", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-12-16", + "last_updated": "2025-12-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.33, + "output": 0.33 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "302ai/mistral-large", + "name": "mistral-large-2512", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-12-16", + "last_updated": "2025-12-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 3.3 + }, + "limit": { + "context": 128000, + "output": 262144 + } + }, + { + "id": "302ai/qwen-flash", + "name": "Qwen-Flash", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.022, + "output": 0.22 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "302ai/qwen-max", + "name": "Qwen-Max-Latest", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2024-04-03", + "last_updated": "2025-01-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.343, + "output": 1.372 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "302ai/qwen-plus", + "name": "Qwen-Plus", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.12, + "output": 1.2 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "302ai/qwen3-235b-a22b", + "name": "Qwen3-235B-A22B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04-29", + "last_updated": "2025-04-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 2.86 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "302ai/qwen3-235b-a22b-instruct", + "name": "qwen3-235b-a22b-instruct-2507", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 1.143 + }, + "limit": { + "context": 128000, + "output": 65536 + } + }, + { + "id": "302ai/qwen3-30b-a3b", + "name": "Qwen3-30B-A3B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04-29", + "last_updated": "2025-04-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.11, + "output": 1.08 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "302ai/qwen3-coder-480b-a35b-instruct", + "name": "qwen3-coder-480b-a35b-instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.86, + "output": 3.43 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "302ai/qwen3-max", + "name": "qwen3-max-2025-09-23", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-24", + "last_updated": "2025-09-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.86, + "output": 3.43 + }, + "limit": { + "context": 258048, + "output": 65536 + } + }, + { + "id": "abacus/Qwen/QwQ-32B", + "name": "QwQ 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-28", + "last_updated": "2024-11-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 0.4 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "abacus/Qwen/Qwen2.5-72B-Instruct", + "name": "Qwen 2.5 72B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-19", + "last_updated": "2024-09-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.11, + "output": 0.38 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "abacus/Qwen/Qwen3-235B-A22B-Instruct", + "name": "Qwen3 235B A22B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-01", + "last_updated": "2025-07-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.6 + }, + "limit": { + "context": 262144, + "output": 8192 + } + }, + { + "id": "abacus/Qwen/Qwen3-32B", + "name": "Qwen3 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-29", + "last_updated": "2025-04-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.29 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "abacus/Qwen/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-22", + "last_updated": "2025-07-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.29, + "output": 1.2 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "abacus/claude-3.7-sonnet", + "name": "Claude Sonnet 3.7", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10-31", + "release_date": "2025-02-19", + "last_updated": "2025-02-19", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "abacus/claude-haiku-4.5", + "name": "Claude Haiku 4.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "abacus/claude-opus-4", + "name": "Claude Opus 4", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-14", + "last_updated": "2025-05-14", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "abacus/claude-opus-4.1", + "name": "Claude Opus 4.1", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "abacus/claude-opus-4.5", + "name": "Claude Opus 4.5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-11-01", + "last_updated": "2025-11-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "abacus/claude-sonnet-4", + "name": "Claude Sonnet 4", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-14", + "last_updated": "2025-05-14", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "abacus/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "abacus/deepseek-ai/DeepSeek-R1", + "name": "DeepSeek R1", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 7.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "abacus/deepseek-ai/DeepSeek-V3.1-Terminus", + "name": "DeepSeek V3.1 Terminus", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-01", + "last_updated": "2025-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "abacus/deepseek-ai/DeepSeek-V3.2", + "name": "DeepSeek V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-15", + "last_updated": "2025-06-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 0.4 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "abacus/deepseek/deepseek-v3.1", + "name": "DeepSeek V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "abacus/gemini-2.0-flash-001", + "name": "Gemini 2.0 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-02-05", + "last_updated": "2025-02-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 1000000, + "output": 8192 + } + }, + { + "id": "abacus/gemini-2.0-pro-exp-02-05", + "name": "Gemini 2.0 Pro Exp", + "family": "gemini-pro", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-02-05", + "last_updated": "2025-02-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 2000000, + "output": 8192 + } + }, + { + "id": "abacus/gemini-2.5-flash", + "name": "Gemini 2.5 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-20", + "last_updated": "2025-06-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "abacus/gemini-2.5-pro", + "name": "Gemini 2.5 Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-25", + "last_updated": "2025-03-25", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "abacus/gemini-3-flash-preview", + "name": "Gemini 3 Flash Preview", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "abacus/gemini-3-pro-preview", + "name": "Gemini 3 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-01", + "last_updated": "2025-06-01", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0 + }, + "limit": { + "context": 1000000, + "output": 65000 + } + }, + { + "id": "abacus/gpt-4.1", + "name": "GPT-4.1", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "abacus/gpt-4.1-mini", + "name": "GPT-4.1 Mini", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.6 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "abacus/gpt-4.1-nano", + "name": "GPT-4.1 Nano", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "abacus/gpt-4o", + "name": "GPT-4o (2024-11-20)", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-11-20", + "last_updated": "2024-11-20", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "abacus/gpt-4o-mini", + "name": "GPT-4o Mini", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "abacus/gpt-5", + "name": "GPT-5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "abacus/gpt-5-mini", + "name": "GPT-5 Mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "abacus/gpt-5-nano", + "name": "GPT-5 Nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "abacus/gpt-5.1", + "name": "GPT-5.1", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "abacus/gpt-5.1-chat", + "name": "GPT-5.1 Chat Latest", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "abacus/gpt-5.2", + "name": "GPT-5.2", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "abacus/gpt-5.2-chat", + "name": "GPT-5.2 Chat Latest", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09-30", + "release_date": "2026-01-01", + "last_updated": "2026-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 12.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "abacus/grok-4", + "name": "Grok 4", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 256000, + "output": 16384 + } + }, + { + "id": "abacus/grok-4-fast-non", + "name": "Grok 4 Fast (Non-Reasoning)", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5 + }, + "limit": { + "context": 2000000, + "output": 16384 + } + }, + { + "id": "abacus/grok-4.1-fast-non", + "name": "Grok 4.1 Fast (Non-Reasoning)", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-17", + "last_updated": "2025-11-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5 + }, + "limit": { + "context": 2000000, + "output": 16384 + } + }, + { + "id": "abacus/grok-code-fast-1", + "name": "Grok Code Fast 1", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.5 + }, + "limit": { + "context": 256000, + "output": 16384 + } + }, + { + "id": "abacus/kimi-k2-turbo-preview", + "name": "Kimi K2 Turbo Preview", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-08", + "last_updated": "2025-07-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 8.0 + }, + "limit": { + "context": 256000, + "output": 8192 + } + }, + { + "id": "abacus/llama-3.3-70b-versatile", + "name": "Llama 3.3 70B Versatile", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.59, + "output": 0.79 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "abacus/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", + "name": "Llama 4 Maverick 17B 128E Instruct FP8", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.59 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "abacus/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", + "name": "Llama 3.1 405B Instruct Turbo", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.5, + "output": 3.5 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "abacus/meta-llama/Meta-Llama-3.1-70B-Instruct", + "name": "Llama 3.1 70B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 0.4 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "abacus/meta-llama/Meta-Llama-3.1-8B-Instruct", + "name": "Llama 3.1 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.05 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "abacus/o3", + "name": "o3", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "abacus/o3-mini", + "name": "o3-mini", + "family": "o-mini", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2024-12-20", + "last_updated": "2025-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "abacus/o3-pro", + "name": "o3-pro", + "family": "o-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-06-10", + "last_updated": "2025-06-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 20.0, + "output": 80.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "abacus/o4-mini", + "name": "o4-mini", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "abacus/openai/gpt-oss-120b", + "name": "GPT-OSS 120B", + "family": "gpt-oss", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.44 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "abacus/qwen-2.5-coder-32b", + "name": "Qwen 2.5 Coder 32B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-11", + "last_updated": "2024-11-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.79, + "output": 0.79 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "abacus/qwen3-max", + "name": "Qwen3 Max", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-28", + "last_updated": "2025-05-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 6.0 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "abacus/route-llm", + "name": "Route LLM", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-01-01", + "last_updated": "2024-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.5 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "abacus/zai-org/glm-4.5", + "name": "GLM-4.5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "abacus/zai-org/glm-4.6", + "name": "GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-01", + "last_updated": "2025-03-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "abacus/zai-org/glm-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-01", + "last_updated": "2025-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.5 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "aihubmix/Kimi-K2", + "name": "Kimi K2 0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.19 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "aihubmix/claude-haiku-4.5", + "name": "Claude Haiku 4.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 5.5, + "cache_read": 0.11, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "aihubmix/claude-opus-4.1", + "name": "Claude Opus 4.1", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 16.5, + "output": 82.5, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "aihubmix/claude-opus-4.5", + "name": "Claude Opus 4.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-11-25", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "aihubmix/claude-opus-4.6", + "name": "Claude Opus 4.6", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "aihubmix/claude-opus-4.6-think", + "name": "Claude Opus 4.6 Think", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "aihubmix/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.3, + "output": 16.5, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "aihubmix/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "aihubmix/claude-sonnet-4.6-think", + "name": "Claude Sonnet 4.6 Think", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "aihubmix/coding-glm-4.7", + "name": "Coding-GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.1, + "cache_read": 0.548 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "aihubmix/coding-glm-4.7-free", + "name": "Coding GLM 4.7 Free", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "aihubmix/coding-minimax-m2.1-free", + "name": "Coding MiniMax M2.1 Free", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "aihubmix/deepseek-v3.2", + "name": "DeepSeek-V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.45 + }, + "limit": { + "context": 131000, + "output": 64000 + } + }, + { + "id": "aihubmix/deepseek-v3.2-fast", + "name": "DeepSeek-V3.2-Fast", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": false, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.1, + "output": 3.29 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "aihubmix/deepseek-v3.2-think", + "name": "DeepSeek-V3.2-Think", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.45 + }, + "limit": { + "context": 131000, + "output": 64000 + } + }, + { + "id": "aihubmix/gemini-2.5-flash", + "name": "Gemini 2.5 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.3, + "cache_read": 0.02 + }, + "limit": { + "context": 1000000, + "output": 65000 + } + }, + { + "id": "aihubmix/gemini-2.5-pro", + "name": "Gemini 2.5 Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 5.0, + "cache_read": 0.31 + }, + "limit": { + "context": 2000000, + "output": 65000 + } + }, + { + "id": "aihubmix/gemini-3-pro-preview", + "name": "Gemini 3 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1000000, + "output": 65000 + } + }, + { + "id": "aihubmix/gemini-3-pro-preview-search", + "name": "Gemini 3 Pro Preview Search", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1000000, + "output": 65000 + } + }, + { + "id": "aihubmix/glm-4.6v", + "name": "GLM-4.6V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.41 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "aihubmix/glm-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.1, + "cache_read": 0.548 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "aihubmix/gpt-4.1", + "name": "GPT-4.1", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "aihubmix/gpt-4.1-mini", + "name": "GPT-4.1 mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.6, + "cache_read": 0.1 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "aihubmix/gpt-4.1-nano", + "name": "GPT-4.1 nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.03 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "aihubmix/gpt-4o", + "name": "GPT-4o", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-05-13", + "last_updated": "2024-08-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0, + "cache_read": 1.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "aihubmix/gpt-5", + "name": "GPT-5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09-30", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 20.0, + "cache_read": 2.5 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "aihubmix/gpt-5-codex", + "name": "GPT-5-Codex", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "aihubmix/gpt-5-mini", + "name": "GPT-5-Mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09-30", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 6.0, + "cache_read": 0.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "aihubmix/gpt-5-nano", + "name": "GPT-5-Nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09-30", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 2.0, + "cache_read": 0.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "aihubmix/gpt-5-pro", + "name": "GPT-5-Pro", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09-30", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 7.0, + "output": 28.0, + "cache_read": 3.5 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "aihubmix/gpt-5.1", + "name": "GPT-5.1", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-15", + "last_updated": "2025-11-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "aihubmix/gpt-5.1-codex", + "name": "GPT-5.1 Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-15", + "last_updated": "2025-11-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "aihubmix/gpt-5.1-codex-max", + "name": "GPT-5.1-Codex-Max", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "aihubmix/gpt-5.1-codex-mini", + "name": "GPT-5.1 Codex Mini", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-15", + "last_updated": "2025-11-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.03 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "aihubmix/gpt-5.2", + "name": "GPT-5.2", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "aihubmix/gpt-5.2-codex", + "name": "GPT-5.2-Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2026-01-14", + "last_updated": "2026-01-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "aihubmix/kimi-k2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0, + "cache_read": 0.1 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "aihubmix/minimax-m2.1", + "name": "MiniMax M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.29, + "output": 1.15 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "aihubmix/o4-mini", + "name": "o4-mini", + "family": "o-mini", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": false, + "knowledge": "2024-09", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 6.0, + "cache_read": 0.75 + }, + "limit": { + "context": 200000, + "output": 65536 + } + }, + { + "id": "aihubmix/qwen3-235b-a22b-instruct", + "name": "Qwen3 235B A22B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.28, + "output": 1.12 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "aihubmix/qwen3-235b-a22b-thinking", + "name": "Qwen3 235B A22B Thinking 2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.28, + "output": 2.8 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "aihubmix/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-01", + "last_updated": "2025-08-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.82, + "output": 3.29 + }, + "limit": { + "context": 262144, + "output": 131000 + } + }, + { + "id": "aihubmix/qwen3-max", + "name": "Qwen3 Max", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.34, + "output": 1.37 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "alibaba-cn/deepseek-r1", + "name": "DeepSeek R1", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.574, + "output": 2.294 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "alibaba-cn/deepseek-r1-distill-llama-70b", + "name": "DeepSeek R1 Distill Llama 70B", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.287, + "output": 0.861 + }, + "limit": { + "context": 32768, + "output": 16384 + } + }, + { + "id": "alibaba-cn/deepseek-r1-distill-llama-8b", + "name": "DeepSeek R1 Distill Llama 8B", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 16384 + } + }, + { + "id": "alibaba-cn/deepseek-r1-distill-qwen-1-5b", + "name": "DeepSeek R1 Distill Qwen 1.5B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 16384 + } + }, + { + "id": "alibaba-cn/deepseek-r1-distill-qwen-14b", + "name": "DeepSeek R1 Distill Qwen 14B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.144, + "output": 0.431 + }, + "limit": { + "context": 32768, + "output": 16384 + } + }, + { + "id": "alibaba-cn/deepseek-r1-distill-qwen-32b", + "name": "DeepSeek R1 Distill Qwen 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.287, + "output": 0.861 + }, + "limit": { + "context": 32768, + "output": 16384 + } + }, + { + "id": "alibaba-cn/deepseek-r1-distill-qwen-7b", + "name": "DeepSeek R1 Distill Qwen 7B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.072, + "output": 0.144 + }, + "limit": { + "context": 32768, + "output": 16384 + } + }, + { + "id": "alibaba-cn/deepseek-v3", + "name": "DeepSeek V3", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-01", + "last_updated": "2024-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.287, + "output": 1.147 + }, + "limit": { + "context": 65536, + "output": 8192 + } + }, + { + "id": "alibaba-cn/deepseek-v3-1", + "name": "DeepSeek V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.574, + "output": 1.721 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "alibaba-cn/deepseek-v3-2-exp", + "name": "DeepSeek V3.2 Exp", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.287, + "output": 0.431 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "alibaba-cn/kimi-k2-thinking", + "name": "Moonshot Kimi K2 Thinking", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.574, + "output": 2.294 + }, + "limit": { + "context": 262144, + "output": 16384 + } + }, + { + "id": "alibaba-cn/kimi-k2.5", + "name": "Moonshot Kimi K2.5", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-27", + "last_updated": "2025-01-27", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.574, + "output": 2.411 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "alibaba-cn/moonshot-kimi-k2-instruct", + "name": "Moonshot Kimi K2 Instruct", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.574, + "output": 2.294 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qvq-max", + "name": "QVQ Max", + "family": "qvq", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-03-25", + "last_updated": "2025-03-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.147, + "output": 4.588 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen-deep-research", + "name": "Qwen Deep Research", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-01", + "last_updated": "2024-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 7.742, + "output": 23.367 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "alibaba-cn/qwen-doc-turbo", + "name": "Qwen Doc Turbo", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-01", + "last_updated": "2024-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.087, + "output": 0.144 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen-flash", + "name": "Qwen Flash", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.022, + "output": 0.216 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "alibaba-cn/qwen-long", + "name": "Qwen Long", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-01-25", + "last_updated": "2025-01-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.072, + "output": 0.287 + }, + "limit": { + "context": 10000000, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen-math-plus", + "name": "Qwen Math Plus", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-08-16", + "last_updated": "2024-09-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.574, + "output": 1.721 + }, + "limit": { + "context": 4096, + "output": 3072 + } + }, + { + "id": "alibaba-cn/qwen-math-turbo", + "name": "Qwen Math Turbo", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09-19", + "last_updated": "2024-09-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.287, + "output": 0.861 + }, + "limit": { + "context": 4096, + "output": 3072 + } + }, + { + "id": "alibaba-cn/qwen-max", + "name": "Qwen Max", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-04-03", + "last_updated": "2025-01-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.345, + "output": 1.377 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen-mt-plus", + "name": "Qwen-MT Plus", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-01", + "last_updated": "2025-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.259, + "output": 0.775 + }, + "limit": { + "context": 16384, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen-mt-turbo", + "name": "Qwen-MT Turbo", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-01", + "last_updated": "2025-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.101, + "output": 0.28 + }, + "limit": { + "context": 16384, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen-omni-turbo", + "name": "Qwen-Omni Turbo", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-01-19", + "last_updated": "2025-03-26", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 0.058, + "output": 0.23 + }, + "limit": { + "context": 32768, + "output": 2048 + } + }, + { + "id": "alibaba-cn/qwen-omni-turbo-realtime", + "name": "Qwen-Omni Turbo Realtime", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-05-08", + "last_updated": "2025-05-08", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 0.23, + "output": 0.918 + }, + "limit": { + "context": 32768, + "output": 2048 + } + }, + { + "id": "alibaba-cn/qwen-plus", + "name": "Qwen Plus", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-01-25", + "last_updated": "2025-09-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.115, + "output": 0.287 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "alibaba-cn/qwen-plus-character", + "name": "Qwen Plus Character", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-01", + "last_updated": "2024-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.115, + "output": 0.287 + }, + "limit": { + "context": 32768, + "output": 4096 + } + }, + { + "id": "alibaba-cn/qwen-turbo", + "name": "Qwen Turbo", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-11-01", + "last_updated": "2025-07-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.044, + "output": 0.087 + }, + "limit": { + "context": 1000000, + "output": 16384 + } + }, + { + "id": "alibaba-cn/qwen-vl-max", + "name": "Qwen-VL Max", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-04-08", + "last_updated": "2025-08-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.23, + "output": 0.574 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen-vl-ocr", + "name": "Qwen-VL OCR", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-10-28", + "last_updated": "2025-04-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.717, + "output": 0.717 + }, + "limit": { + "context": 34096, + "output": 4096 + } + }, + { + "id": "alibaba-cn/qwen-vl-plus", + "name": "Qwen-VL Plus", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-01-25", + "last_updated": "2025-08-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.115, + "output": 0.287 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen2-5-14b-instruct", + "name": "Qwen2.5 14B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.144, + "output": 0.431 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen2-5-32b-instruct", + "name": "Qwen2.5 32B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.287, + "output": 0.861 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen2-5-72b-instruct", + "name": "Qwen2.5 72B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.574, + "output": 1.721 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen2-5-7b-instruct", + "name": "Qwen2.5 7B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.072, + "output": 0.144 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen2-5-coder-32b-instruct", + "name": "Qwen2.5-Coder 32B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-11", + "last_updated": "2024-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.287, + "output": 0.861 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen2-5-coder-7b-instruct", + "name": "Qwen2.5-Coder 7B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-11", + "last_updated": "2024-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.144, + "output": 0.287 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen2-5-math-72b-instruct", + "name": "Qwen2.5-Math 72B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.574, + "output": 1.721 + }, + "limit": { + "context": 4096, + "output": 3072 + } + }, + { + "id": "alibaba-cn/qwen2-5-math-7b-instruct", + "name": "Qwen2.5-Math 7B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.144, + "output": 0.287 + }, + "limit": { + "context": 4096, + "output": 3072 + } + }, + { + "id": "alibaba-cn/qwen2-5-omni-7b", + "name": "Qwen2.5-Omni 7B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-12", + "last_updated": "2024-12", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": true, + "cost": { + "input": 0.087, + "output": 0.345 + }, + "limit": { + "context": 32768, + "output": 2048 + } + }, + { + "id": "alibaba-cn/qwen2-5-vl-72b-instruct", + "name": "Qwen2.5-VL 72B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.294, + "output": 6.881 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen2-5-vl-7b-instruct", + "name": "Qwen2.5-VL 7B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.287, + "output": 0.717 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen3-14b", + "name": "Qwen3 14B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.144, + "output": 0.574 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen3-235b-a22b", + "name": "Qwen3 235B-A22B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.287, + "output": 1.147 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "alibaba-cn/qwen3-32b", + "name": "Qwen3 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.287, + "output": 1.147 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "alibaba-cn/qwen3-8b", + "name": "Qwen3 8B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.072, + "output": 0.287 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwen3-asr-flash", + "name": "Qwen3-ASR Flash", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-04", + "release_date": "2025-09-08", + "last_updated": "2025-09-08", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.032, + "output": 0.032 + }, + "limit": { + "context": 53248, + "output": 4096 + } + }, + { + "id": "alibaba-cn/qwen3-coder-30b-a3b-instruct", + "name": "Qwen3-Coder 30B-A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.216, + "output": 0.861 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "alibaba-cn/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3-Coder 480B-A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.861, + "output": 3.441 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "alibaba-cn/qwen3-coder-flash", + "name": "Qwen3 Coder Flash", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.144, + "output": 0.574 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "alibaba-cn/qwen3-coder-plus", + "name": "Qwen3 Coder Plus", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 5.0 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "alibaba-cn/qwen3-max", + "name": "Qwen3 Max", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.861, + "output": 3.441 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "alibaba-cn/qwen3-next-80b-a3b-instruct", + "name": "Qwen3-Next 80B-A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09", + "last_updated": "2025-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.144, + "output": 0.574 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "alibaba-cn/qwen3-next-80b-a3b-thinking", + "name": "Qwen3-Next 80B-A3B (Thinking)", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09", + "last_updated": "2025-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.144, + "output": 1.434 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "alibaba-cn/qwen3-omni-flash", + "name": "Qwen3-Omni Flash", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 0.058, + "output": 0.23 + }, + "limit": { + "context": 65536, + "output": 16384 + } + }, + { + "id": "alibaba-cn/qwen3-omni-flash-realtime", + "name": "Qwen3-Omni Flash Realtime", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 0.23, + "output": 0.918 + }, + "limit": { + "context": 65536, + "output": 16384 + } + }, + { + "id": "alibaba-cn/qwen3-vl-235b-a22b", + "name": "Qwen3-VL 235B-A22B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.286705, + "output": 1.14682 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "alibaba-cn/qwen3-vl-30b-a3b", + "name": "Qwen3-VL 30B-A3B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.108, + "output": 0.431 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "alibaba-cn/qwen3-vl-plus", + "name": "Qwen3-VL Plus", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.143353, + "output": 1.433525 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "alibaba-cn/qwen3.5-397b-a17b", + "name": "Qwen3.5 397B-A17B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.43, + "output": 2.58 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "alibaba-cn/qwen3.5-plus", + "name": "Qwen3.5 Plus", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.573, + "output": 3.44 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "alibaba-cn/qwq-32b", + "name": "QwQ 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-12", + "last_updated": "2024-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.287, + "output": 0.861 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/qwq-plus", + "name": "QwQ Plus", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-03-05", + "last_updated": "2025-03-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.23, + "output": 0.574 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba-cn/tongyi-intent-detect-v3", + "name": "Tongyi Intent Detect V3", + "family": "yi", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-01", + "last_updated": "2024-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.058, + "output": 0.144 + }, + "limit": { + "context": 8192, + "output": 1024 + } + }, + { + "id": "alibaba/qvq-max", + "name": "QVQ Max", + "family": "qvq", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-03-25", + "last_updated": "2025-03-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 4.8 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba/qwen-flash", + "name": "Qwen Flash", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "alibaba/qwen-max", + "name": "Qwen Max", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-04-03", + "last_updated": "2025-01-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.6, + "output": 6.4 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "alibaba/qwen-mt-plus", + "name": "Qwen-MT Plus", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-01", + "last_updated": "2025-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.46, + "output": 7.37 + }, + "limit": { + "context": 16384, + "output": 8192 + } + }, + { + "id": "alibaba/qwen-mt-turbo", + "name": "Qwen-MT Turbo", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-01", + "last_updated": "2025-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.16, + "output": 0.49 + }, + "limit": { + "context": 16384, + "output": 8192 + } + }, + { + "id": "alibaba/qwen-omni-turbo", + "name": "Qwen-Omni Turbo", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-01-19", + "last_updated": "2025-03-26", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.27 + }, + "limit": { + "context": 32768, + "output": 2048 + } + }, + { + "id": "alibaba/qwen-omni-turbo-realtime", + "name": "Qwen-Omni Turbo Realtime", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-05-08", + "last_updated": "2025-05-08", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 1.07 + }, + "limit": { + "context": 32768, + "output": 2048 + } + }, + { + "id": "alibaba/qwen-plus", + "name": "Qwen Plus", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-01-25", + "last_updated": "2025-09-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.2 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "alibaba/qwen-plus-character-ja", + "name": "Qwen Plus Character (Japanese)", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-01", + "last_updated": "2024-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.4 + }, + "limit": { + "context": 8192, + "output": 512 + } + }, + { + "id": "alibaba/qwen-turbo", + "name": "Qwen Turbo", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-11-01", + "last_updated": "2025-04-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.2 + }, + "limit": { + "context": 1000000, + "output": 16384 + } + }, + { + "id": "alibaba/qwen-vl-max", + "name": "Qwen-VL Max", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-04-08", + "last_updated": "2025-08-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 3.2 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba/qwen-vl-ocr", + "name": "Qwen-VL OCR", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-10-28", + "last_updated": "2025-04-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.72, + "output": 0.72 + }, + "limit": { + "context": 34096, + "output": 4096 + } + }, + { + "id": "alibaba/qwen-vl-plus", + "name": "Qwen-VL Plus", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-01-25", + "last_updated": "2025-08-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.21, + "output": 0.63 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba/qwen2-5-14b-instruct", + "name": "Qwen2.5 14B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 1.4 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba/qwen2-5-32b-instruct", + "name": "Qwen2.5 32B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.8 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba/qwen2-5-72b-instruct", + "name": "Qwen2.5 72B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 5.6 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba/qwen2-5-7b-instruct", + "name": "Qwen2.5 7B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.175, + "output": 0.7 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba/qwen2-5-omni-7b", + "name": "Qwen2.5-Omni 7B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-12", + "last_updated": "2024-12", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 32768, + "output": 2048 + } + }, + { + "id": "alibaba/qwen2-5-vl-72b-instruct", + "name": "Qwen2.5-VL 72B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.8, + "output": 8.4 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba/qwen2-5-vl-7b-instruct", + "name": "Qwen2.5-VL 7B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 1.05 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba/qwen3-14b", + "name": "Qwen3 14B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 1.4 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba/qwen3-235b-a22b", + "name": "Qwen3 235B-A22B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.8 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "alibaba/qwen3-32b", + "name": "Qwen3 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.8 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "alibaba/qwen3-8b", + "name": "Qwen3 8B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.18, + "output": 0.7 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "alibaba/qwen3-asr-flash", + "name": "Qwen3-ASR Flash", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-04", + "release_date": "2025-09-08", + "last_updated": "2025-09-08", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.035, + "output": 0.035 + }, + "limit": { + "context": 53248, + "output": 4096 + } + }, + { + "id": "alibaba/qwen3-coder-30b-a3b-instruct", + "name": "Qwen3-Coder 30B-A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 2.25 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "alibaba/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3-Coder 480B-A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.5, + "output": 7.5 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "alibaba/qwen3-coder-flash", + "name": "Qwen3 Coder Flash", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.5 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "alibaba/qwen3-coder-plus", + "name": "Qwen3 Coder Plus", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 5.0 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "alibaba/qwen3-livetranslate-flash-realtime", + "name": "Qwen3-LiveTranslate Flash Realtime", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-09-22", + "last_updated": "2025-09-22", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 10.0 + }, + "limit": { + "context": 53248, + "output": 4096 + } + }, + { + "id": "alibaba/qwen3-max", + "name": "Qwen3 Max", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 6.0 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "alibaba/qwen3-next-80b-a3b-instruct", + "name": "Qwen3-Next 80B-A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09", + "last_updated": "2025-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 2.0 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "alibaba/qwen3-next-80b-a3b-thinking", + "name": "Qwen3-Next 80B-A3B (Thinking)", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09", + "last_updated": "2025-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 6.0 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "alibaba/qwen3-omni-flash", + "name": "Qwen3-Omni Flash", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 0.43, + "output": 1.66 + }, + "limit": { + "context": 65536, + "output": 16384 + } + }, + { + "id": "alibaba/qwen3-omni-flash-realtime", + "name": "Qwen3-Omni Flash Realtime", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 0.52, + "output": 1.99 + }, + "limit": { + "context": 65536, + "output": 16384 + } + }, + { + "id": "alibaba/qwen3-vl-235b-a22b", + "name": "Qwen3-VL 235B-A22B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.8 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "alibaba/qwen3-vl-30b-a3b", + "name": "Qwen3-VL 30B-A3B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "alibaba/qwen3-vl-plus", + "name": "Qwen3-VL Plus", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.6 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "alibaba/qwen3.5-397b-a17b", + "name": "Qwen3.5 397B-A17B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.6 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "alibaba/qwen3.5-plus", + "name": "Qwen3.5 Plus", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.4 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "alibaba/qwq-plus", + "name": "QwQ Plus", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-03-05", + "last_updated": "2025-03-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 2.4 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, { "id": "amazon-bedrock/ai21.jamba-1.5-large-v1:0", "name": "Jamba 1.5 Large", @@ -753,6 +8644,39 @@ "output": 64000 } }, + { + "id": "amazon-bedrock/anthropic.claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, { "id": "amazon-bedrock/anthropic.claude-v2", "name": "Claude 2", @@ -985,6 +8909,35 @@ "output": 81920 } }, + { + "id": "amazon-bedrock/deepseek.v3.2-v1:0", + "name": "DeepSeek-V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2026-02-15", + "last_updated": "2026-02-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.62, + "output": 1.85 + }, + "limit": { + "context": 163840, + "output": 81920 + } + }, { "id": "amazon-bedrock/eu.anthropic.claude-haiku-4.5-20251001-v1:0", "name": "Claude Haiku 4.5 (EU)", @@ -1150,6 +9103,39 @@ "output": 64000 } }, + { + "id": "amazon-bedrock/eu.anthropic.claude-sonnet-4.6", + "name": "Claude Sonnet 4.6 (EU)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, { "id": "amazon-bedrock/global.anthropic.claude-haiku-4.5-20251001-v1:0", "name": "Claude Haiku 4.5 (Global)", @@ -1315,6 +9301,39 @@ "output": 64000 } }, + { + "id": "amazon-bedrock/global.anthropic.claude-sonnet-4.6", + "name": "Claude Sonnet 4.6 (Global)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, { "id": "amazon-bedrock/google.gemma-3-12b-it", "name": "Google Gemma 3 12B", @@ -2609,6 +10628,39 @@ "output": 64000 } }, + { + "id": "amazon-bedrock/us.anthropic.claude-sonnet-4.6", + "name": "Claude Sonnet 4.6 (US)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, { "id": "amazon-bedrock/writer.palmyra-x4-v1:0", "name": "Palmyra X4", @@ -2890,7 +10942,7 @@ }, { "id": "anthropic/claude-3.7-sonnet", - "name": "Claude Sonnet 3.7", + "name": "Claude Sonnet 3.7 (latest)", "family": "claude-sonnet", "attachment": true, "reasoning": true, @@ -2923,7 +10975,7 @@ }, { "id": "anthropic/claude-haiku-4.5", - "name": "Claude Haiku 4.5 (latest)", + "name": "Claude Haiku 4.5", "family": "claude-haiku", "attachment": true, "reasoning": true, @@ -3055,15 +11107,15 @@ }, { "id": "anthropic/claude-opus-4.5", - "name": "Claude Opus 4.5 (latest)", + "name": "Claude Opus 4.5", "family": "claude-opus", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, "knowledge": "2025-03-31", - "release_date": "2025-11-24", - "last_updated": "2025-11-24", + "release_date": "2025-11-01", + "last_updated": "2025-11-01", "modalities": { "input": [ "text", @@ -3187,7 +11239,7 @@ }, { "id": "anthropic/claude-sonnet-4.5", - "name": "Claude Sonnet 4.5 (latest)", + "name": "Claude Sonnet 4.5", "family": "claude-sonnet", "attachment": true, "reasoning": true, @@ -3218,6 +11270,2676 @@ "output": 64000 } }, + { + "id": "anthropic/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "azure-cognitive-services/claude-haiku-4.5", + "name": "Claude Haiku 4.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-31", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "azure-cognitive-services/claude-opus-4.1", + "name": "Claude Opus 4.1", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "azure-cognitive-services/claude-opus-4.5", + "name": "Claude Opus 4.5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-11-24", + "last_updated": "2025-08-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "azure-cognitive-services/claude-opus-4.6", + "name": "Claude Opus 4.6", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "azure-cognitive-services/codestral", + "name": "Codestral 25.01", + "family": "codestral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "azure-cognitive-services/codex-mini", + "name": "Codex Mini", + "family": "gpt-codex-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-04", + "release_date": "2025-05-16", + "last_updated": "2025-05-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 6.0, + "cache_read": 0.375 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "azure-cognitive-services/cohere-command-a", + "name": "Command A", + "family": "command-a", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06-01", + "release_date": "2025-03-13", + "last_updated": "2025-03-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.5, + "output": 10.0 + }, + "limit": { + "context": 256000, + "output": 8000 + } + }, + { + "id": "azure-cognitive-services/cohere-command-r-08", + "name": "Command R", + "family": "command-r", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06-01", + "release_date": "2024-08-30", + "last_updated": "2024-08-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 128000, + "output": 4000 + } + }, + { + "id": "azure-cognitive-services/cohere-command-r-plus-08", + "name": "Command R+", + "family": "command-r", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06-01", + "release_date": "2024-08-30", + "last_updated": "2024-08-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.5, + "output": 10.0 + }, + "limit": { + "context": 128000, + "output": 4000 + } + }, + { + "id": "azure-cognitive-services/cohere-embed-v-4.0", + "name": "Embed v4", + "family": "cohere-embed", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-04-15", + "last_updated": "2025-04-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.12, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 1536 + } + }, + { + "id": "azure-cognitive-services/cohere-embed-v3-english", + "name": "Embed v3 English", + "family": "cohere-embed", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2023-11-07", + "last_updated": "2023-11-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.0 + }, + "limit": { + "context": 512, + "output": 1024 + } + }, + { + "id": "azure-cognitive-services/cohere-embed-v3-multilingual", + "name": "Embed v3 Multilingual", + "family": "cohere-embed", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2023-11-07", + "last_updated": "2023-11-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.0 + }, + "limit": { + "context": 512, + "output": 1024 + } + }, + { + "id": "azure-cognitive-services/deepseek-r1", + "name": "DeepSeek-R1-0528", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-05-28", + "last_updated": "2025-05-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.35, + "output": 5.4 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "azure-cognitive-services/deepseek-v3", + "name": "DeepSeek-V3-0324", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-03-24", + "last_updated": "2025-03-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.14, + "output": 4.56 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "azure-cognitive-services/deepseek-v3.1", + "name": "DeepSeek-V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-08-21", + "last_updated": "2025-08-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.56, + "output": 1.68 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "azure-cognitive-services/deepseek-v3.2", + "name": "DeepSeek-V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.58, + "output": 1.68 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/deepseek-v3.2-speciale", + "name": "DeepSeek-V3.2-Speciale", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.58, + "output": 1.68 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/gpt-3.5-turbo", + "name": "GPT-3.5 Turbo 0125", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2021-08", + "release_date": "2024-01-25", + "last_updated": "2024-01-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.5 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "azure-cognitive-services/gpt-3.5-turbo-instruct", + "name": "GPT-3.5 Turbo Instruct", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2021-08", + "release_date": "2023-09-21", + "last_updated": "2023-09-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 2.0 + }, + "limit": { + "context": 4096, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/gpt-4", + "name": "GPT-4", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-11", + "release_date": "2023-03-14", + "last_updated": "2023-03-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 60.0, + "output": 120.0 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "azure-cognitive-services/gpt-4-32k", + "name": "GPT-4 32K", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-11", + "release_date": "2023-03-14", + "last_updated": "2023-03-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 60.0, + "output": 120.0 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "azure-cognitive-services/gpt-4-turbo", + "name": "GPT-4 Turbo", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-11", + "release_date": "2023-11-06", + "last_updated": "2024-04-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 30.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/gpt-4-turbo-vision", + "name": "GPT-4 Turbo Vision", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-11", + "release_date": "2023-11-06", + "last_updated": "2024-04-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 30.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/gpt-4.1", + "name": "GPT-4.1", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-05", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "azure-cognitive-services/gpt-4.1-mini", + "name": "GPT-4.1 mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-05", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.6, + "cache_read": 0.1 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "azure-cognitive-services/gpt-4.1-nano", + "name": "GPT-4.1 nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-05", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.03 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "azure-cognitive-services/gpt-4o", + "name": "GPT-4o", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-05-13", + "last_updated": "2024-05-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0, + "cache_read": 1.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "azure-cognitive-services/gpt-4o-mini", + "name": "GPT-4o mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.08 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "azure-cognitive-services/gpt-5", + "name": "GPT-5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 272000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/gpt-5-chat", + "name": "GPT-5 Chat", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": false, + "knowledge": "2024-10-24", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "azure-cognitive-services/gpt-5-codex", + "name": "GPT-5-Codex", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/gpt-5-mini", + "name": "GPT-5 Mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.03 + }, + "limit": { + "context": 272000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/gpt-5-nano", + "name": "GPT-5 Nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 272000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/gpt-5-pro", + "name": "GPT-5 Pro", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-10-06", + "last_updated": "2025-10-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 120.0 + }, + "limit": { + "context": 400000, + "output": 272000 + } + }, + { + "id": "azure-cognitive-services/gpt-5.1", + "name": "GPT-5.1", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text", + "image", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 272000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/gpt-5.1-chat", + "name": "GPT-5.1 Chat", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text", + "image", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "azure-cognitive-services/gpt-5.1-codex", + "name": "GPT-5.1 Codex", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text", + "image", + "audio" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/gpt-5.1-codex-mini", + "name": "GPT-5.1 Codex Mini", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.025 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/gpt-5.2", + "name": "GPT-5.2", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/gpt-5.2-chat", + "name": "GPT-5.2 Chat", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "azure-cognitive-services/gpt-5.2-codex", + "name": "GPT-5.2 Codex", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-01-14", + "last_updated": "2026-01-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/grok-3", + "name": "Grok 3", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2025-02-17", + "last_updated": "2025-02-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "azure-cognitive-services/grok-3-mini", + "name": "Grok 3 Mini", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2025-02-17", + "last_updated": "2025-02-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.5, + "cache_read": 0.075 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "azure-cognitive-services/grok-4", + "name": "Grok 4", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "azure-cognitive-services/grok-4-fast", + "name": "Grok 4 Fast (Reasoning)", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-09-19", + "last_updated": "2025-09-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "azure-cognitive-services/grok-4-fast-non", + "name": "Grok 4 Fast (Non-Reasoning)", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-09-19", + "last_updated": "2025-09-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "azure-cognitive-services/grok-code-fast-1", + "name": "Grok Code Fast 1", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2025-08-28", + "last_updated": "2025-08-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.5, + "cache_read": 0.02 + }, + "limit": { + "context": 256000, + "output": 10000 + } + }, + { + "id": "azure-cognitive-services/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2025-12-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "azure-cognitive-services/kimi-k2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-06", + "last_updated": "2026-02-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "azure-cognitive-services/llama-3.2-11b-vision-instruct", + "name": "Llama-3.2-11B-Vision-Instruct", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-09-25", + "last_updated": "2024-09-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.37, + "output": 0.37 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "azure-cognitive-services/llama-3.2-90b-vision-instruct", + "name": "Llama-3.2-90B-Vision-Instruct", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-09-25", + "last_updated": "2024-09-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.04, + "output": 2.04 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "azure-cognitive-services/llama-3.3-70b-instruct", + "name": "Llama-3.3-70B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.71, + "output": 0.71 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "azure-cognitive-services/llama-4-maverick-17b-128e-instruct-fp8", + "name": "Llama 4 Maverick 17B 128E Instruct FP8", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 1.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "azure-cognitive-services/llama-4-scout-17b-16e-instruct", + "name": "Llama 4 Scout 17B 16E Instruct", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.78 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "azure-cognitive-services/mai-ds-r1", + "name": "MAI-DS-R1", + "family": "mai", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.35, + "output": 5.4 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "azure-cognitive-services/meta-llama-3-70b-instruct", + "name": "Meta-Llama-3-70B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-04-18", + "last_updated": "2024-04-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.68, + "output": 3.54 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "azure-cognitive-services/meta-llama-3-8b-instruct", + "name": "Meta-Llama-3-8B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-04-18", + "last_updated": "2024-04-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.61 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "azure-cognitive-services/meta-llama-3.1-405b-instruct", + "name": "Meta-Llama-3.1-405B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 5.33, + "output": 16.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "azure-cognitive-services/meta-llama-3.1-70b-instruct", + "name": "Meta-Llama-3.1-70B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.68, + "output": 3.54 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "azure-cognitive-services/meta-llama-3.1-8b-instruct", + "name": "Meta-Llama-3.1-8B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.61 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "azure-cognitive-services/ministral-3b", + "name": "Ministral 3B", + "family": "ministral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.04, + "output": 0.04 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "azure-cognitive-services/mistral-large", + "name": "Mistral Large 24.11", + "family": "mistral-large", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2024-11-01", + "last_updated": "2024-11-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "azure-cognitive-services/mistral-medium", + "name": "Mistral Medium 3", + "family": "mistral-medium", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2025-05-07", + "last_updated": "2025-05-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/mistral-nemo", + "name": "Mistral Nemo", + "family": "mistral-nemo", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.15 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "azure-cognitive-services/mistral-small", + "name": "Mistral Small 3.1", + "family": "mistral-small", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2025-03-01", + "last_updated": "2025-03-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "azure-cognitive-services/model-router", + "name": "Model Router", + "family": "model-router", + "attachment": true, + "reasoning": false, + "tool_call": true, + "release_date": "2025-05-19", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "azure-cognitive-services/o1", + "name": "o1", + "family": "o", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2023-09", + "release_date": "2024-12-05", + "last_updated": "2024-12-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 60.0, + "cache_read": 7.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "azure-cognitive-services/o1-mini", + "name": "o1-mini", + "family": "o-mini", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2023-09", + "release_date": "2024-09-12", + "last_updated": "2024-09-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.55 + }, + "limit": { + "context": 128000, + "output": 65536 + } + }, + { + "id": "azure-cognitive-services/o1-preview", + "name": "o1-preview", + "family": "o", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2023-09", + "release_date": "2024-09-12", + "last_updated": "2024-09-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 16.5, + "output": 66.0, + "cache_read": 8.25 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "azure-cognitive-services/o3", + "name": "o3", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "azure-cognitive-services/o3-mini", + "name": "o3-mini", + "family": "o-mini", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2024-12-20", + "last_updated": "2025-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.55 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "azure-cognitive-services/o4-mini", + "name": "o4-mini", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.28 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "azure-cognitive-services/phi-3-medium-128k-instruct", + "name": "Phi-3-medium-instruct (128k)", + "family": "phi", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.17, + "output": 0.68 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/phi-3-medium-4k-instruct", + "name": "Phi-3-medium-instruct (4k)", + "family": "phi", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.17, + "output": 0.68 + }, + "limit": { + "context": 4096, + "output": 1024 + } + }, + { + "id": "azure-cognitive-services/phi-3-mini-128k-instruct", + "name": "Phi-3-mini-instruct (128k)", + "family": "phi", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.52 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/phi-3-mini-4k-instruct", + "name": "Phi-3-mini-instruct (4k)", + "family": "phi", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.52 + }, + "limit": { + "context": 4096, + "output": 1024 + } + }, + { + "id": "azure-cognitive-services/phi-3-small-128k-instruct", + "name": "Phi-3-small-instruct (128k)", + "family": "phi", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/phi-3-small-8k-instruct", + "name": "Phi-3-small-instruct (8k)", + "family": "phi", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "azure-cognitive-services/phi-3.5-mini-instruct", + "name": "Phi-3.5-mini-instruct", + "family": "phi", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-08-20", + "last_updated": "2024-08-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.52 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/phi-3.5-moe-instruct", + "name": "Phi-3.5-MoE-instruct", + "family": "phi", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-08-20", + "last_updated": "2024-08-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.16, + "output": 0.64 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/phi-4", + "name": "Phi-4", + "family": "phi", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.125, + "output": 0.5 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/phi-4-mini", + "name": "Phi-4-mini", + "family": "phi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.075, + "output": 0.3 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/phi-4-multimodal", + "name": "Phi-4-multimodal", + "family": "phi", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.32 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/phi-4-reasoning-plus", + "name": "Phi-4-reasoning-plus", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.125, + "output": 0.5 + }, + "limit": { + "context": 32000, + "output": 4096 + } + }, + { + "id": "azure-cognitive-services/text-embedding-3-large", + "name": "text-embedding-3-large", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2024-01-25", + "last_updated": "2024-01-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.13, + "output": 0.0 + }, + "limit": { + "context": 8191, + "output": 3072 + } + }, + { + "id": "azure-cognitive-services/text-embedding-3-small", + "name": "text-embedding-3-small", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2024-01-25", + "last_updated": "2024-01-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.02, + "output": 0.0 + }, + "limit": { + "context": 8191, + "output": 1536 + } + }, + { + "id": "azure-cognitive-services/text-embedding-ada-002", + "name": "text-embedding-ada-002", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2022-12-15", + "last_updated": "2022-12-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, { "id": "azure/claude-haiku-4.5", "name": "Claude Haiku 4.5", @@ -5886,6 +16608,5759 @@ "output": 1536 } }, + { + "id": "bailing/Ling-1T", + "name": "Ling-1T", + "family": "ling", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-10", + "last_updated": "2025-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.57, + "output": 2.29 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "bailing/Ring-1T", + "name": "Ring-1T", + "family": "ring", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-10", + "last_updated": "2025-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.57, + "output": 2.29 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "baseten/Qwen/Qwen3-Coder-480B-A35B-Instruct", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.38, + "output": 1.53 + }, + "limit": { + "context": 262144, + "output": 66536 + } + }, + { + "id": "baseten/deepseek-ai/DeepSeek-V3.2", + "name": "DeepSeek V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-10", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.45 + }, + "limit": { + "context": 163800, + "output": 131100 + } + }, + { + "id": "baseten/moonshotai/Kimi-K2-Instruct", + "name": "Kimi K2 Instruct 0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "baseten/moonshotai/Kimi-K2-Thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "baseten/moonshotai/Kimi-K2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2026-01-30", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0 + }, + "limit": { + "context": 262144, + "output": 8192 + } + }, + { + "id": "baseten/zai-org/GLM-4.6", + "name": "GLM 4.6", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2025-09-16", + "last_updated": "2025-09-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 200000, + "output": 200000 + } + }, + { + "id": "baseten/zai-org/GLM-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "baseten/zai-org/GLM-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-01", + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.95, + "output": 3.15 + }, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "berget/BAAI/bge-reranker-v2-m3", + "name": "bge-reranker-v2-m3", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2025-04", + "release_date": "2025-04-23", + "last_updated": "2025-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 512, + "output": 512 + } + }, + { + "id": "berget/KBLab/kb-whisper-large", + "name": "KB-Whisper-Large", + "family": "whisper", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2025-04", + "release_date": "2025-04-27", + "last_updated": "2025-04-27", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 3.0 + }, + "limit": { + "context": 480000, + "output": 4800 + } + }, + { + "id": "berget/intfloat/multilingual-e5-large", + "name": "Multilingual-E5-large", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2025-09", + "release_date": "2025-09-11", + "last_updated": "2025-09-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.0 + }, + "limit": { + "context": 512, + "output": 1024 + } + }, + { + "id": "berget/intfloat/multilingual-e5-large-instruct", + "name": "Multilingual-E5-large-instruct", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2025-04", + "release_date": "2025-04-27", + "last_updated": "2025-04-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.0 + }, + "limit": { + "context": 512, + "output": 1024 + } + }, + { + "id": "berget/meta-llama/Llama-3.3-70B-Instruct", + "name": "Llama 3.3 70B Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2025-04-27", + "last_updated": "2025-04-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.9, + "output": 0.9 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "berget/mistralai/Mistral-Small-3.2-24B-Instruct", + "name": "Mistral Small 3.2 24B Instruct 2506", + "family": "mistral-small", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-10-01", + "last_updated": "2025-10-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.3 + }, + "limit": { + "context": 32000, + "output": 8192 + } + }, + { + "id": "berget/openai/gpt-oss-120b", + "name": "GPT-OSS-120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "berget/zai-org/GLM-4.7", + "name": "GLM 4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.3 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "cerebras/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.69 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "cerebras/llama3.1-8b", + "name": "Llama 3.1 8B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 32000, + "output": 8000 + } + }, + { + "id": "cerebras/qwen-3-235b-a22b-instruct", + "name": "Qwen 3 235B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-22", + "last_updated": "2025-07-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.2 + }, + "limit": { + "context": 131000, + "output": 32000 + } + }, + { + "id": "cerebras/zai-glm-4.7", + "name": "Z.AI GLM-4.7", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-10", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.25, + "output": 2.75, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 40000 + } + }, + { + "id": "chutes/MiniMaxAI/MiniMax-M2.1-TEE", + "name": "MiniMax M2.1 TEE", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.12 + }, + "limit": { + "context": 196608, + "output": 65536 + } + }, + { + "id": "chutes/MiniMaxAI/MiniMax-M2.5-TEE", + "name": "MiniMax M2.5 TEE", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-15", + "last_updated": "2026-02-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 196608, + "output": 65536 + } + }, + { + "id": "chutes/NousResearch/DeepHermes-3-Mistral-24B-Preview", + "name": "DeepHermes 3 Mistral 24B Preview", + "family": "nousresearch", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.1 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "chutes/NousResearch/Hermes-4-14B", + "name": "Hermes 4 14B", + "family": "nousresearch", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.05 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "chutes/NousResearch/Hermes-4-405B-FP8-TEE", + "name": "Hermes 4 405B FP8 TEE", + "family": "nousresearch", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "chutes/NousResearch/Hermes-4-70B", + "name": "Hermes 4 70B", + "family": "nousresearch", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.11, + "output": 0.38 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "chutes/NousResearch/Hermes-4.3-36B", + "name": "Hermes 4.3 36B", + "family": "nousresearch", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.39 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "chutes/OpenGVLab/InternVL3-78B-TEE", + "name": "InternVL3 78B TEE", + "family": "opengvlab", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-01-06", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.39 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "chutes/Qwen/Qwen2.5-72B-Instruct", + "name": "Qwen2.5 72B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.52 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "chutes/Qwen/Qwen2.5-Coder-32B-Instruct", + "name": "Qwen2.5 Coder 32B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.11 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "chutes/Qwen/Qwen2.5-VL-32B-Instruct", + "name": "Qwen2.5 VL 32B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.22 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "chutes/Qwen/Qwen2.5-VL-72B-Instruct-TEE", + "name": "Qwen2.5 VL 72B Instruct TEE", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "chutes/Qwen/Qwen3-14B", + "name": "Qwen3 14B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.22 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "chutes/Qwen/Qwen3-235B-A22B", + "name": "Qwen3 235B A22B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "chutes/Qwen/Qwen3-235B-A22B-Instruct-2507-TEE", + "name": "Qwen3 235B A22B Instruct 2507 TEE", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.55, + "cache_read": 0.04 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "chutes/Qwen/Qwen3-235B-A22B-Thinking", + "name": "Qwen3 235B A22B Thinking 2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.11, + "output": 0.6 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "chutes/Qwen/Qwen3-30B-A3B", + "name": "Qwen3 30B A3B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.22 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "chutes/Qwen/Qwen3-30B-A3B-Instruct", + "name": "Qwen3 30B A3B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.33 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "chutes/Qwen/Qwen3-32B", + "name": "Qwen3 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.24, + "cache_read": 0.04 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "chutes/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8-TEE", + "name": "Qwen3 Coder 480B A35B Instruct FP8 TEE", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 0.95, + "cache_read": 0.11 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "chutes/Qwen/Qwen3-Coder-Next", + "name": "Qwen3 Coder Next", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.3 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "chutes/Qwen/Qwen3-Next-80B-A3B-Instruct", + "name": "Qwen3 Next 80B A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.8 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "chutes/Qwen/Qwen3-VL-235B-A22B-Instruct", + "name": "Qwen3 VL 235B A22B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "chutes/Qwen/Qwen3.5-397B-A17B-TEE", + "name": "Qwen3.5 397B A17B TEE", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-18", + "last_updated": "2026-02-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "chutes/Qwen/Qwen3Guard-Gen-0.6B", + "name": "Qwen3Guard Gen 0.6B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.01, + "cache_read": 0.005 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "chutes/XiaomiMiMo/MiMo-V2-Flash", + "name": "MiMo V2 Flash", + "family": "mimo", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.29 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "chutes/chutesai/Mistral-Small-3.1-24B-Instruct", + "name": "Mistral Small 3.1 24B Instruct 2503", + "family": "chutesai", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.11, + "cache_read": 0.015 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "chutes/chutesai/Mistral-Small-3.2-24B-Instruct", + "name": "Mistral Small 3.2 24B Instruct 2506", + "family": "chutesai", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.18 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "chutes/deepseek-ai/DeepSeek-R1-0528-TEE", + "name": "DeepSeek R1 0528 TEE", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 1.75 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "chutes/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", + "name": "DeepSeek R1 Distill Llama 70B", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.11 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "chutes/deepseek-ai/DeepSeek-R1-TEE", + "name": "DeepSeek R1 TEE", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "chutes/deepseek-ai/DeepSeek-V3", + "name": "DeepSeek V3", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "chutes/deepseek-ai/DeepSeek-V3-0324-TEE", + "name": "DeepSeek V3 0324 TEE", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.19, + "output": 0.87, + "cache_read": 0.095 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "chutes/deepseek-ai/DeepSeek-V3.1-TEE", + "name": "DeepSeek V3.1 TEE", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "chutes/deepseek-ai/DeepSeek-V3.1-Terminus-TEE", + "name": "DeepSeek V3.1 Terminus TEE", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.23, + "output": 0.9 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "chutes/deepseek-ai/DeepSeek-V3.2-Speciale-TEE", + "name": "DeepSeek V3.2 Speciale TEE", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 0.41 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "chutes/deepseek-ai/DeepSeek-V3.2-TEE", + "name": "DeepSeek V3.2 TEE", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.38, + "cache_read": 0.125 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "chutes/miromind-ai/MiroThinker-v1.5-235B", + "name": "MiroThinker V1.5 235B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-01-10", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 8192 + } + }, + { + "id": "chutes/mistralai/Devstral-2-123B-Instruct-2512-TEE", + "name": "Devstral 2 123B Instruct 2512 TEE", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-10", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.22 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "chutes/moonshotai/Kimi-K2-Instruct", + "name": "Kimi K2 Instruct 0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.39, + "output": 1.9, + "cache_read": 0.195 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "chutes/moonshotai/Kimi-K2-Thinking-TEE", + "name": "Kimi K2 Thinking TEE", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 1.75 + }, + "limit": { + "context": 262144, + "output": 65535 + } + }, + { + "id": "chutes/moonshotai/Kimi-K2.5-TEE", + "name": "Kimi K2.5 TEE", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0 + }, + "limit": { + "context": 262144, + "output": 65535 + } + }, + { + "id": "chutes/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", + "name": "NVIDIA Nemotron 3 Nano 30B A3B BF16", + "family": "nemotron", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.24 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "chutes/openai/gpt-oss-120b-TEE", + "name": "gpt oss 120b TEE", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.04, + "output": 0.18 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "chutes/openai/gpt-oss-20b", + "name": "gpt oss 20b", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.1 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "chutes/rednote-hilab/dots.ocr", + "name": "dots.ocr", + "family": "rednote", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.01, + "cache_read": 0.005 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "chutes/tngtech/DeepSeek-R1T-Chimera", + "name": "DeepSeek R1T Chimera", + "family": "tngtech", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "chutes/tngtech/DeepSeek-TNG-R1T2-Chimera", + "name": "DeepSeek TNG R1T2 Chimera", + "family": "tngtech", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.85 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "chutes/tngtech/TNG-R1T-Chimera-TEE", + "name": "TNG R1T Chimera TEE", + "family": "tngtech", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.85 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "chutes/tngtech/TNG-R1T-Chimera-Turbo", + "name": "TNG R1T Chimera Turbo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 0.6 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "chutes/unsloth/Llama-3.2-1B-Instruct", + "name": "Llama 3.2 1B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.01, + "cache_read": 0.005 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "chutes/unsloth/Llama-3.2-3B-Instruct", + "name": "Llama 3.2 3B Instruct", + "family": "unsloth", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-02-12", + "last_updated": "2025-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.01, + "cache_read": 0.005 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "chutes/unsloth/Mistral-Nemo-Instruct", + "name": "Mistral Nemo Instruct 2407", + "family": "unsloth", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.04, + "cache_read": 0.01 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "chutes/unsloth/Mistral-Small-24B-Instruct", + "name": "Mistral Small 24B Instruct 2501", + "family": "unsloth", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.11 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "chutes/unsloth/gemma-3-12b-it", + "name": "gemma 3 12b it", + "family": "unsloth", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.1 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "chutes/unsloth/gemma-3-27b-it", + "name": "gemma 3 27b it", + "family": "unsloth", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.04, + "output": 0.15, + "cache_read": 0.02 + }, + "limit": { + "context": 128000, + "output": 65536 + } + }, + { + "id": "chutes/unsloth/gemma-3-4b-it", + "name": "gemma 3 4b it", + "family": "unsloth", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.03 + }, + "limit": { + "context": 96000, + "output": 96000 + } + }, + { + "id": "chutes/zai-org/GLM-4.5-Air", + "name": "GLM 4.5 Air", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.22 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "chutes/zai-org/GLM-4.5-FP8", + "name": "GLM 4.5 FP8", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "chutes/zai-org/GLM-4.5-TEE", + "name": "GLM 4.5 TEE", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 1.55 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "chutes/zai-org/GLM-4.6-FP8", + "name": "GLM 4.6 FP8", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 202752, + "output": 65535 + } + }, + { + "id": "chutes/zai-org/GLM-4.6-TEE", + "name": "GLM 4.6 TEE", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 1.5 + }, + "limit": { + "context": 202752, + "output": 65536 + } + }, + { + "id": "chutes/zai-org/GLM-4.6V", + "name": "GLM 4.6V", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "chutes/zai-org/GLM-4.7-FP8", + "name": "GLM 4.7 FP8", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 202752, + "output": 65535 + } + }, + { + "id": "chutes/zai-org/GLM-4.7-Flash", + "name": "GLM 4.7 Flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.35 + }, + "limit": { + "context": 202752, + "output": 65535 + } + }, + { + "id": "chutes/zai-org/GLM-4.7-TEE", + "name": "GLM 4.7 TEE", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 1.5 + }, + "limit": { + "context": 202752, + "output": 65535 + } + }, + { + "id": "chutes/zai-org/GLM-5-TEE", + "name": "GLM 5 TEE", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-14", + "last_updated": "2026-02-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.75, + "output": 2.5 + }, + "limit": { + "context": 202752, + "output": 65535 + } + }, + { + "id": "cloudferro-sherlock/meta-llama/Llama-3.3-70B-Instruct", + "name": "Llama 3.3 70B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10-09", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.92, + "output": 2.92 + }, + "limit": { + "context": 70000, + "output": 70000 + } + }, + { + "id": "cloudferro-sherlock/openai/gpt-oss-120b", + "name": "OpenAI GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-28", + "last_updated": "2025-08-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.92, + "output": 2.92 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "cloudferro-sherlock/speakleash/Bielik-11B-v2.6-Instruct", + "name": "Bielik 11B v2.6 Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-03-13", + "last_updated": "2025-03-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.67, + "output": 0.67 + }, + "limit": { + "context": 32000, + "output": 32000 + } + }, + { + "id": "cloudferro-sherlock/speakleash/Bielik-11B-v3.0-Instruct", + "name": "Bielik 11B v3.0 Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-03-13", + "last_updated": "2025-03-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.67, + "output": 0.67 + }, + "limit": { + "context": 32000, + "output": 32000 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-3-haiku", + "name": "Claude Haiku 3", + "family": "claude-haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-08-31", + "release_date": "2024-03-13", + "last_updated": "2024-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.25, + "cache_read": 0.03, + "cache_write": 0.3 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-3-opus", + "name": "Claude Opus 3", + "family": "claude-opus", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-08-31", + "release_date": "2024-02-29", + "last_updated": "2024-02-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-3-sonnet", + "name": "Claude Sonnet 3", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-08-31", + "release_date": "2024-03-04", + "last_updated": "2024-03-04", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 0.3 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-3.5-haiku", + "name": "Claude Haiku 3.5 (latest)", + "family": "claude-haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07-31", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 4.0, + "cache_read": 0.08, + "cache_write": 1.0 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-3.5-sonnet", + "name": "Claude Sonnet 3.5 v2", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04-30", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-haiku-4.5", + "name": "Claude Haiku 4.5 (latest)", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-opus-4", + "name": "Claude Opus 4 (latest)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-opus-4.1", + "name": "Claude Opus 4.1 (latest)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-opus-4.5", + "name": "Claude Opus 4.5 (latest)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-11-24", + "last_updated": "2025-11-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-opus-4.6", + "name": "Claude Opus 4.6 (latest)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-sonnet-4", + "name": "Claude Sonnet 4 (latest)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5 (latest)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "cloudflare-ai-gateway/anthropic/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "cloudflare-ai-gateway/openai/gpt-3.5-turbo", + "name": "GPT-3.5-turbo", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2021-09-01", + "release_date": "2023-03-01", + "last_updated": "2023-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.5, + "cache_read": 1.25 + }, + "limit": { + "context": 16385, + "output": 4096 + } + }, + { + "id": "cloudflare-ai-gateway/openai/gpt-4", + "name": "GPT-4", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-11", + "release_date": "2023-11-06", + "last_updated": "2024-04-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 30.0, + "output": 60.0 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "cloudflare-ai-gateway/openai/gpt-4-turbo", + "name": "GPT-4 Turbo", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2023-11-06", + "last_updated": "2024-04-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 30.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "cloudflare-ai-gateway/openai/gpt-4o", + "name": "GPT-4o", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-05-13", + "last_updated": "2024-08-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0, + "cache_read": 1.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/openai/gpt-4o-mini", + "name": "GPT-4o mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.08 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/openai/gpt-5.1", + "name": "GPT-5.1", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "cloudflare-ai-gateway/openai/gpt-5.1-codex", + "name": "GPT-5.1 Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "cloudflare-ai-gateway/openai/gpt-5.2", + "name": "GPT-5.2", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "cloudflare-ai-gateway/openai/o1", + "name": "o1", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2023-09", + "release_date": "2024-12-05", + "last_updated": "2024-12-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 60.0, + "cache_read": 7.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "cloudflare-ai-gateway/openai/o3", + "name": "o3", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "cloudflare-ai-gateway/openai/o3-mini", + "name": "o3-mini", + "family": "o-mini", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2024-12-20", + "last_updated": "2025-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.55 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "cloudflare-ai-gateway/openai/o3-pro", + "name": "o3-pro", + "family": "o-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-06-10", + "last_updated": "2025-06-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 20.0, + "output": 80.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "cloudflare-ai-gateway/openai/o4-mini", + "name": "o4-mini", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.28 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B", + "name": "IndicTrans2 EN-Indic 1B", + "family": "indictrans", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-09-25", + "last_updated": "2025-09-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.34, + "output": 0.34 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it", + "name": "Gemma SEA-LION v4 27B IT", + "family": "gemma", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-09-25", + "last_updated": "2025-09-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.35, + "output": 0.56 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/baai/bge-base-en-v1.5", + "name": "BGE Base EN v1.5", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.067, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/baai/bge-large-en-v1.5", + "name": "BGE Large EN v1.5", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/baai/bge-m3", + "name": "BGE M3", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.012, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/baai/bge-reranker-base", + "name": "BGE Reranker Base", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-09", + "last_updated": "2025-04-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0031, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/baai/bge-small-en-v1.5", + "name": "BGE Small EN v1.5", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.02, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/deepgram/aura-2-en", + "name": "Deepgram Aura 2 (EN)", + "family": "aura", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/deepgram/aura-2-es", + "name": "Deepgram Aura 2 (ES)", + "family": "aura", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/deepgram/nova-3", + "name": "Deepgram Nova 3", + "family": "nova", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", + "name": "DeepSeek R1 Distill Qwen 32B", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 4.88 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/facebook/bart-large-cnn", + "name": "BART Large CNN", + "family": "bart", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-09", + "last_updated": "2025-04-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/google/gemma-3-12b-it", + "name": "Gemma 3 12B IT", + "family": "gemma", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-11", + "last_updated": "2025-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.35, + "output": 0.56 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/huggingface/distilbert-sst-2-int8", + "name": "DistilBERT SST-2 INT8", + "family": "distilbert", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.026, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/ibm-granite/granite-4.0-h-micro", + "name": "IBM Granite 4.0 H Micro", + "family": "granite", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.017, + "output": 0.11 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-2-7b-chat-fp16", + "name": "Llama 2 7B Chat FP16", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.56, + "output": 6.67 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3-8b-instruct", + "name": "Llama 3 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.28, + "output": 0.83 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3-8b-instruct-awq", + "name": "Llama 3 8B Instruct AWQ", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.12, + "output": 0.27 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct", + "name": "Llama 3.1 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.28, + "output": 0.8299999999999998 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct-awq", + "name": "Llama 3.1 8B Instruct AWQ", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.12, + "output": 0.27 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8", + "name": "Llama 3.1 8B Instruct FP8", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.29 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-11b-vision-instruct", + "name": "Llama 3.2 11B Vision Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.049, + "output": 0.68 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-1b-instruct", + "name": "Llama 3.2 1B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.027, + "output": 0.2 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-3b-instruct", + "name": "Llama 3.2 3B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.051, + "output": 0.34 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast", + "name": "Llama 3.3 70B Instruct FP8 Fast", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 2.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct", + "name": "Llama 4 Scout 17B 16E Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.85 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/llama-guard-3-8b", + "name": "Llama Guard 3 8B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.48, + "output": 0.03 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/meta/m2m100-1.2b", + "name": "M2M100 1.2B", + "family": "m2m", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.34, + "output": 0.34 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/mistral/mistral-7b-instruct-v0.1", + "name": "Mistral 7B Instruct v0.1", + "family": "mistral", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.11, + "output": 0.19 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct", + "name": "Mistral Small 3.1 24B Instruct", + "family": "mistral-small", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-11", + "last_updated": "2025-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.35, + "output": 0.56 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/myshell-ai/melotts", + "name": "MyShell MeloTTS", + "family": "melotts", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-120b", + "name": "GPT OSS 120B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.35, + "output": 0.75 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-20b", + "name": "GPT OSS 20B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.3 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/pfnet/plamo-embedding-1b", + "name": "PLaMo Embedding 1B", + "family": "plamo", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-09-25", + "last_updated": "2025-09-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.019, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/pipecat-ai/smart-turn-v2", + "name": "Pipecat Smart Turn v2", + "family": "smart-turn", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct", + "name": "Qwen 2.5 Coder 32B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-11", + "last_updated": "2025-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.66, + "output": 1.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen3-30b-a3b-fp8", + "name": "Qwen3 30B A3B FP8", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.051, + "output": 0.34 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen3-embedding-0.6b", + "name": "Qwen3 Embedding 0.6B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.012, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-ai-gateway/workers-ai/@cf/qwen/qwq-32b", + "name": "QwQ 32B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-11", + "last_updated": "2025-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.66, + "output": 1.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B", + "name": "IndicTrans2 EN-Indic 1B", + "family": "indictrans", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-09-25", + "last_updated": "2025-09-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.34, + "output": 0.34 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it", + "name": "Gemma SEA-LION v4 27B IT", + "family": "gemma", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-09-25", + "last_updated": "2025-09-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.35, + "output": 0.56 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/baai/bge-base-en-v1.5", + "name": "BGE Base EN v1.5", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.067, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/baai/bge-large-en-v1.5", + "name": "BGE Large EN v1.5", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/baai/bge-m3", + "name": "BGE M3", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.012, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/baai/bge-reranker-base", + "name": "BGE Reranker Base", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-09", + "last_updated": "2025-04-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0031, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/baai/bge-small-en-v1.5", + "name": "BGE Small EN v1.5", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.02, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/deepgram/aura-2-en", + "name": "Deepgram Aura 2 (EN)", + "family": "aura", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/deepgram/aura-2-es", + "name": "Deepgram Aura 2 (ES)", + "family": "aura", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/deepgram/nova-3", + "name": "Deepgram Nova 3", + "family": "nova", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", + "name": "DeepSeek R1 Distill Qwen 32B", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 4.88 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/facebook/bart-large-cnn", + "name": "BART Large CNN", + "family": "bart", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-09", + "last_updated": "2025-04-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/google/gemma-3-12b-it", + "name": "Gemma 3 12B IT", + "family": "gemma", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-11", + "last_updated": "2025-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.35, + "output": 0.56 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/huggingface/distilbert-sst-2-int8", + "name": "DistilBERT SST-2 INT8", + "family": "distilbert", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.026, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/ibm-granite/granite-4.0-h-micro", + "name": "IBM Granite 4.0 H Micro", + "family": "granite", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.017, + "output": 0.11 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-2-7b-chat-fp16", + "name": "Llama 2 7B Chat FP16", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.56, + "output": 6.67 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-3-8b-instruct", + "name": "Llama 3 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.28, + "output": 0.83 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-3-8b-instruct-awq", + "name": "Llama 3 8B Instruct AWQ", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.12, + "output": 0.27 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-3.1-8b-instruct", + "name": "Llama 3.1 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.28, + "output": 0.8299999999999998 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-3.1-8b-instruct-awq", + "name": "Llama 3.1 8B Instruct AWQ", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.12, + "output": 0.27 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8", + "name": "Llama 3.1 8B Instruct FP8", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.29 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-3.2-11b-vision-instruct", + "name": "Llama 3.2 11B Vision Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.049, + "output": 0.68 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-3.2-1b-instruct", + "name": "Llama 3.2 1B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.027, + "output": 0.2 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-3.2-3b-instruct", + "name": "Llama 3.2 3B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.051, + "output": 0.34 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast", + "name": "Llama 3.3 70B Instruct FP8 Fast", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 2.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct", + "name": "Llama 4 Scout 17B 16E Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.85 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/llama-guard-3-8b", + "name": "Llama Guard 3 8B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.48, + "output": 0.03 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/meta/m2m100-1.2b", + "name": "M2M100 1.2B", + "family": "m2m", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.34, + "output": 0.34 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/mistral/mistral-7b-instruct-v0.1", + "name": "Mistral 7B Instruct v0.1", + "family": "mistral", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.11, + "output": 0.19 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct", + "name": "Mistral Small 3.1 24B Instruct", + "family": "mistral-small", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-11", + "last_updated": "2025-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.35, + "output": 0.56 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/myshell-ai/melotts", + "name": "MyShell MeloTTS", + "family": "melotts", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/openai/gpt-oss-120b", + "name": "GPT OSS 120B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.35, + "output": 0.75 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/openai/gpt-oss-20b", + "name": "GPT OSS 20B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.3 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/pfnet/plamo-embedding-1b", + "name": "PLaMo Embedding 1B", + "family": "plamo", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-09-25", + "last_updated": "2025-09-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.019, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/pipecat-ai/smart-turn-v2", + "name": "Pipecat Smart Turn v2", + "family": "smart-turn", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct", + "name": "Qwen 2.5 Coder 32B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-11", + "last_updated": "2025-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.66, + "output": 1.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/qwen/qwen3-30b-a3b-fp8", + "name": "Qwen3 30B A3B FP8", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.051, + "output": 0.34 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/qwen/qwen3-embedding-0.6b", + "name": "Qwen3 Embedding 0.6B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.012, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cloudflare-workers-ai/@cf/qwen/qwq-32b", + "name": "QwQ 32B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-11", + "last_updated": "2025-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.66, + "output": 1.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "cohere/c4ai-aya-expanse-32b", + "name": "Aya Expanse 32B", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-10-24", + "last_updated": "2024-10-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 128000, + "output": 4000 + } + }, + { + "id": "cohere/c4ai-aya-expanse-8b", + "name": "Aya Expanse 8B", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-10-24", + "last_updated": "2024-10-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 8000, + "output": 4000 + } + }, + { + "id": "cohere/c4ai-aya-vision-32b", + "name": "Aya Vision 32B", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-04", + "last_updated": "2025-05-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 16000, + "output": 4000 + } + }, + { + "id": "cohere/c4ai-aya-vision-8b", + "name": "Aya Vision 8B", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-04", + "last_updated": "2025-05-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 16000, + "output": 4000 + } + }, { "id": "cohere/command-a-03", "name": "Command A", @@ -6090,6 +22565,1113 @@ "output": 4000 } }, + { + "id": "cohere/command-r7b-arabic-02", + "name": "Command R7B Arabic", + "family": "command-r", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06-01", + "release_date": "2025-02-27", + "last_updated": "2025-02-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0375, + "output": 0.15 + }, + "limit": { + "context": 128000, + "output": 4000 + } + }, + { + "id": "cortecs/claude-4.5-sonnet", + "name": "Claude 4.5 Sonnet", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.259, + "output": 16.296 + }, + "limit": { + "context": 200000, + "output": 200000 + } + }, + { + "id": "cortecs/claude-sonnet-4", + "name": "Claude Sonnet 4", + "family": "claude-sonnet", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.307, + "output": 16.536 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "cortecs/deepseek-v3", + "name": "DeepSeek V3 0324", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-03-24", + "last_updated": "2025-03-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.551, + "output": 1.654 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "cortecs/devstral", + "name": "Devstral 2 2512", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2025-12-09", + "last_updated": "2025-12-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "cortecs/devstral-small", + "name": "Devstral Small 2 2512", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2025-12-09", + "last_updated": "2025-12-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "cortecs/gemini-2.5-pro", + "name": "Gemini 2.5 Pro", + "family": "gemini-pro", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-20", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.654, + "output": 11.024 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "cortecs/glm-4p5", + "name": "GLM 4.5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-29", + "last_updated": "2025-07-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.67, + "output": 2.46 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "cortecs/glm-4p5-air", + "name": "GLM 4.5 Air", + "family": "glm-air", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-08-01", + "last_updated": "2025-08-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 1.34 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "cortecs/glm-4p7", + "name": "GLM 4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 2.23 + }, + "limit": { + "context": 198000, + "output": 198000 + } + }, + { + "id": "cortecs/gpt-4.1", + "name": "GPT 4.1", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.354, + "output": 9.417 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "cortecs/gpt-oss-120b", + "name": "GPT Oss 120b", + "family": "gpt-oss", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-01", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "cortecs/intellect-3", + "name": "INTELLECT 3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-26", + "last_updated": "2025-11-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.219, + "output": 1.202 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "cortecs/kimi-k2-instruct", + "name": "Kimi K2 Instruct", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-07-11", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.551, + "output": 2.646 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "cortecs/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.656, + "output": 2.731 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "cortecs/llama-3.1-405b-instruct", + "name": "Llama 3.1 405B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "cortecs/minimax-m2", + "name": "MiniMax-M2", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.39, + "output": 1.57 + }, + "limit": { + "context": 400000, + "output": 400000 + } + }, + { + "id": "cortecs/minimax-m2p1", + "name": "MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.34, + "output": 1.34 + }, + "limit": { + "context": 196000, + "output": 196000 + } + }, + { + "id": "cortecs/nova-pro-v1", + "name": "Nova Pro 1.0", + "family": "nova-pro", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-12-03", + "last_updated": "2024-12-03", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.016, + "output": 4.061 + }, + "limit": { + "context": 300000, + "output": 5000 + } + }, + { + "id": "cortecs/qwen3-32b", + "name": "Qwen3 32B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-04-29", + "last_updated": "2025-04-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.099, + "output": 0.33 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "cortecs/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.441, + "output": 1.984 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "cortecs/qwen3-next-80b-a3b-thinking", + "name": "Qwen3 Next 80B A3B Thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-11", + "last_updated": "2025-09-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.164, + "output": 1.311 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "deepinfra/MiniMaxAI/MiniMax-M2", + "name": "MiniMax M2", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.254, + "output": 1.02 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "deepinfra/MiniMaxAI/MiniMax-M2.1", + "name": "MiniMax M2.1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.28, + "output": 1.2 + }, + "limit": { + "context": 196608, + "output": 196608 + } + }, + { + "id": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 1.6 + }, + "limit": { + "context": 262144, + "output": 66536 + } + }, + { + "id": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", + "name": "Qwen3 Coder 480B A35B Instruct Turbo", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 262144, + "output": 66536 + } + }, + { + "id": "deepinfra/anthropic/claude-3.7-sonnet", + "name": "Claude Sonnet 3.7 (Latest)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10-31", + "release_date": "2025-03-13", + "last_updated": "2025-03-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.3, + "output": 16.5, + "cache_read": 0.33 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "deepinfra/anthropic/claude-4-opus", + "name": "Claude Opus 4", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-06-12", + "last_updated": "2025-06-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 16.5, + "output": 82.5 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "deepinfra/deepseek-ai/DeepSeek-R1", + "name": "DeepSeek-R1-0528", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-05-28", + "last_updated": "2025-05-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 2.15, + "cache_read": 0.35 + }, + "limit": { + "context": 163840, + "output": 64000 + } + }, + { + "id": "deepinfra/deepseek-ai/DeepSeek-V3.2", + "name": "DeepSeek-V3.2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-12-02", + "last_updated": "2025-12-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.26, + "output": 0.38, + "cache_read": 0.13 + }, + "limit": { + "context": 163840, + "output": 64000 + } + }, + { + "id": "deepinfra/moonshotai/Kimi-K2-Instruct", + "name": "Kimi K2", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-11", + "last_updated": "2025-07-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 2.0 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "deepinfra/moonshotai/Kimi-K2-Thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-11-06", + "last_updated": "2025-11-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.47, + "output": 2.0 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "deepinfra/moonshotai/Kimi-K2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 2.8 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "deepinfra/openai/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.24 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "deepinfra/openai/gpt-oss-20b", + "name": "GPT OSS 20B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.14 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "deepinfra/zai-org/GLM-4.5", + "name": "GLM-4.5", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "deepinfra/zai-org/GLM-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.43, + "output": 1.75, + "cache_read": 0.08 + }, + "limit": { + "context": 202752, + "output": 16384 + } + }, + { + "id": "deepinfra/zai-org/GLM-4.7-Flash", + "name": "GLM-4.7-Flash", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.4 + }, + "limit": { + "context": 202752, + "output": 16384 + } + }, { "id": "deepseek/deepseek-chat", "name": "DeepSeek Chat", @@ -6150,6 +23732,4833 @@ "output": 128000 } }, + { + "id": "evroc/KBLab/kb-whisper-large", + "name": "KB Whisper", + "family": "whisper", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2024-10-01", + "last_updated": "2024-10-01", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.00236, + "output": 0.00236 + }, + "limit": { + "context": 448, + "output": 448 + } + }, + { + "id": "evroc/Qwen/Qwen3-30B-A3B-Instruct-2507-FP8", + "name": "Qwen3 30B 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 1.42 + }, + "limit": { + "context": 64000, + "output": 64000 + } + }, + { + "id": "evroc/Qwen/Qwen3-Embedding-8B", + "name": "Qwen3 Embedding 8B", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.12, + "output": 0.12 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "evroc/Qwen/Qwen3-VL-30B-A3B-Instruct", + "name": "Qwen3 VL 30B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.24, + "output": 0.94 + }, + "limit": { + "context": 100000, + "output": 100000 + } + }, + { + "id": "evroc/intfloat/multilingual-e5-large-instruct", + "name": "E5 Multi-Lingual Large Embeddings 0.6B", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2024-06-01", + "last_updated": "2024-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.12, + "output": 0.12 + }, + "limit": { + "context": 512, + "output": 512 + } + }, + { + "id": "evroc/microsoft/Phi-4-multimodal-instruct", + "name": "Phi-4 15B", + "family": "phi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": true, + "cost": { + "input": 0.24, + "output": 0.47 + }, + "limit": { + "context": 32000, + "output": 32000 + } + }, + { + "id": "evroc/mistralai/Magistral-Small", + "name": "Magistral Small 1.2 24B", + "family": "magistral-small", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2025-06-01", + "last_updated": "2025-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.59, + "output": 2.36 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "evroc/mistralai/Voxtral-Small-24B", + "name": "Voxtral Small 24B", + "family": "voxtral", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2025-03-01", + "last_updated": "2025-03-01", + "modalities": { + "input": [ + "audio", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.00236, + "output": 0.00236 + }, + "limit": { + "context": 32000, + "output": 32000 + } + }, + { + "id": "evroc/mistralai/devstral-small-2-24b-instruct", + "name": "Devstral Small 2 24B Instruct 2512", + "family": "devstral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.12, + "output": 0.47 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "evroc/moonshotai/Kimi-K2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.47, + "output": 5.9 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "evroc/nvidia/Llama-3.3-70B-Instruct-FP8", + "name": "Llama 3.3 70B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2024-12-01", + "last_updated": "2024-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.18, + "output": 1.18 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "evroc/openai/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.24, + "output": 0.94 + }, + "limit": { + "context": 65536, + "output": 65536 + } + }, + { + "id": "evroc/openai/whisper-large-v3", + "name": "Whisper 3 Large", + "family": "whisper", + "attachment": false, + "reasoning": false, + "tool_call": false, + "release_date": "2024-10-01", + "last_updated": "2024-10-01", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.00236, + "output": 0.00236 + }, + "limit": { + "context": 448, + "output": 4096 + } + }, + { + "id": "fastrouter/anthropic/claude-opus-4.1", + "name": "Claude Opus 4.1", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "fastrouter/anthropic/claude-sonnet-4", + "name": "Claude Sonnet 4", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "fastrouter/deepseek-ai/deepseek-r1-distill-llama-70b", + "name": "DeepSeek R1 Distill Llama 70B", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-01-23", + "last_updated": "2025-01-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.14 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "fastrouter/google/gemini-2.5-flash", + "name": "Gemini 2.5 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.0375 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "fastrouter/google/gemini-2.5-pro", + "name": "Gemini 2.5 Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.31 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "fastrouter/moonshotai/kimi-k2", + "name": "Kimi K2", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-11", + "last_updated": "2025-07-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.2 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "fastrouter/openai/gpt-4.1", + "name": "GPT-4.1", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "fastrouter/openai/gpt-5", + "name": "GPT-5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10-01", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "fastrouter/openai/gpt-5-mini", + "name": "GPT-5 Mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10-01", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.025 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "fastrouter/openai/gpt-5-nano", + "name": "GPT-5 Nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10-01", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.005 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "fastrouter/openai/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "fastrouter/openai/gpt-oss-20b", + "name": "GPT OSS 20B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.2 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "fastrouter/qwen/qwen3-coder", + "name": "Qwen3 Coder", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 262144, + "output": 66536 + } + }, + { + "id": "fastrouter/x-ai/grok-4", + "name": "Grok 4", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75, + "cache_write": 15.0 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/deepseek-v3p1", + "name": "DeepSeek V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-08-21", + "last_updated": "2025-08-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.56, + "output": 1.68 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/deepseek-v3p2", + "name": "DeepSeek V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.56, + "output": 1.68, + "cache_read": 0.28 + }, + "limit": { + "context": 160000, + "output": 160000 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/glm-4p5", + "name": "GLM 4.5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-29", + "last_updated": "2025-07-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.19 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/glm-4p5-air", + "name": "GLM 4.5 Air", + "family": "glm-air", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-08-01", + "last_updated": "2025-08-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 0.88 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/glm-4p7", + "name": "GLM 4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.3 + }, + "limit": { + "context": 198000, + "output": 198000 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/glm-5", + "name": "GLM 5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.5 + }, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/gpt-oss-20b", + "name": "GPT OSS 20B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.2 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/kimi-k2-instruct", + "name": "Kimi K2 Instruct", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-11", + "last_updated": "2025-07-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.3 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/kimi-k2p5", + "name": "Kimi K2.5", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0, + "cache_read": 0.1 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/minimax-m2p1", + "name": "MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03 + }, + "limit": { + "context": 200000, + "output": 200000 + } + }, + { + "id": "fireworks-ai/accounts/fireworks/models/minimax-m2p5", + "name": "MiniMax-M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03 + }, + "limit": { + "context": 196608, + "output": 196608 + } + }, + { + "id": "firmware/claude-haiku-4.5", + "name": "Claude Haiku 4.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "firmware/claude-opus-4.5", + "name": "Claude Opus 4.5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-11-24", + "last_updated": "2025-11-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "firmware/claude-opus-4.6", + "name": "Claude Opus 4.6", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05-31", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "firmware/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "firmware/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-17", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "firmware/gemini-2.5-flash", + "name": "Gemini 2.5 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-07-17", + "last_updated": "2025-07-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.075 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "firmware/gemini-2.5-pro", + "name": "Gemini 2.5 Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-20", + "last_updated": "2025-06-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.31 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "firmware/gemini-3-flash-preview", + "name": "Gemini 3 Flash Preview", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "firmware/gemini-3-pro-preview", + "name": "Gemini 3 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "firmware/gpt-4o", + "name": "GPT-4o", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-05-13", + "last_updated": "2024-08-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0, + "cache_read": 1.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "firmware/gpt-5", + "name": "GPT-5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "firmware/gpt-5-mini", + "name": "GPT-5 Mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.03 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "firmware/gpt-5-nano", + "name": "GPT-5 Nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "firmware/gpt-5.2", + "name": "GPT-5.2", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "firmware/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "1970-01-01", + "last_updated": "1970-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "firmware/gpt-oss-20b", + "name": "GPT OSS 20B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "1970-01-01", + "last_updated": "1970-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.2 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "friendli/LGAI-EXAONE/EXAONE-4.0.1-32B", + "name": "EXAONE 4.0.1 32B", + "family": "exaone", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-31", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.0 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "friendli/LGAI-EXAONE/K-EXAONE-236B-A23B", + "name": "K EXAONE 236B A23B", + "family": "exaone", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-31", + "last_updated": "2026-01-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "friendli/MiniMaxAI/MiniMax-M2.1", + "name": "MiniMax M2.1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-13", + "last_updated": "2026-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 196608, + "output": 196608 + } + }, + { + "id": "friendli/Qwen/Qwen3-235B-A22B-Instruct", + "name": "Qwen3 235B A22B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-29", + "last_updated": "2026-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "friendli/meta-llama/Llama-3.1-8B-Instruct", + "name": "Llama 3.1 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-08-01", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 131072, + "output": 8000 + } + }, + { + "id": "friendli/meta-llama/Llama-3.3-70B-Instruct", + "name": "Llama 3.3 70B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-08-01", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "friendli/zai-org/GLM-4.7", + "name": "GLM 4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-22", + "last_updated": "2026-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 202752, + "output": 202752 + } + }, + { + "id": "friendli/zai-org/GLM-5", + "name": "GLM 5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2 + }, + "limit": { + "context": 202752, + "output": 202752 + } + }, + { + "id": "github-copilot/claude-haiku-4.5", + "name": "Claude Haiku 4.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "github-copilot/claude-opus-4.5", + "name": "Claude Opus 4.5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-11-24", + "last_updated": "2025-08-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "github-copilot/claude-opus-4.6", + "name": "Claude Opus 4.6", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "github-copilot/claude-opus-41", + "name": "Claude Opus 4.1", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 80000, + "output": 16000 + } + }, + { + "id": "github-copilot/claude-sonnet-4", + "name": "Claude Sonnet 4", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16000 + } + }, + { + "id": "github-copilot/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "github-copilot/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "github-copilot/gemini-2.5-pro", + "name": "Gemini 2.5 Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-20", + "last_updated": "2025-06-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "github-copilot/gemini-3-flash-preview", + "name": "Gemini 3 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "github-copilot/gemini-3-pro-preview", + "name": "Gemini 3 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "github-copilot/gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "github-copilot/gpt-4.1", + "name": "GPT-4.1", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 64000, + "output": 16384 + } + }, + { + "id": "github-copilot/gpt-4o", + "name": "GPT-4o", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-05-13", + "last_updated": "2024-05-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 64000, + "output": 16384 + } + }, + { + "id": "github-copilot/gpt-5", + "name": "GPT-5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "github-copilot/gpt-5-mini", + "name": "GPT-5-mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-08-13", + "last_updated": "2025-08-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "github-copilot/gpt-5.1", + "name": "GPT-5.1", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "github-copilot/gpt-5.1-codex", + "name": "GPT-5.1-Codex", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "github-copilot/gpt-5.1-codex-max", + "name": "GPT-5.1-Codex-max", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-12-04", + "last_updated": "2025-12-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "github-copilot/gpt-5.1-codex-mini", + "name": "GPT-5.1-Codex-mini", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "github-copilot/gpt-5.2", + "name": "GPT-5.2", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "github-copilot/gpt-5.2-codex", + "name": "GPT-5.2-Codex", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 272000, + "output": 128000 + } + }, + { + "id": "github-copilot/grok-code-fast-1", + "name": "Grok Code Fast 1", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2025-08-27", + "last_updated": "2025-08-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "github-models/ai21-labs/ai21-jamba-1.5-large", + "name": "AI21 Jamba 1.5 Large", + "family": "jamba", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2024-08-29", + "last_updated": "2024-08-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 4096 + } + }, + { + "id": "github-models/ai21-labs/ai21-jamba-1.5-mini", + "name": "AI21 Jamba 1.5 Mini", + "family": "jamba", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2024-08-29", + "last_updated": "2024-08-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 4096 + } + }, + { + "id": "github-models/cohere/cohere-command-a", + "name": "Cohere Command A", + "family": "command-a", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2024-11-01", + "last_updated": "2024-11-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/cohere/cohere-command-r", + "name": "Cohere Command R", + "family": "command-r", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2024-03-11", + "last_updated": "2024-08-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/cohere/cohere-command-r-08", + "name": "Cohere Command R 08-2024", + "family": "command-r", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2024-08-01", + "last_updated": "2024-08-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/cohere/cohere-command-r-plus", + "name": "Cohere Command R+", + "family": "command-r", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2024-04-04", + "last_updated": "2024-08-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/cohere/cohere-command-r-plus-08", + "name": "Cohere Command R+ 08-2024", + "family": "command-r", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2024-08-01", + "last_updated": "2024-08-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/core42/jais-30b-chat", + "name": "JAIS 30b Chat", + "family": "jais", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-03", + "release_date": "2023-08-30", + "last_updated": "2023-08-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "github-models/deepseek/deepseek-r1", + "name": "DeepSeek-R1", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 65536, + "output": 8192 + } + }, + { + "id": "github-models/deepseek/deepseek-v3", + "name": "DeepSeek-V3-0324", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-03-24", + "last_updated": "2025-03-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "github-models/meta/llama-3.2-11b-vision-instruct", + "name": "Llama-3.2-11B-Vision-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-09-25", + "last_updated": "2024-09-25", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "github-models/meta/llama-3.2-90b-vision-instruct", + "name": "Llama-3.2-90B-Vision-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-09-25", + "last_updated": "2024-09-25", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "github-models/meta/llama-3.3-70b-instruct", + "name": "Llama-3.3-70B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "github-models/meta/llama-4-maverick-17b-128e-instruct-fp8", + "name": "Llama 4 Maverick 17B 128E Instruct FP8", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-31", + "last_updated": "2025-01-31", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "github-models/meta/llama-4-scout-17b-16e-instruct", + "name": "Llama 4 Scout 17B 16E Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-31", + "last_updated": "2025-01-31", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "github-models/meta/meta-llama-3-70b-instruct", + "name": "Meta-Llama-3-70B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-04-18", + "last_updated": "2024-04-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "github-models/meta/meta-llama-3-8b-instruct", + "name": "Meta-Llama-3-8B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-04-18", + "last_updated": "2024-04-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "github-models/meta/meta-llama-3.1-405b-instruct", + "name": "Meta-Llama-3.1-405B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "github-models/meta/meta-llama-3.1-70b-instruct", + "name": "Meta-Llama-3.1-70B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "github-models/meta/meta-llama-3.1-8b-instruct", + "name": "Meta-Llama-3.1-8B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "github-models/microsoft/mai-ds-r1", + "name": "MAI-DS-R1", + "family": "mai", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 65536, + "output": 8192 + } + }, + { + "id": "github-models/microsoft/phi-3-medium-128k-instruct", + "name": "Phi-3-medium instruct (128k)", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/microsoft/phi-3-medium-4k-instruct", + "name": "Phi-3-medium instruct (4k)", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 4096, + "output": 1024 + } + }, + { + "id": "github-models/microsoft/phi-3-mini-128k-instruct", + "name": "Phi-3-mini instruct (128k)", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/microsoft/phi-3-mini-4k-instruct", + "name": "Phi-3-mini instruct (4k)", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 4096, + "output": 1024 + } + }, + { + "id": "github-models/microsoft/phi-3-small-128k-instruct", + "name": "Phi-3-small instruct (128k)", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/microsoft/phi-3-small-8k-instruct", + "name": "Phi-3-small instruct (8k)", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-04-23", + "last_updated": "2024-04-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "github-models/microsoft/phi-3.5-mini-instruct", + "name": "Phi-3.5-mini instruct (128k)", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-08-20", + "last_updated": "2024-08-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/microsoft/phi-3.5-moe-instruct", + "name": "Phi-3.5-MoE instruct (128k)", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-08-20", + "last_updated": "2024-08-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/microsoft/phi-3.5-vision-instruct", + "name": "Phi-3.5-vision instruct (128k)", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-08-20", + "last_updated": "2024-08-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/microsoft/phi-4", + "name": "Phi-4-Reasoning", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/microsoft/phi-4-mini", + "name": "Phi-4-mini-reasoning", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/microsoft/phi-4-mini-instruct", + "name": "Phi-4-mini-instruct", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/microsoft/phi-4-multimodal-instruct", + "name": "Phi-4-multimodal-instruct", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "github-models/mistral-ai/codestral", + "name": "Codestral 25.01", + "family": "codestral", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32000, + "output": 8192 + } + }, + { + "id": "github-models/mistral-ai/ministral-3b", + "name": "Ministral 3B", + "family": "ministral", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "github-models/mistral-ai/mistral-large", + "name": "Mistral Large 24.11", + "family": "mistral-large", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2024-11-01", + "last_updated": "2024-11-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "github-models/mistral-ai/mistral-medium", + "name": "Mistral Medium 3 (25.05)", + "family": "mistral-medium", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2025-05-01", + "last_updated": "2025-05-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "github-models/mistral-ai/mistral-nemo", + "name": "Mistral Nemo", + "family": "mistral-nemo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "github-models/mistral-ai/mistral-small", + "name": "Mistral Small 3.1", + "family": "mistral-small", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2025-03-01", + "last_updated": "2025-03-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "github-models/openai/gpt-4.1", + "name": "GPT-4.1", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "github-models/openai/gpt-4.1-mini", + "name": "GPT-4.1-mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "github-models/openai/gpt-4.1-nano", + "name": "GPT-4.1-nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "github-models/openai/gpt-4o", + "name": "GPT-4o", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-05-13", + "last_updated": "2024-05-13", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "github-models/openai/gpt-4o-mini", + "name": "GPT-4o mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "github-models/openai/o1", + "name": "OpenAI o1", + "family": "o", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": false, + "knowledge": "2023-10", + "release_date": "2024-09-12", + "last_updated": "2024-12-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "github-models/openai/o1-mini", + "name": "OpenAI o1-mini", + "family": "o-mini", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": false, + "knowledge": "2023-10", + "release_date": "2024-09-12", + "last_updated": "2024-12-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 65536 + } + }, + { + "id": "github-models/openai/o1-preview", + "name": "OpenAI o1-preview", + "family": "o", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": false, + "knowledge": "2023-10", + "release_date": "2024-09-12", + "last_updated": "2024-09-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "github-models/openai/o3", + "name": "OpenAI o3", + "family": "o", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": false, + "knowledge": "2024-04", + "release_date": "2025-01-31", + "last_updated": "2025-01-31", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "github-models/openai/o3-mini", + "name": "OpenAI o3-mini", + "family": "o-mini", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": false, + "knowledge": "2024-04", + "release_date": "2025-01-31", + "last_updated": "2025-01-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "github-models/openai/o4-mini", + "name": "OpenAI o4-mini", + "family": "o-mini", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": false, + "knowledge": "2024-04", + "release_date": "2025-01-31", + "last_updated": "2025-01-31", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "github-models/xai/grok-3", + "name": "Grok 3", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-09", + "last_updated": "2024-12-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "github-models/xai/grok-3-mini", + "name": "Grok 3 Mini", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-09", + "last_updated": "2024-12-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "gitlab/duo-chat-gpt-5-codex", + "name": "Agentic Chat (GPT-5 Codex)", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2026-01-22", + "last_updated": "2026-01-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "gitlab/duo-chat-gpt-5-mini", + "name": "Agentic Chat (GPT-5 Mini)", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2026-01-22", + "last_updated": "2026-01-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "gitlab/duo-chat-gpt-5.1", + "name": "Agentic Chat (GPT-5.1)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2026-01-22", + "last_updated": "2026-01-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "gitlab/duo-chat-gpt-5.2", + "name": "Agentic Chat (GPT-5.2)", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-01-23", + "last_updated": "2026-01-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "gitlab/duo-chat-gpt-5.2-codex", + "name": "Agentic Chat (GPT-5.2 Codex)", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-01-22", + "last_updated": "2026-01-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "gitlab/duo-chat-haiku-4.5", + "name": "Agentic Chat (Claude Haiku 4.5)", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2026-01-08", + "last_updated": "2026-01-08", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "gitlab/duo-chat-opus-4.5", + "name": "Agentic Chat (Claude Opus 4.5)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2026-01-08", + "last_updated": "2026-01-08", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "gitlab/duo-chat-opus-4.6", + "name": "Agentic Chat (Claude Opus 4.6)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "gitlab/duo-chat-sonnet-4.5", + "name": "Agentic Chat (Claude Sonnet 4.5)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2026-01-08", + "last_updated": "2026-01-08", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "gitlab/duo-chat-sonnet-4.6", + "name": "Agentic Chat (Claude Sonnet 4.6)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "google-vertex-anthropic/claude-3.5-haiku", + "name": "Claude Haiku 3.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07-31", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 4.0, + "cache_read": 0.08, + "cache_write": 1.0 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "google-vertex-anthropic/claude-3.5-sonnet", + "name": "Claude Sonnet 3.5 v2", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04-30", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "google-vertex-anthropic/claude-3.7-sonnet", + "name": "Claude Sonnet 3.7", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10-31", + "release_date": "2025-02-19", + "last_updated": "2025-02-19", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "google-vertex-anthropic/claude-haiku-4.5", + "name": "Claude Haiku 4.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "google-vertex-anthropic/claude-opus-4", + "name": "Claude Opus 4", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "google-vertex-anthropic/claude-opus-4.1", + "name": "Claude Opus 4.1", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "google-vertex-anthropic/claude-opus-4.5", + "name": "Claude Opus 4.5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-11-24", + "last_updated": "2025-11-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "google-vertex-anthropic/claude-opus-4.6@default", + "name": "Claude Opus 4.6", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "google-vertex-anthropic/claude-sonnet-4", + "name": "Claude Sonnet 4", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "google-vertex-anthropic/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "google-vertex-anthropic/claude-sonnet-4.6@default", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "google-vertex/deepseek-ai/deepseek-v3.1-maas", + "name": "DeepSeek V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-28", + "last_updated": "2025-08-28", + "modalities": { + "input": [ + "text", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.7 + }, + "limit": { + "context": 163840, + "output": 32768 + } + }, { "id": "google-vertex/gemini-2.0-flash", "name": "Gemini 2.0 Flash", @@ -6627,6 +29036,74 @@ "output": 65536 } }, + { + "id": "google-vertex/gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "google-vertex/gemini-3.1-pro-preview-customtools", + "name": "Gemini 3.1 Pro Preview Custom Tools", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, { "id": "google-vertex/gemini-embedding-001", "name": "Gemini Embedding 001", @@ -6725,6 +29202,65 @@ "output": 65536 } }, + { + "id": "google-vertex/meta/llama-3.3-70b-instruct-maas", + "name": "Llama 3.3 70B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2025-04-29", + "last_updated": "2025-04-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.72, + "output": 0.72 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "google-vertex/meta/llama-4-maverick-17b-128e-instruct-maas", + "name": "Llama 4 Maverick 17B 128E Instruct", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-29", + "last_updated": "2025-04-29", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 1.15 + }, + "limit": { + "context": 524288, + "output": 8192 + } + }, { "id": "google-vertex/openai/gpt-oss-120b-maas", "name": "GPT OSS 120B", @@ -6782,16 +29318,15 @@ } }, { - "id": "google-vertex/zai-org/glm-4.7-maas", - "name": "GLM-4.7", - "family": "glm", + "id": "google-vertex/qwen/qwen3-235b-a22b-instruct-2507-maas", + "name": "Qwen3 235B A22B Instruct", + "family": "qwen", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-04", - "release_date": "2025-12-22", - "last_updated": "2025-12-22", + "release_date": "2025-08-13", + "last_updated": "2025-08-13", "modalities": { "input": [ "text" @@ -6801,10 +29336,69 @@ ] }, "open_weights": true, + "cost": { + "input": 0.22, + "output": 0.88 + }, + "limit": { + "context": 262144, + "output": 16384 + } + }, + { + "id": "google-vertex/zai-org/glm-4.7-maas", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-01-06", + "last_updated": "2026-01-06", + "modalities": { + "input": [ + "text", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": true, "cost": { "input": 0.6, "output": 2.2 }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "google-vertex/zai-org/glm-5-maas", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.1 + }, "limit": { "context": 204800, "output": 131072 @@ -7506,6 +30100,74 @@ "output": 64000 } }, + { + "id": "google/gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "google/gemini-3.1-pro-preview-customtools", + "name": "Gemini 3.1 Pro Preview Custom Tools", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, { "id": "google/gemini-embedding-001", "name": "Gemini Embedding 001", @@ -7668,6 +30330,14582 @@ "output": 65536 } }, + { + "id": "groq/deepseek-r1-distill-llama-70b", + "name": "DeepSeek R1 Distill Llama 70B", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.75, + "output": 0.99 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "groq/gemma2-9b-it", + "name": "Gemma 2 9B", + "family": "gemma", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2024-06-27", + "last_updated": "2024-06-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "groq/llama-3.1-8b-instant", + "name": "Llama 3.1 8B Instant", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.08 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "groq/llama-3.3-70b-versatile", + "name": "Llama 3.3 70B Versatile", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.59, + "output": 0.79 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "groq/llama-guard-3-8b", + "name": "Llama Guard 3 8B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "groq/llama3-70b", + "name": "Llama 3 70B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-03", + "release_date": "2024-04-18", + "last_updated": "2024-04-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.59, + "output": 0.79 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "groq/llama3-8b", + "name": "Llama 3 8B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-03", + "release_date": "2024-04-18", + "last_updated": "2024-04-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.08 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "groq/meta-llama/llama-4-maverick-17b-128e-instruct", + "name": "Llama 4 Maverick 17B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "groq/meta-llama/llama-4-scout-17b-16e-instruct", + "name": "Llama 4 Scout 17B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.11, + "output": 0.34 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "groq/meta-llama/llama-guard-4-12b", + "name": "Llama Guard 4 12B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 131072, + "output": 1024 + } + }, + { + "id": "groq/mistral-saba-24b", + "name": "Mistral Saba 24B", + "family": "mistral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-02-06", + "last_updated": "2025-02-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.79, + "output": 0.79 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "groq/moonshotai/kimi-k2-instruct", + "name": "Kimi K2 Instruct", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-14", + "last_updated": "2025-07-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.0 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "groq/openai/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "groq/openai/gpt-oss-20b", + "name": "GPT OSS 20B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.075, + "output": 0.3 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "groq/qwen-qwq-32b", + "name": "Qwen QwQ 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2024-11-27", + "last_updated": "2024-11-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.29, + "output": 0.39 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "groq/qwen/qwen3-32b", + "name": "Qwen3 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11-08", + "release_date": "2024-12-23", + "last_updated": "2024-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.29, + "output": 0.59 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "helicone/chatgpt-4o", + "name": "OpenAI ChatGPT-4o", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2024-08-14", + "last_updated": "2024-08-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 20.0, + "cache_read": 2.5 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "helicone/claude-3-haiku", + "name": "Anthropic: Claude 3 Haiku", + "family": "claude-haiku", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-03", + "release_date": "2024-03-07", + "last_updated": "2024-03-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.25, + "cache_read": 0.03, + "cache_write": 0.3 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "helicone/claude-3.5-haiku", + "name": "Anthropic: Claude 3.5 Haiku", + "family": "claude-haiku", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.7999999999999999, + "output": 4.0, + "cache_read": 0.08, + "cache_write": 1.0 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "helicone/claude-3.5-sonnet-v2", + "name": "Anthropic: Claude 3.5 Sonnet v2", + "family": "claude-sonnet", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.30000000000000004, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "helicone/claude-3.7-sonnet", + "name": "Anthropic: Claude 3.7 Sonnet", + "family": "claude-sonnet", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02", + "release_date": "2025-02-19", + "last_updated": "2025-02-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.30000000000000004, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "helicone/claude-4.5-haiku", + "name": "Anthropic: Claude 4.5 Haiku", + "family": "claude-haiku", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-10", + "release_date": "2025-10-01", + "last_updated": "2025-10-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.09999999999999999, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "helicone/claude-4.5-opus", + "name": "Anthropic: Claude Opus 4.5", + "family": "claude-opus", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-24", + "last_updated": "2025-11-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "helicone/claude-4.5-sonnet", + "name": "Anthropic: Claude Sonnet 4.5", + "family": "claude-sonnet", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.30000000000000004, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "helicone/claude-haiku-4.5", + "name": "Anthropic: Claude 4.5 Haiku (20251001)", + "family": "claude-haiku", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-10", + "release_date": "2025-10-01", + "last_updated": "2025-10-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.09999999999999999, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "helicone/claude-opus-4", + "name": "Anthropic: Claude Opus 4", + "family": "claude-opus", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2025-05-14", + "last_updated": "2025-05-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "helicone/claude-opus-4.1", + "name": "Anthropic: Claude Opus 4.1 (20250805)", + "family": "claude-opus", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "helicone/claude-sonnet-4", + "name": "Anthropic: Claude Sonnet 4", + "family": "claude-sonnet", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2025-05-14", + "last_updated": "2025-05-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.30000000000000004, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "helicone/claude-sonnet-4.5", + "name": "Anthropic: Claude Sonnet 4.5 (20250929)", + "family": "claude-sonnet", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.30000000000000004, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "helicone/codex-mini", + "name": "OpenAI Codex Mini Latest", + "family": "gpt-codex-mini", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 6.0, + "cache_read": 0.375 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "helicone/deepseek-r1-distill-llama-70b", + "name": "DeepSeek R1 Distill Llama 70B", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.03, + "output": 0.13 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "helicone/deepseek-reasoner", + "name": "DeepSeek Reasoner", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.56, + "output": 1.68, + "cache_read": 0.07 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "helicone/deepseek-tng-r1t2-chimera", + "name": "DeepSeek TNG R1T2 Chimera", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-02", + "last_updated": "2025-07-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 130000, + "output": 163840 + } + }, + { + "id": "helicone/deepseek-v3", + "name": "DeepSeek V3", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-12-26", + "last_updated": "2024-12-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.56, + "output": 1.68, + "cache_read": 0.07 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "helicone/deepseek-v3.1-terminus", + "name": "DeepSeek V3.1 Terminus", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-22", + "last_updated": "2025-09-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 1.0, + "cache_read": 0.21600000000000003 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "helicone/deepseek-v3.2", + "name": "DeepSeek V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-22", + "last_updated": "2025-09-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.41 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "helicone/ernie-4.5-21b-a3b-thinking", + "name": "Baidu Ernie 4.5 21B A3B Thinking", + "family": "ernie", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-03-16", + "last_updated": "2025-03-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 128000, + "output": 8000 + } + }, + { + "id": "helicone/gemini-2.5-flash", + "name": "Google Gemini 2.5 Flash", + "family": "gemini-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.075, + "cache_write": 0.3 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "helicone/gemini-2.5-flash-lite", + "name": "Google Gemini 2.5 Flash Lite", + "family": "gemini-flash-lite", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-22", + "last_updated": "2025-07-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09999999999999999, + "output": 0.39999999999999997, + "cache_read": 0.024999999999999998, + "cache_write": 0.09999999999999999 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "helicone/gemini-2.5-pro", + "name": "Google Gemini 2.5 Pro", + "family": "gemini-pro", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.3125, + "cache_write": 1.25 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "helicone/gemini-3-pro-preview", + "name": "Google Gemini 3 Pro Preview", + "family": "gemini-pro", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.19999999999999998 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "helicone/gemma-3-12b-it", + "name": "Google Gemma 3 12B", + "family": "gemma", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-12-01", + "last_updated": "2024-12-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.049999999999999996, + "output": 0.09999999999999999 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "helicone/gemma2-9b-it", + "name": "Google Gemma 2", + "family": "gemma", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2024-06-25", + "last_updated": "2024-06-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.01, + "output": 0.03 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "helicone/glm-4.6", + "name": "Zai GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.44999999999999996, + "output": 1.5 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "helicone/gpt-4.1", + "name": "OpenAI GPT-4.1", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "helicone/gpt-4.1-mini", + "name": "OpenAI GPT-4.1 Mini", + "family": "gpt-mini", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.39999999999999997, + "output": 1.5999999999999999, + "cache_read": 0.09999999999999999 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "helicone/gpt-4.1-nano", + "name": "OpenAI GPT-4.1 Nano", + "family": "gpt-nano", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09999999999999999, + "output": 0.39999999999999997, + "cache_read": 0.024999999999999998 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "helicone/gpt-4o", + "name": "OpenAI GPT-4o", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-05", + "release_date": "2024-05-13", + "last_updated": "2024-05-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0, + "cache_read": 1.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "helicone/gpt-4o-mini", + "name": "OpenAI GPT-4o-mini", + "family": "gpt-mini", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.075 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "helicone/gpt-5", + "name": "OpenAI GPT-5", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.12500000000000003 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "helicone/gpt-5-chat", + "name": "OpenAI GPT-5 Chat Latest", + "family": "gpt-codex", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09", + "release_date": "2024-09-30", + "last_updated": "2024-09-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.12500000000000003 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "helicone/gpt-5-codex", + "name": "OpenAI: GPT-5 Codex", + "family": "gpt-codex", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.12500000000000003 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "helicone/gpt-5-mini", + "name": "OpenAI GPT-5 Mini", + "family": "gpt-mini", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.024999999999999998 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "helicone/gpt-5-nano", + "name": "OpenAI GPT-5 Nano", + "family": "gpt-nano", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.049999999999999996, + "output": 0.39999999999999997, + "cache_read": 0.005 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "helicone/gpt-5-pro", + "name": "OpenAI: GPT-5 Pro", + "family": "gpt-pro", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 120.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "helicone/gpt-5.1", + "name": "OpenAI GPT-5.1", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.12500000000000003 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "helicone/gpt-5.1-chat", + "name": "OpenAI GPT-5.1 Chat", + "family": "gpt-codex", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.12500000000000003 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "helicone/gpt-5.1-codex", + "name": "OpenAI: GPT-5.1 Codex", + "family": "gpt-codex", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.12500000000000003 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "helicone/gpt-5.1-codex-mini", + "name": "OpenAI: GPT-5.1 Codex Mini", + "family": "gpt-codex", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.024999999999999998 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "helicone/gpt-oss-120b", + "name": "OpenAI GPT-OSS 120b", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2024-06-01", + "last_updated": "2024-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.04, + "output": 0.16 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "helicone/gpt-oss-20b", + "name": "OpenAI GPT-OSS 20b", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2024-06-01", + "last_updated": "2024-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.049999999999999996, + "output": 0.19999999999999998 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "helicone/grok-3", + "name": "xAI Grok 3", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2024-06-01", + "last_updated": "2024-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "helicone/grok-3-mini", + "name": "xAI Grok 3 Mini", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2024-06-01", + "last_updated": "2024-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.5, + "cache_read": 0.075 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "helicone/grok-4", + "name": "xAI Grok 4", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-07-09", + "last_updated": "2024-07-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "helicone/grok-4-fast", + "name": "xAI: Grok 4 Fast Reasoning", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.19999999999999998, + "output": 0.5, + "cache_read": 0.049999999999999996 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "helicone/grok-4-fast-non", + "name": "xAI Grok 4 Fast Non-Reasoning", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-19", + "last_updated": "2025-09-19", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.19999999999999998, + "output": 0.5, + "cache_read": 0.049999999999999996 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "helicone/grok-4.1-fast", + "name": "xAI Grok 4.1 Fast Reasoning", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-17", + "last_updated": "2025-11-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.19999999999999998, + "output": 0.5, + "cache_read": 0.049999999999999996 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "helicone/grok-4.1-fast-non", + "name": "xAI Grok 4.1 Fast Non-Reasoning", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-17", + "last_updated": "2025-11-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 0.19999999999999998, + "output": 0.5, + "cache_read": 0.049999999999999996 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "helicone/grok-code-fast-1", + "name": "xAI Grok Code Fast 1", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2024-08-25", + "last_updated": "2024-08-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.19999999999999998, + "output": 1.5, + "cache_read": 0.02 + }, + "limit": { + "context": 256000, + "output": 10000 + } + }, + { + "id": "helicone/hermes-2-pro-llama-3-8b", + "name": "Hermes 2 Pro Llama 3 8B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-05", + "release_date": "2024-05-27", + "last_updated": "2024-05-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.14 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "helicone/kimi-k2", + "name": "Kimi K2 (09/05)", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 2.0, + "cache_read": 0.39999999999999997 + }, + "limit": { + "context": 262144, + "output": 16384 + } + }, + { + "id": "helicone/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.48, + "output": 2.0 + }, + "limit": { + "context": 256000, + "output": 262144 + } + }, + { + "id": "helicone/llama-3.1-8b-instant", + "name": "Meta Llama 3.1 8B Instant", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-07-01", + "last_updated": "2024-07-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.049999999999999996, + "output": 0.08 + }, + "limit": { + "context": 131072, + "output": 32678 + } + }, + { + "id": "helicone/llama-3.1-8b-instruct", + "name": "Meta Llama 3.1 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.02, + "output": 0.049999999999999996 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "helicone/llama-3.1-8b-instruct-turbo", + "name": "Meta Llama 3.1 8B Instruct Turbo", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.02, + "output": 0.03 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "helicone/llama-3.3-70b-instruct", + "name": "Meta Llama 3.3 70B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.13, + "output": 0.39 + }, + "limit": { + "context": 128000, + "output": 16400 + } + }, + { + "id": "helicone/llama-3.3-70b-versatile", + "name": "Meta Llama 3.3 70B Versatile", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.59, + "output": 0.7899999999999999 + }, + "limit": { + "context": 131072, + "output": 32678 + } + }, + { + "id": "helicone/llama-4-maverick", + "name": "Meta Llama 4 Maverick 17B 128E", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "helicone/llama-4-scout", + "name": "Meta Llama 4 Scout 17B 16E", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.08, + "output": 0.3 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "helicone/llama-guard-4", + "name": "Meta Llama Guard 4 12B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.21, + "output": 0.21 + }, + "limit": { + "context": 131072, + "output": 1024 + } + }, + { + "id": "helicone/llama-prompt-guard-2-22m", + "name": "Meta Llama Prompt Guard 2 22M", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-10-01", + "last_updated": "2024-10-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.01, + "output": 0.01 + }, + "limit": { + "context": 512, + "output": 2 + } + }, + { + "id": "helicone/llama-prompt-guard-2-86m", + "name": "Meta Llama Prompt Guard 2 86M", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-10-01", + "last_updated": "2024-10-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.01, + "output": 0.01 + }, + "limit": { + "context": 512, + "output": 2 + } + }, + { + "id": "helicone/mistral-large", + "name": "Mistral-Large", + "family": "mistral-large", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-07-24", + "last_updated": "2024-07-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "helicone/mistral-nemo", + "name": "Mistral Nemo", + "family": "mistral-nemo", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 20.0, + "output": 40.0 + }, + "limit": { + "context": 128000, + "output": 16400 + } + }, + { + "id": "helicone/mistral-small", + "name": "Mistral Small", + "family": "mistral-small", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-02", + "release_date": "2024-02-26", + "last_updated": "2024-02-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 75.0, + "output": 200.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "helicone/o1", + "name": "OpenAI: o1", + "family": "o", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 60.0, + "cache_read": 7.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "helicone/o1-mini", + "name": "OpenAI: o1-mini", + "family": "o-mini", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.55 + }, + "limit": { + "context": 128000, + "output": 65536 + } + }, + { + "id": "helicone/o3", + "name": "OpenAI o3", + "family": "o", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2024-06", + "release_date": "2024-06-01", + "last_updated": "2024-06-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "helicone/o3-mini", + "name": "OpenAI o3 Mini", + "family": "o-mini", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2023-10", + "release_date": "2023-10-01", + "last_updated": "2023-10-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.55 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "helicone/o3-pro", + "name": "OpenAI o3 Pro", + "family": "o-pro", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2024-06", + "release_date": "2024-06-01", + "last_updated": "2024-06-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 20.0, + "output": 80.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "helicone/o4-mini", + "name": "OpenAI o4 Mini", + "family": "o-mini", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "knowledge": "2024-06", + "release_date": "2024-06-01", + "last_updated": "2024-06-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.275 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "helicone/qwen2.5-coder-7b-fast", + "name": "Qwen2.5 Coder 7B fast", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2024-09-15", + "last_updated": "2024-09-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.03, + "output": 0.09 + }, + "limit": { + "context": 32000, + "output": 8192 + } + }, + { + "id": "helicone/qwen3-235b-a22b-thinking", + "name": "Qwen3 235B A22B Thinking", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.9000000000000004 + }, + "limit": { + "context": 262144, + "output": 81920 + } + }, + { + "id": "helicone/qwen3-30b-a3b", + "name": "Qwen3 30B A3B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-06-01", + "last_updated": "2025-06-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.08, + "output": 0.29 + }, + "limit": { + "context": 41000, + "output": 41000 + } + }, + { + "id": "helicone/qwen3-32b", + "name": "Qwen3 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04-28", + "last_updated": "2025-04-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 0.59 + }, + "limit": { + "context": 131072, + "output": 40960 + } + }, + { + "id": "helicone/qwen3-coder", + "name": "Qwen3 Coder 480B A35B Instruct Turbo", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.22, + "output": 0.95 + }, + "limit": { + "context": 262144, + "output": 16384 + } + }, + { + "id": "helicone/qwen3-coder-30b-a3b-instruct", + "name": "Qwen3 Coder 30B A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-31", + "last_updated": "2025-07-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09999999999999999, + "output": 0.3 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "helicone/qwen3-next-80b-a3b-instruct", + "name": "Qwen3 Next 80B A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 1.4 + }, + "limit": { + "context": 262000, + "output": 16384 + } + }, + { + "id": "helicone/qwen3-vl-235b-a22b-instruct", + "name": "Qwen3 VL 235B A22B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.5 + }, + "limit": { + "context": 256000, + "output": 16384 + } + }, + { + "id": "helicone/sonar", + "name": "Perplexity Sonar", + "family": "sonar", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-27", + "last_updated": "2025-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 1.0 + }, + "limit": { + "context": 127000, + "output": 4096 + } + }, + { + "id": "helicone/sonar-deep-research", + "name": "Perplexity Sonar Deep Research", + "family": "sonar-deep-research", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-27", + "last_updated": "2025-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 127000, + "output": 4096 + } + }, + { + "id": "helicone/sonar-pro", + "name": "Perplexity Sonar Pro", + "family": "sonar-pro", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-27", + "last_updated": "2025-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "helicone/sonar-reasoning-pro", + "name": "Perplexity Sonar Reasoning Pro", + "family": "sonar-reasoning", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-27", + "last_updated": "2025-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 127000, + "output": 4096 + } + }, + { + "id": "huggingface/MiniMaxAI/MiniMax-M2.1", + "name": "MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-10", + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "huggingface/MiniMaxAI/MiniMax-M2.5", + "name": "MiniMax-M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "huggingface/Qwen/Qwen3-235B-A22B-Thinking", + "name": "Qwen3-235B-A22B-Thinking-2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 3.0 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct", + "name": "Qwen3-Coder-480B-A35B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 2.0 + }, + "limit": { + "context": 262144, + "output": 66536 + } + }, + { + "id": "huggingface/Qwen/Qwen3-Coder-Next", + "name": "Qwen3-Coder-Next", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-02-03", + "last_updated": "2026-02-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.5 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "huggingface/Qwen/Qwen3-Embedding-4B", + "name": "Qwen 3 Embedding 4B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.0 + }, + "limit": { + "context": 32000, + "output": 2048 + } + }, + { + "id": "huggingface/Qwen/Qwen3-Embedding-8B", + "name": "Qwen 3 Embedding 8B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.0 + }, + "limit": { + "context": 32000, + "output": 4096 + } + }, + { + "id": "huggingface/Qwen/Qwen3-Next-80B-A3B-Instruct", + "name": "Qwen3-Next-80B-A3B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-11", + "last_updated": "2025-09-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 1.0 + }, + "limit": { + "context": 262144, + "output": 66536 + } + }, + { + "id": "huggingface/Qwen/Qwen3-Next-80B-A3B-Thinking", + "name": "Qwen3-Next-80B-A3B-Thinking", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-11", + "last_updated": "2025-09-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 2.0 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "huggingface/Qwen/Qwen3.5-397B-A17B", + "name": "Qwen3.5-397B-A17B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-02-01", + "last_updated": "2026-02-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.6 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "huggingface/XiaomiMiMo/MiMo-V2-Flash", + "name": "MiMo-V2-Flash", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-12-16", + "last_updated": "2025-12-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 262144, + "output": 4096 + } + }, + { + "id": "huggingface/deepseek-ai/DeepSeek-R1", + "name": "DeepSeek-R1-0528", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2025-05-28", + "last_updated": "2025-05-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 5.0 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "huggingface/deepseek-ai/DeepSeek-V3.2", + "name": "DeepSeek-V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.28, + "output": 0.4 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "huggingface/moonshotai/Kimi-K2-Instruct", + "name": "Kimi-K2-Instruct-0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-04", + "last_updated": "2025-09-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.0 + }, + "limit": { + "context": 262144, + "output": 16384 + } + }, + { + "id": "huggingface/moonshotai/Kimi-K2-Thinking", + "name": "Kimi-K2-Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "huggingface/moonshotai/Kimi-K2.5", + "name": "Kimi-K2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-01-01", + "last_updated": "2026-01-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0, + "cache_read": 0.1 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "huggingface/zai-org/GLM-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "huggingface/zai-org/GLM-4.7-Flash", + "name": "GLM-4.7-Flash", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-08-08", + "last_updated": "2025-08-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "huggingface/zai-org/GLM-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.2 + }, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "iflowcn/deepseek-r1", + "name": "DeepSeek-R1", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "iflowcn/deepseek-v3", + "name": "DeepSeek-V3", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-26", + "last_updated": "2024-12-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "iflowcn/deepseek-v3.2", + "name": "DeepSeek-V3.2-Exp", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "iflowcn/glm-4.6", + "name": "GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-01", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "iflowcn/kimi-k2", + "name": "Kimi-K2-0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "iflowcn/qwen3-235b", + "name": "Qwen3-235B-A22B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-01", + "last_updated": "2024-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "iflowcn/qwen3-235b-a22b-instruct", + "name": "Qwen3-235B-A22B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-01", + "last_updated": "2025-07-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "iflowcn/qwen3-235b-a22b-thinking", + "name": "Qwen3-235B-A22B-Thinking", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-01", + "last_updated": "2025-07-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "iflowcn/qwen3-32b", + "name": "Qwen3-32B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-01", + "last_updated": "2024-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "iflowcn/qwen3-coder-plus", + "name": "Qwen3-Coder-Plus", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-01", + "last_updated": "2025-07-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "iflowcn/qwen3-max", + "name": "Qwen3-Max", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "iflowcn/qwen3-max-preview", + "name": "Qwen3-Max-Preview", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "iflowcn/qwen3-vl-plus", + "name": "Qwen3-VL-Plus", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "inception/mercury", + "name": "Mercury", + "family": "mercury", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2025-06-26", + "last_updated": "2025-07-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.0, + "cache_read": 0.25, + "cache_write": 1.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "inception/mercury-coder", + "name": "Mercury Coder", + "family": "mercury", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2025-02-26", + "last_updated": "2025-07-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.0, + "cache_read": 0.25, + "cache_write": 1.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "inference/google/gemma-3", + "name": "Google Gemma 3", + "family": "gemma", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.3 + }, + "limit": { + "context": 125000, + "output": 4096 + } + }, + { + "id": "inference/meta/llama-3.1-8b-instruct", + "name": "Llama 3.1 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.025, + "output": 0.025 + }, + "limit": { + "context": 16000, + "output": 4096 + } + }, + { + "id": "inference/meta/llama-3.2-11b-vision-instruct", + "name": "Llama 3.2 11B Vision Instruct", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.055, + "output": 0.055 + }, + "limit": { + "context": 16000, + "output": 4096 + } + }, + { + "id": "inference/meta/llama-3.2-1b-instruct", + "name": "Llama 3.2 1B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.01 + }, + "limit": { + "context": 16000, + "output": 4096 + } + }, + { + "id": "inference/meta/llama-3.2-3b-instruct", + "name": "Llama 3.2 3B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.02 + }, + "limit": { + "context": 16000, + "output": 4096 + } + }, + { + "id": "inference/mistral/mistral-nemo-12b-instruct", + "name": "Mistral Nemo 12B Instruct", + "family": "mistral-nemo", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.038, + "output": 0.1 + }, + "limit": { + "context": 16000, + "output": 4096 + } + }, + { + "id": "inference/osmosis/osmosis-structure-0.6b", + "name": "Osmosis Structure 0.6B", + "family": "osmosis", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.5 + }, + "limit": { + "context": 4000, + "output": 2048 + } + }, + { + "id": "inference/qwen/qwen-2.5-7b-vision-instruct", + "name": "Qwen 2.5 7B Vision Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 125000, + "output": 4096 + } + }, + { + "id": "inference/qwen/qwen3-embedding-4b", + "name": "Qwen 3 Embedding 4B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.0 + }, + "limit": { + "context": 32000, + "output": 2048 + } + }, + { + "id": "io-net/Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar", + "name": "Qwen 3 Coder 480B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-15", + "last_updated": "2025-01-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 0.95, + "cache_read": 0.11, + "cache_write": 0.44 + }, + "limit": { + "context": 106000, + "output": 4096 + } + }, + { + "id": "io-net/Qwen/Qwen2.5-VL-32B-Instruct", + "name": "Qwen 2.5 VL 32B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2024-11-01", + "last_updated": "2024-11-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.22, + "cache_read": 0.025, + "cache_write": 0.1 + }, + "limit": { + "context": 32000, + "output": 4096 + } + }, + { + "id": "io-net/Qwen/Qwen3-235B-A22B-Thinking", + "name": "Qwen 3 235B Thinking", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-07-01", + "last_updated": "2025-07-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.11, + "output": 0.6, + "cache_read": 0.055, + "cache_write": 0.22 + }, + "limit": { + "context": 262144, + "output": 4096 + } + }, + { + "id": "io-net/Qwen/Qwen3-Next-80B-A3B-Instruct", + "name": "Qwen 3 Next 80B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-10", + "last_updated": "2025-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.8, + "cache_read": 0.05, + "cache_write": 0.2 + }, + "limit": { + "context": 262144, + "output": 4096 + } + }, + { + "id": "io-net/deepseek-ai/DeepSeek-R1", + "name": "DeepSeek R1", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-01-20", + "last_updated": "2025-05-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 8.75, + "cache_read": 1.0, + "cache_write": 4.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "io-net/meta-llama/Llama-3.2-90B-Vision-Instruct", + "name": "Llama 3.2 90B Vision Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-09-25", + "last_updated": "2024-09-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 0.4, + "cache_read": 0.175, + "cache_write": 0.7 + }, + "limit": { + "context": 16000, + "output": 4096 + } + }, + { + "id": "io-net/meta-llama/Llama-3.3-70B-Instruct", + "name": "Llama 3.3 70B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.38, + "cache_read": 0.065, + "cache_write": 0.26 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "io-net/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", + "name": "Llama 4 Maverick 17B 128E Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-15", + "last_updated": "2025-01-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.075, + "cache_write": 0.3 + }, + "limit": { + "context": 430000, + "output": 4096 + } + }, + { + "id": "io-net/mistralai/Devstral-Small", + "name": "Devstral Small 2505", + "family": "devstral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-05-01", + "last_updated": "2025-05-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.22, + "cache_read": 0.025, + "cache_write": 0.1 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "io-net/mistralai/Magistral-Small", + "name": "Magistral Small 2506", + "family": "magistral-small", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-01", + "last_updated": "2025-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.5, + "cache_read": 0.25, + "cache_write": 1.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "io-net/mistralai/Mistral-Large-Instruct", + "name": "Mistral Large Instruct 2411", + "family": "mistral-large", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-11-01", + "last_updated": "2024-11-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 6.0, + "cache_read": 1.0, + "cache_write": 4.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "io-net/mistralai/Mistral-Nemo-Instruct", + "name": "Mistral Nemo Instruct 2407", + "family": "mistral-nemo", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-05", + "release_date": "2024-07-01", + "last_updated": "2024-07-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.04, + "cache_read": 0.01, + "cache_write": 0.04 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "io-net/moonshotai/Kimi-K2-Instruct", + "name": "Kimi K2 Instruct", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2024-09-05", + "last_updated": "2024-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.39, + "output": 1.9, + "cache_read": 0.195, + "cache_write": 0.78 + }, + "limit": { + "context": 32768, + "output": 4096 + } + }, + { + "id": "io-net/moonshotai/Kimi-K2-Thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2024-11-01", + "last_updated": "2024-11-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.55, + "output": 2.25, + "cache_read": 0.275, + "cache_write": 1.1 + }, + "limit": { + "context": 32768, + "output": 4096 + } + }, + { + "id": "io-net/openai/gpt-oss-120b", + "name": "GPT-OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-01", + "last_updated": "2024-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.04, + "output": 0.4, + "cache_read": 0.02, + "cache_write": 0.08 + }, + "limit": { + "context": 131072, + "output": 4096 + } + }, + { + "id": "io-net/openai/gpt-oss-20b", + "name": "GPT-OSS 20B", + "family": "gpt-oss", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-01", + "last_updated": "2024-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.14, + "cache_read": 0.015, + "cache_write": 0.06 + }, + "limit": { + "context": 64000, + "output": 4096 + } + }, + { + "id": "io-net/zai-org/GLM-4.6", + "name": "GLM 4.6", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-11-15", + "last_updated": "2024-11-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.75, + "cache_read": 0.2, + "cache_write": 0.8 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "jiekou/baidu/ernie-4.5-300b-a47b-paddle", + "name": "ERNIE 4.5 300B A47B", + "family": "ernie", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.28, + "output": 1.1 + }, + "limit": { + "context": 123000, + "output": 12000 + } + }, + { + "id": "jiekou/baidu/ernie-4.5-vl-424b-a47b", + "name": "ERNIE 4.5 VL 424B A47B", + "family": "ernie", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.42, + "output": 1.25 + }, + "limit": { + "context": 123000, + "output": 16000 + } + }, + { + "id": "jiekou/claude-haiku-4.5", + "name": "claude-haiku-4-5-20251001", + "family": "claude-haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.9, + "output": 4.5 + }, + "limit": { + "context": 20000, + "output": 64000 + } + }, + { + "id": "jiekou/claude-opus-4", + "name": "claude-opus-4-20250514", + "family": "claude-opus", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 13.5, + "output": 67.5 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "jiekou/claude-opus-4.1", + "name": "claude-opus-4-1-20250805", + "family": "claude-opus", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 13.5, + "output": 67.5 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "jiekou/claude-opus-4.5", + "name": "claude-opus-4-5-20251101", + "family": "claude-opus", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 4.5, + "output": 22.5 + }, + "limit": { + "context": 200000, + "output": 65536 + } + }, + { + "id": "jiekou/claude-opus-4.6", + "name": "claude-opus-4-6", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02", + "last_updated": "2026-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "jiekou/claude-sonnet-4", + "name": "claude-sonnet-4-20250514", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.7, + "output": 13.5 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "jiekou/claude-sonnet-4.5", + "name": "claude-sonnet-4-5-20250929", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.7, + "output": 13.5 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "jiekou/deepseek/deepseek-r1", + "name": "DeepSeek R1 0528", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.5 + }, + "limit": { + "context": 163840, + "output": 32768 + } + }, + { + "id": "jiekou/deepseek/deepseek-v3", + "name": "DeepSeek V3 0324", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.28, + "output": 1.14 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "jiekou/deepseek/deepseek-v3.1", + "name": "DeepSeek V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.0 + }, + "limit": { + "context": 163840, + "output": 32768 + } + }, + { + "id": "jiekou/gemini-2.5-flash", + "name": "gemini-2.5-flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 2.25 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "jiekou/gemini-2.5-flash-lite", + "name": "gemini-2.5-flash-lite", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.36 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "jiekou/gemini-2.5-flash-lite-preview-06-17", + "name": "gemini-2.5-flash-lite-preview-06-17", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "video", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.36 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "jiekou/gemini-2.5-flash-lite-preview-09", + "name": "gemini-2.5-flash-lite-preview-09-2025", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.36 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "jiekou/gemini-2.5-flash-preview-05-20", + "name": "gemini-2.5-flash-preview-05-20", + "family": "gemini-flash", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.135, + "output": 3.15 + }, + "limit": { + "context": 1048576, + "output": 200000 + } + }, + { + "id": "jiekou/gemini-2.5-pro", + "name": "gemini-2.5-pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.125, + "output": 9.0 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "jiekou/gemini-2.5-pro-preview-06-05", + "name": "gemini-2.5-pro-preview-06-05", + "family": "gemini-pro", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.125, + "output": 9.0 + }, + "limit": { + "context": 1048576, + "output": 200000 + } + }, + { + "id": "jiekou/gemini-3-flash-preview", + "name": "gemini-3-flash-preview", + "family": "gemini-flash", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "jiekou/gemini-3-pro-preview", + "name": "gemini-3-pro-preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.8, + "output": 10.8 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "jiekou/gpt-5-chat", + "name": "gpt-5-chat-latest", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.125, + "output": 9.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "jiekou/gpt-5-codex", + "name": "gpt-5-codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.125, + "output": 9.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "jiekou/gpt-5-mini", + "name": "gpt-5-mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.225, + "output": 1.8 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "jiekou/gpt-5-nano", + "name": "gpt-5-nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.045, + "output": 0.36 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "jiekou/gpt-5-pro", + "name": "gpt-5-pro", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 13.5, + "output": 108.0 + }, + "limit": { + "context": 400000, + "output": 272000 + } + }, + { + "id": "jiekou/gpt-5.1", + "name": "gpt-5.1", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02", + "last_updated": "2026-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.125, + "output": 9.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "jiekou/gpt-5.1-codex", + "name": "gpt-5.1-codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.125, + "output": 9.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "jiekou/gpt-5.1-codex-max", + "name": "gpt-5.1-codex-max", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.125, + "output": 9.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "jiekou/gpt-5.1-codex-mini", + "name": "gpt-5.1-codex-mini", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.225, + "output": 1.8 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "jiekou/gpt-5.2", + "name": "gpt-5.2", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.575, + "output": 12.6 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "jiekou/gpt-5.2-codex", + "name": "gpt-5.2-codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "jiekou/gpt-5.2-pro", + "name": "gpt-5.2-pro", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 18.9, + "output": 151.2 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "jiekou/grok-4", + "name": "grok-4-0709", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.7, + "output": 13.5 + }, + "limit": { + "context": 256000, + "output": 8192 + } + }, + { + "id": "jiekou/grok-4-fast", + "name": "grok-4-fast-reasoning", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.45 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "jiekou/grok-4-fast-non", + "name": "grok-4-fast-non-reasoning", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.45 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "jiekou/grok-4.1-fast", + "name": "grok-4-1-fast-reasoning", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.45 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "jiekou/grok-4.1-fast-non", + "name": "grok-4-1-fast-non-reasoning", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.45 + }, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "jiekou/grok-code-fast-1", + "name": "grok-code-fast-1", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 1.35 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "jiekou/minimax/minimax-m2.1", + "name": "Minimax M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "jiekou/minimaxai/minimax-m1-80k", + "name": "MiniMax M1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.2 + }, + "limit": { + "context": 1000000, + "output": 40000 + } + }, + { + "id": "jiekou/moonshotai/kimi-k2", + "name": "Kimi K2 0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "jiekou/moonshotai/kimi-k2-instruct", + "name": "Kimi K2 Instruct", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.57, + "output": 2.3 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "jiekou/moonshotai/kimi-k2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "jiekou/o3", + "name": "o3", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 40.0 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "jiekou/o3-mini", + "name": "o3-mini", + "family": "o", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "jiekou/o4-mini", + "name": "o4-mini", + "family": "o", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "jiekou/qwen/qwen3-235b-a22b-fp8", + "name": "Qwen3 235B A22B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 40960, + "output": 20000 + } + }, + { + "id": "jiekou/qwen/qwen3-235b-a22b-instruct", + "name": "Qwen3 235B A22B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.8 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "jiekou/qwen/qwen3-235b-a22b-thinking", + "name": "Qwen3 235B A22b Thinking 2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 3.0 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "jiekou/qwen/qwen3-30b-a3b-fp8", + "name": "Qwen3 30B A3B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.45 + }, + "limit": { + "context": 40960, + "output": 20000 + } + }, + { + "id": "jiekou/qwen/qwen3-32b-fp8", + "name": "Qwen3 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.45 + }, + "limit": { + "context": 40960, + "output": 20000 + } + }, + { + "id": "jiekou/qwen/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.29, + "output": 1.2 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "jiekou/qwen/qwen3-coder-next", + "name": "qwen/qwen3-coder-next", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-02", + "last_updated": "2026-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.5 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "jiekou/qwen/qwen3-next-80b-a3b-instruct", + "name": "Qwen3 Next 80B A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.5 + }, + "limit": { + "context": 65536, + "output": 65536 + } + }, + { + "id": "jiekou/qwen/qwen3-next-80b-a3b-thinking", + "name": "Qwen3 Next 80B A3B Thinking", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.5 + }, + "limit": { + "context": 65536, + "output": 65536 + } + }, + { + "id": "jiekou/xiaomimimo/mimo-v2-flash", + "name": "XiaomiMiMo/MiMo-V2-Flash", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "jiekou/zai-org/glm-4.5", + "name": "GLM-4.5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "jiekou/zai-org/glm-4.5v", + "name": "GLM 4.5V", + "family": "glmv", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.8 + }, + "limit": { + "context": 65536, + "output": 16384 + } + }, + { + "id": "jiekou/zai-org/glm-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "jiekou/zai-org/glm-4.7-flash", + "name": "GLM-4.7-Flash", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.4 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "kilo/allenai/molmo-2-8b", + "name": "AllenAI: Molmo2 8B", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-01-09", + "last_updated": "2026-01-31", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 36864, + "output": 36864 + } + }, + { + "id": "kilo/amazon/nova-2-lite-v1", + "name": "Amazon: Nova 2 Lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5 + }, + "limit": { + "context": 1000000, + "output": 65535 + } + }, + { + "id": "kilo/amazon/nova-pro-v1", + "name": "Amazon: Nova Pro 1.0", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-03", + "last_updated": "2024-12-03", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 3.2 + }, + "limit": { + "context": 300000, + "output": 5120 + } + }, + { + "id": "kilo/anthropic/claude-3-haiku", + "name": "Anthropic: Claude 3 Haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-03-07", + "last_updated": "2024-03-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.25, + "cache_read": 0.03, + "cache_write": 0.3 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "kilo/anthropic/claude-3.5-haiku", + "name": "Anthropic: Claude 3.5 Haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 4.0, + "cache_read": 0.08, + "cache_write": 1.0 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "kilo/anthropic/claude-3.5-sonnet", + "name": "Anthropic: Claude 3.5 Sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 6.0, + "output": 30.0 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "kilo/anthropic/claude-3.7-sonnet", + "name": "Anthropic: Claude 3.7 Sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-02-19", + "last_updated": "2025-02-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "kilo/anthropic/claude-3.7-sonnet:thinking", + "name": "Anthropic: Claude 3.7 Sonnet (thinking)", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-02-19", + "last_updated": "2025-02-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "kilo/anthropic/claude-haiku-4.5", + "name": "Anthropic: Claude Haiku 4.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "kilo/anthropic/claude-opus-4", + "name": "Anthropic: Claude Opus 4", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "kilo/anthropic/claude-opus-4.1", + "name": "Anthropic: Claude Opus 4.1", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "kilo/anthropic/claude-opus-4.5", + "name": "Anthropic: Claude Opus 4.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-24", + "last_updated": "2025-11-24", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "kilo/anthropic/claude-opus-4.6", + "name": "Anthropic: Claude Opus 4.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "kilo/anthropic/claude-sonnet-4", + "name": "Anthropic: Claude Sonnet 4", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "kilo/anthropic/claude-sonnet-4.5", + "name": "Anthropic: Claude Sonnet 4.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "kilo/arcee-ai/trinity-large-preview:free", + "name": "Arcee AI: Trinity Large Preview (free)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-28", + "last_updated": "2026-01-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131000, + "output": 26200 + } + }, + { + "id": "kilo/arcee-ai/trinity-mini", + "name": "Arcee AI: Trinity Mini", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12", + "last_updated": "2026-01-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.045, + "output": 0.15 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "kilo/arcee-ai/trinity-mini:free", + "name": "Arcee AI: Trinity Mini (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-28", + "last_updated": "2026-01-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/baidu/ernie-4.5-21b-a3b", + "name": "Baidu: ERNIE 4.5 21B A3B", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-30", + "last_updated": "2025-06-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 120000, + "output": 8000 + } + }, + { + "id": "kilo/baidu/ernie-4.5-21b-a3b-thinking", + "name": "Baidu: ERNIE 4.5 21B A3B Thinking", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-09-19", + "last_updated": "2025-09-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "kilo/baidu/ernie-4.5-300b-a47b", + "name": "Baidu: ERNIE 4.5 300B A47B ", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-06-30", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.28, + "output": 1.1 + }, + "limit": { + "context": 123000, + "output": 12000 + } + }, + { + "id": "kilo/baidu/ernie-4.5-vl-28b-a3b", + "name": "Baidu: ERNIE 4.5 VL 28B A3B", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-30", + "last_updated": "2025-06-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.56 + }, + "limit": { + "context": 30000, + "output": 8000 + } + }, + { + "id": "kilo/baidu/ernie-4.5-vl-424b-a47b", + "name": "Baidu: ERNIE 4.5 VL 424B A47B ", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-06-30", + "last_updated": "2026-01", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.42, + "output": 1.25 + }, + "limit": { + "context": 123000, + "output": 16000 + } + }, + { + "id": "kilo/bytedance-seed/seed-1.6", + "name": "ByteDance Seed: Seed 1.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09", + "last_updated": "2025-09", + "modalities": { + "input": [ + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "kilo/cognitivecomputations/dolphin-mistral-24b-venice-edition:free", + "name": "Venice: Uncensored (free)", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-07-09", + "last_updated": "2026-01-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 6554 + } + }, + { + "id": "kilo/cohere/command-a", + "name": "Cohere: Command A", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-13", + "last_updated": "2025-03-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.5, + "output": 10.0 + }, + "limit": { + "context": 256000, + "output": 8192 + } + }, + { + "id": "kilo/cohere/command-r-08", + "name": "Cohere: Command R (08-2024)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-08-30", + "last_updated": "2024-08-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 128000, + "output": 4000 + } + }, + { + "id": "kilo/cohere/command-r-plus-08", + "name": "Cohere: Command R+ (08-2024)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-08-30", + "last_updated": "2024-08-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.5, + "output": 10.0 + }, + "limit": { + "context": 128000, + "output": 4000 + } + }, + { + "id": "kilo/cohere/command-r7b-12", + "name": "Cohere: Command R7B (12-2024)", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-02-27", + "last_updated": "2024-02-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0375, + "output": 0.15 + }, + "limit": { + "context": 128000, + "output": 4000 + } + }, + { + "id": "kilo/deepseek/deepseek-chat", + "name": "DeepSeek: DeepSeek V3", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-01", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.15 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "kilo/deepseek/deepseek-chat-v3", + "name": "DeepSeek: DeepSeek V3 0324", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-24", + "last_updated": "2025-03-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.19, + "output": 0.87, + "cache_read": 0.095 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "kilo/deepseek/deepseek-chat-v3.1", + "name": "DeepSeek: DeepSeek V3.1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-21", + "last_updated": "2025-08-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.75 + }, + "limit": { + "context": 32768, + "output": 7168 + } + }, + { + "id": "kilo/deepseek/deepseek-r1", + "name": "DeepSeek: R1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.5 + }, + "limit": { + "context": 64000, + "output": 16000 + } + }, + { + "id": "kilo/deepseek/deepseek-r1-0528:free", + "name": "DeepSeek: R1 0528 (free)", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-05-28", + "last_updated": "2025-05-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "kilo/deepseek/deepseek-r1-distill-llama-70b", + "name": "DeepSeek: R1 Distill Llama 70B", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-01-23", + "last_updated": "2025-01-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.11, + "cache_read": 0.015 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "kilo/deepseek/deepseek-r1-distill-qwen-32b", + "name": "DeepSeek: R1 Distill Qwen 32B", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.29, + "output": 0.29 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "kilo/deepseek/deepseek-v3.1-terminus", + "name": "DeepSeek: DeepSeek V3.1 Terminus", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-22", + "last_updated": "2025-09-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.21, + "output": 0.79, + "cache_read": 0.13 + }, + "limit": { + "context": 163840, + "output": 32768 + } + }, + { + "id": "kilo/deepseek/deepseek-v3.1-terminus:exacto", + "name": "DeepSeek: DeepSeek V3.1 Terminus (exacto)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-22", + "last_updated": "2025-09-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.21, + "output": 0.79, + "cache_read": 0.168 + }, + "limit": { + "context": 163840, + "output": 32768 + } + }, + { + "id": "kilo/deepseek/deepseek-v3.2", + "name": "DeepSeek: DeepSeek V3.2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.38, + "cache_read": 0.125 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "kilo/deepseek/deepseek-v3.2-exp", + "name": "DeepSeek: DeepSeek V3.2 Exp", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 0.41 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "kilo/deepseek/deepseek-v3.2-speciale", + "name": "DeepSeek: DeepSeek V3.2 Speciale", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 0.41, + "cache_read": 0.135 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "kilo/essentialai/rnj-1-instruct", + "name": "EssentialAI: Rnj 1 Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-05", + "last_updated": "2025-12-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.15 + }, + "limit": { + "context": 32768, + "output": 6554 + } + }, + { + "id": "kilo/google/gemini-2.0-flash-001", + "name": "Google: Gemini 2.0 Flash", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.025, + "cache_write": 0.083333 + }, + "limit": { + "context": 1048576, + "output": 8192 + } + }, + { + "id": "kilo/google/gemini-2.0-flash-lite-001", + "name": "Google: Gemini 2.0 Flash Lite", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-11", + "last_updated": "2025-06-16", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.3 + }, + "limit": { + "context": 1048576, + "output": 8192 + } + }, + { + "id": "kilo/google/gemini-2.5-flash", + "name": "Google: Gemini 2.5 Flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-17", + "last_updated": "2025-07-17", + "modalities": { + "input": [ + "image", + "text", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.03, + "cache_write": 0.083333 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "kilo/google/gemini-2.5-flash-lite", + "name": "Google: Gemini 2.5 Flash Lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.01, + "cache_write": 0.083333 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "kilo/google/gemini-2.5-flash-lite-preview-09", + "name": "Google: Gemini 2.5 Flash Lite Preview 09-2025", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-25", + "last_updated": "2025-09-25", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.01, + "cache_write": 0.083333 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "kilo/google/gemini-2.5-flash-preview-09", + "name": "Google: Gemini 2.5 Flash Preview 09-2025", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-25", + "last_updated": "2025-09-25", + "modalities": { + "input": [ + "image", + "text", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.03, + "cache_write": 0.083333 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "kilo/google/gemini-2.5-pro", + "name": "Google: Gemini 2.5 Pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-20", + "last_updated": "2025-06-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125, + "cache_write": 0.375 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "kilo/google/gemini-2.5-pro-preview", + "name": "Google: Gemini 2.5 Pro Preview 06-05", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-05", + "last_updated": "2026-01", + "modalities": { + "input": [ + "image", + "text", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125, + "cache_write": 0.375 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "kilo/google/gemini-2.5-pro-preview-05-06", + "name": "Google: Gemini 2.5 Pro Preview 05-06", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-06", + "last_updated": "2025-05-06", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125, + "cache_write": 0.375 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "kilo/google/gemini-3-flash-preview", + "name": "Google: Gemini 3 Flash Preview", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05, + "cache_write": 0.083333 + }, + "limit": { + "context": 1048576, + "output": 65535 + } + }, + { + "id": "kilo/google/gemini-3-pro-preview", + "name": "Google: Gemini 3 Pro Preview", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-18", + "last_updated": "2025-11", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2, + "cache_write": 0.375 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "kilo/google/gemma-2-27b-it", + "name": "Google: Gemma 2 27B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-06-24", + "last_updated": "2024-06-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.65, + "output": 0.65 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "kilo/google/gemma-2-9b-it", + "name": "Google: Gemma 2 9B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-06-28", + "last_updated": "2024-06-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.09 + }, + "limit": { + "context": 8192, + "output": 1639 + } + }, + { + "id": "kilo/google/gemma-3-12b-it", + "name": "Google: Gemma 3 12B", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-13", + "last_updated": "2025-03-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.1, + "cache_read": 0.015 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "kilo/google/gemma-3-12b-it:free", + "name": "Google: Gemma 3 12B (free)", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-13", + "last_updated": "2025-03-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "kilo/google/gemma-3-27b-it", + "name": "Google: Gemma 3 27B", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-12", + "last_updated": "2025-03-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.04, + "output": 0.15, + "cache_read": 0.02 + }, + "limit": { + "context": 128000, + "output": 65536 + } + }, + { + "id": "kilo/google/gemma-3-27b-it:free", + "name": "Google: Gemma 3 27B (free)", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-12", + "last_updated": "2025-03-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "kilo/google/gemma-3-4b-it", + "name": "Google: Gemma 3 4B", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-13", + "last_updated": "2025-03-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01703, + "output": 0.068154 + }, + "limit": { + "context": 96000, + "output": 19200 + } + }, + { + "id": "kilo/google/gemma-3-4b-it:free", + "name": "Google: Gemma 3 4B (free)", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-13", + "last_updated": "2025-03-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "kilo/google/gemma-3n-e2b-it:free", + "name": "Google: Gemma 3n 2B (free)", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "kilo/google/gemma-3n-e4b-it", + "name": "Google: Gemma 3n 4B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-05-20", + "last_updated": "2025-05-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.04 + }, + "limit": { + "context": 32768, + "output": 6554 + } + }, + { + "id": "kilo/google/gemma-3n-e4b-it:free", + "name": "Google: Gemma 3n 4B (free)", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-05-20", + "last_updated": "2025-05-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 2048 + } + }, + { + "id": "kilo/gryphe/mythomax-l2-13b", + "name": "MythoMax 13B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-04-25", + "last_updated": "2024-04-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.06 + }, + "limit": { + "context": 4096, + "output": 4096 + } + }, + { + "id": "kilo/inception/mercury", + "name": "Inception: Mercury", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-26", + "last_updated": "2025-07-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "kilo/inception/mercury-coder", + "name": "Inception: Mercury Coder", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-02-26", + "last_updated": "2025-07-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "kilo/kilo/auto", + "name": "Kilo: Auto", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2024-06-01", + "last_updated": "2024-06-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 1.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "kilo/kwaipilot/kat-coder-pro", + "name": "Kwaipilot: KAT-Coder-Pro V1", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-30", + "last_updated": "2025-10-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.207, + "output": 0.828, + "cache_read": 0.0414 + }, + "limit": { + "context": 256000, + "output": 128000 + } + }, + { + "id": "kilo/liquid/lfm-2.5-1.2b-instruct:free", + "name": "LiquidAI: LFM2.5-1.2B-Instruct (free)", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-01-20", + "last_updated": "2026-01-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 6554 + } + }, + { + "id": "kilo/liquid/lfm-2.5-1.2b-thinking:free", + "name": "LiquidAI: LFM2.5-1.2B-Thinking (free)", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2026-01-20", + "last_updated": "2026-01-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 6554 + } + }, + { + "id": "kilo/meituan/longcat-flash-chat", + "name": "Meituan: LongCat Flash Chat", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-08-30", + "last_updated": "2025-08-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.8, + "cache_read": 0.2 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "kilo/meta-llama/llama-3-70b-instruct", + "name": "Meta: Llama 3 70B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.51, + "output": 0.74 + }, + "limit": { + "context": 8192, + "output": 8000 + } + }, + { + "id": "kilo/meta-llama/llama-3-8b-instruct", + "name": "Meta: Llama 3 8B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-04-25", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.04 + }, + "limit": { + "context": 8192, + "output": 16384 + } + }, + { + "id": "kilo/meta-llama/llama-3.1-405b-instruct", + "name": "Meta: Llama 3.1 405B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-16", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 4.0, + "output": 4.0 + }, + "limit": { + "context": 131000, + "output": 26200 + } + }, + { + "id": "kilo/meta-llama/llama-3.1-70b-instruct", + "name": "Meta: Llama 3.1 70B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-16", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 0.4 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/meta-llama/llama-3.1-8b-instruct", + "name": "Meta: Llama 3.1 8B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.05 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "kilo/meta-llama/llama-3.2-11b-vision-instruct", + "name": "Meta: Llama 3.2 11B Vision Instruct", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-09-25", + "last_updated": "2024-09-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.049, + "output": 0.049 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "kilo/meta-llama/llama-3.2-1b-instruct", + "name": "Meta: Llama 3.2 1B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.027, + "output": 0.2 + }, + "limit": { + "context": 60000, + "output": 12000 + } + }, + { + "id": "kilo/meta-llama/llama-3.2-3b-instruct", + "name": "Meta: Llama 3.2 3B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.02 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "kilo/meta-llama/llama-3.2-3b-instruct:free", + "name": "Meta: Llama 3.2 3B Instruct (free)", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-09-25", + "last_updated": "2024-09-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/meta-llama/llama-3.3-70b-instruct", + "name": "Meta: Llama 3.3 70B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-08-01", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.32 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "kilo/meta-llama/llama-3.3-70b-instruct:free", + "name": "Meta: Llama 3.3 70B Instruct (free)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "kilo/meta-llama/llama-4-maverick", + "name": "Meta: Llama 4 Maverick", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-05", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 1048576, + "output": 16384 + } + }, + { + "id": "kilo/meta-llama/llama-4-scout", + "name": "Meta: Llama 4 Scout", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.3 + }, + "limit": { + "context": 327680, + "output": 16384 + } + }, + { + "id": "kilo/meta-llama/llama-guard-3-8b", + "name": "Llama Guard 3 8B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-04-18", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.06 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/meta-llama/llama-guard-4-12b", + "name": "Meta: Llama Guard 4 12B", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.18, + "output": 0.18 + }, + "limit": { + "context": 163840, + "output": 32768 + } + }, + { + "id": "kilo/microsoft/phi-4", + "name": "Microsoft: Phi 4", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.14 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "kilo/microsoft/wizardlm-2-8x22b", + "name": "WizardLM-2 8x22B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-04-24", + "last_updated": "2024-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.62, + "output": 0.62 + }, + "limit": { + "context": 65535, + "output": 8000 + } + }, + { + "id": "kilo/minimax/minimax-01", + "name": "MiniMax: MiniMax-01", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-01-15", + "last_updated": "2025-01-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.1 + }, + "limit": { + "context": 1000192, + "output": 1000192 + } + }, + { + "id": "kilo/minimax/minimax-m1", + "name": "MiniMax: MiniMax M1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.2 + }, + "limit": { + "context": 1000000, + "output": 40000 + } + }, + { + "id": "kilo/minimax/minimax-m2", + "name": "MiniMax: MiniMax M2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-23", + "last_updated": "2025-10-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.255, + "output": 1.0, + "cache_read": 0.03 + }, + "limit": { + "context": 196608, + "output": 65536 + } + }, + { + "id": "kilo/minimax/minimax-m2.1", + "name": "MiniMax: MiniMax M2.1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 0.95, + "cache_read": 0.03 + }, + "limit": { + "context": 196608, + "output": 39322 + } + }, + { + "id": "kilo/minimax/minimax-m2.5", + "name": "MiniMax: MiniMax M2.5", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.029 + }, + "limit": { + "context": 196608, + "output": 39322 + } + }, + { + "id": "kilo/minimax/minimax-m2.5:free", + "name": "MiniMax: MiniMax M2.5 (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "kilo/mistralai/codestral", + "name": "Mistral: Codestral 2508", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-01", + "last_updated": "2025-08-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 256000, + "output": 51200 + } + }, + { + "id": "kilo/mistralai/devstral", + "name": "Mistral: Devstral 2 2512", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-12", + "last_updated": "2025-09-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.22, + "cache_read": 0.025 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "kilo/mistralai/devstral-medium", + "name": "Mistral: Devstral Medium", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-10", + "last_updated": "2025-07-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/mistralai/devstral-small", + "name": "Mistral: Devstral Small 1.1", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-07", + "last_updated": "2025-07-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/mistralai/ministral-14b", + "name": "Mistral: Ministral 3 14B 2512", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-16", + "last_updated": "2025-12-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 262144, + "output": 52429 + } + }, + { + "id": "kilo/mistralai/mistral-7b-instruct", + "name": "Mistral: Mistral 7B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-05-27", + "last_updated": "2024-05-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 32768, + "output": 4096 + } + }, + { + "id": "kilo/mistralai/mistral-7b-instruct-v0.1", + "name": "Mistral: Mistral 7B Instruct v0.1", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-03", + "last_updated": "2025-04-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.11, + "output": 0.19 + }, + "limit": { + "context": 2824, + "output": 565 + } + }, + { + "id": "kilo/mistralai/mistral-7b-instruct-v0.3", + "name": "Mistral: Mistral 7B Instruct v0.3", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-01", + "last_updated": "2025-04-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 32768, + "output": 4096 + } + }, + { + "id": "kilo/mistralai/mistral-large", + "name": "Mistral Large 2411", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-24", + "last_updated": "2024-11-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 6.0 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/mistralai/mistral-medium-3", + "name": "Mistral: Mistral Medium 3", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-07", + "last_updated": "2025-05-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/mistralai/mistral-medium-3.1", + "name": "Mistral: Mistral Medium 3.1", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-12", + "last_updated": "2025-08-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/mistralai/mistral-nemo", + "name": "Mistral: Mistral Nemo", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-01", + "last_updated": "2024-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.04 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "kilo/mistralai/mistral-small-24b-instruct", + "name": "Mistral: Mistral Small 3", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.08 + }, + "limit": { + "context": 32768, + "output": 16384 + } + }, + { + "id": "kilo/mistralai/mistral-small-3.1-24b-instruct", + "name": "Mistral: Mistral Small 3.1 24B", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-17", + "last_updated": "2025-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.11, + "cache_read": 0.015 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "kilo/mistralai/mistral-small-3.1-24b-instruct:free", + "name": "Mistral: Mistral Small 3.1 24B (free)", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-17", + "last_updated": "2025-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 25600 + } + }, + { + "id": "kilo/mistralai/mistral-small-3.2-24b-instruct", + "name": "Mistral: Mistral Small 3.2 24B", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-20", + "last_updated": "2025-06-20", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.18, + "cache_read": 0.03 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "kilo/mistralai/mixtral-8x22b-instruct", + "name": "Mistral: Mixtral 8x22B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-04-17", + "last_updated": "2024-04-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 6.0 + }, + "limit": { + "context": 65536, + "output": 13108 + } + }, + { + "id": "kilo/mistralai/voxtral-small-24b", + "name": "Mistral: Voxtral Small 24B 2507", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-01", + "last_updated": "2025-07-01", + "modalities": { + "input": [ + "text", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 32000, + "output": 6400 + } + }, + { + "id": "kilo/moonshotai/kimi-k2", + "name": "MoonshotAI: Kimi K2 0905", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.0, + "cache_read": 0.15 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/moonshotai/kimi-k2-0905:exacto", + "name": "MoonshotAI: Kimi K2 0905 (exacto)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5 + }, + "limit": { + "context": 262144, + "output": 52429 + } + }, + { + "id": "kilo/moonshotai/kimi-k2-thinking", + "name": "MoonshotAI: Kimi K2 Thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 1.75, + "cache_read": 0.2 + }, + "limit": { + "context": 262144, + "output": 65535 + } + }, + { + "id": "kilo/moonshotai/kimi-k2.5", + "name": "MoonshotAI: Kimi K2.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.23, + "output": 3.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "kilo/morph/morph-v3-fast", + "name": "Morph: Morph V3 Fast", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-08-15", + "last_updated": "2024-08-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 1.2 + }, + "limit": { + "context": 81920, + "output": 38000 + } + }, + { + "id": "kilo/morph/morph-v3-large", + "name": "Morph: Morph V3 Large", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-08-15", + "last_updated": "2024-08-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.9, + "output": 1.9 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "kilo/nex-agi/deepseek-v3.1-nex-n1", + "name": "Nex AGI: DeepSeek V3.1 Nex N1", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 1.0 + }, + "limit": { + "context": 131072, + "output": 163840 + } + }, + { + "id": "kilo/nousresearch/deephermes-3-mistral-24b-preview", + "name": "Nous: DeepHermes 3 Mistral 24B Preview", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.1, + "cache_read": 0.01 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "kilo/nousresearch/hermes-2-pro-llama-3-8b", + "name": "NousResearch: Hermes 2 Pro - Llama-3 8B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-05-27", + "last_updated": "2024-06-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.14 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "kilo/nousresearch/hermes-3-llama-3.1-405b", + "name": "Nous: Hermes 3 405B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-08-16", + "last_updated": "2024-08-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 1.0 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "kilo/nousresearch/hermes-3-llama-3.1-405b:free", + "name": "Nous: Hermes 3 405B Instruct (free)", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-08-16", + "last_updated": "2024-08-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/nousresearch/hermes-4-405b", + "name": "Nous: Hermes 4 405B", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-08-25", + "last_updated": "2025-08-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.0 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/nousresearch/hermes-4-70b", + "name": "Nous: Hermes 4 70B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-25", + "last_updated": "2025-08-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.11, + "output": 0.38, + "cache_read": 0.055 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "kilo/nvidia/llama-3.1-nemotron-70b-instruct", + "name": "NVIDIA: Llama 3.1 Nemotron 70B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-10-12", + "last_updated": "2024-10-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 1.2 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "kilo/nvidia/llama-3.1-nemotron-ultra-253b-v1", + "name": "NVIDIA: Llama 3.1 Nemotron Ultra 253B v1", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2024-07-01", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.8 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/nvidia/llama-3.3-nemotron-super-49b-v1.5", + "name": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-16", + "last_updated": "2025-03-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/nvidia/nemotron-3-nano-30b-a3b", + "name": "NVIDIA: Nemotron 3 Nano 30B A3B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2024-12", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.2 + }, + "limit": { + "context": 262144, + "output": 52429 + } + }, + { + "id": "kilo/nvidia/nemotron-3-nano-30b-a3b:free", + "name": "NVIDIA: Nemotron 3 Nano 30B A3B (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-14", + "last_updated": "2026-01-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 51200 + } + }, + { + "id": "kilo/nvidia/nemotron-nano-12b-v2-vl", + "name": "NVIDIA: Nemotron Nano 12B 2 VL", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-10-28", + "last_updated": "2026-01-31", + "modalities": { + "input": [ + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/nvidia/nemotron-nano-12b-v2-vl:free", + "name": "NVIDIA: Nemotron Nano 12B 2 VL (free)", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-28", + "last_updated": "2026-01-31", + "modalities": { + "input": [ + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "kilo/nvidia/nemotron-nano-9b-v2", + "name": "NVIDIA: Nemotron Nano 9B V2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-18", + "last_updated": "2025-08-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.04, + "output": 0.16 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/nvidia/nemotron-nano-9b-v2:free", + "name": "NVIDIA: Nemotron Nano 9B V2 (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-05", + "last_updated": "2025-08-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 25600 + } + }, + { + "id": "kilo/openai/chatgpt-4o", + "name": "OpenAI: ChatGPT-4o", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-08-08", + "last_updated": "2024-08-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 15.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "kilo/openai/gpt-3.5-turbo", + "name": "OpenAI: GPT-3.5 Turbo (older v0613)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2023-06-13", + "last_updated": "2023-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 4095, + "output": 4096 + } + }, + { + "id": "kilo/openai/gpt-3.5-turbo-instruct", + "name": "OpenAI: GPT-3.5 Turbo Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2023-03-01", + "last_updated": "2023-09-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 2.0 + }, + "limit": { + "context": 4095, + "output": 4096 + } + }, + { + "id": "kilo/openai/gpt-4", + "name": "OpenAI: GPT-4", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2023-03-14", + "last_updated": "2024-04-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 30.0, + "output": 60.0 + }, + "limit": { + "context": 8191, + "output": 4096 + } + }, + { + "id": "kilo/openai/gpt-4-turbo", + "name": "OpenAI: GPT-4 Turbo", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2023-09-13", + "last_updated": "2024-04-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 30.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "kilo/openai/gpt-4.1", + "name": "OpenAI: GPT-4.1", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "kilo/openai/gpt-4.1-mini", + "name": "OpenAI: GPT-4.1 Mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.6, + "cache_read": 0.1 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "kilo/openai/gpt-4.1-nano", + "name": "OpenAI: GPT-4.1 Nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-14", + "last_updated": "2025-04-15", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.025 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "kilo/openai/gpt-4o", + "name": "OpenAI: GPT-4o (2024-11-20)", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-20", + "last_updated": "2024-11-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0, + "cache_read": 1.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "kilo/openai/gpt-4o-mini", + "name": "OpenAI: GPT-4o-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.075 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "kilo/openai/gpt-4o-mini-search-preview", + "name": "OpenAI: GPT-4o-mini Search Preview", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-01", + "last_updated": "2025-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "kilo/openai/gpt-4o:extended", + "name": "OpenAI: GPT-4o (extended)", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-05-13", + "last_updated": "2024-08-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 6.0, + "output": 18.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "kilo/openai/gpt-5", + "name": "OpenAI: GPT-5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-5-chat", + "name": "OpenAI: GPT-5 Chat", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "kilo/openai/gpt-5-codex", + "name": "OpenAI: GPT-5 Codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-5-mini", + "name": "OpenAI: GPT-5 Mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.025 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-5-nano", + "name": "OpenAI: GPT-5 Nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.005 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-5-pro", + "name": "OpenAI: GPT-5 Pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-10-06", + "last_updated": "2025-10-06", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 120.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-5.1", + "name": "OpenAI: GPT-5.1", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-5.1-chat", + "name": "OpenAI: GPT-5.1 Chat", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "kilo/openai/gpt-5.1-codex", + "name": "OpenAI: GPT-5.1-Codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-5.1-codex-max", + "name": "OpenAI: GPT-5.1-Codex-Max", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-5.1-codex-mini", + "name": "OpenAI: GPT-5.1-Codex-Mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.025 + }, + "limit": { + "context": 400000, + "output": 100000 + } + }, + { + "id": "kilo/openai/gpt-5.2", + "name": "OpenAI: GPT-5.2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-5.2-chat", + "name": "OpenAI: GPT-5.2 Chat", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "kilo/openai/gpt-5.2-codex", + "name": "OpenAI: GPT-5.2-Codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-01-14", + "last_updated": "2026-01-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-5.2-pro", + "name": "OpenAI: GPT-5.2 Pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 21.0, + "output": 168.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "kilo/openai/gpt-oss-120b", + "name": "OpenAI: gpt-oss-120b", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.039, + "output": 0.19 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/openai/gpt-oss-120b:exacto", + "name": "OpenAI: gpt-oss-120b (exacto)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.039, + "output": 0.19 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/openai/gpt-oss-120b:free", + "name": "OpenAI: gpt-oss-120b (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "kilo/openai/gpt-oss-20b", + "name": "OpenAI: gpt-oss-20b", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.14 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/openai/gpt-oss-20b:free", + "name": "OpenAI: gpt-oss-20b (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2026-01-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "kilo/openai/gpt-oss-safeguard-20b", + "name": "OpenAI: gpt-oss-safeguard-20b", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-29", + "last_updated": "2025-10-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.3, + "cache_read": 0.037 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "kilo/openai/o1", + "name": "OpenAI: o1", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-12-05", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 60.0, + "cache_read": 7.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "kilo/openai/o1-pro", + "name": "OpenAI: o1-pro", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": false, + "release_date": "2025-03-19", + "last_updated": "2025-03-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 150.0, + "output": 600.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "kilo/openai/o3", + "name": "OpenAI: o3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-04-16", + "last_updated": "2026-01", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "kilo/openai/o3-deep-research", + "name": "OpenAI: o3 Deep Research", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2024-06-26", + "last_updated": "2025-06-27", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 40.0, + "cache_read": 2.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "kilo/openai/o3-mini", + "name": "OpenAI: o3 Mini", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-12-20", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.55 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "kilo/openai/o3-mini-high", + "name": "OpenAI: o3 Mini High", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-01-31", + "last_updated": "2025-01-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.55 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "kilo/openai/o3-pro", + "name": "OpenAI: o3 Pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-04-16", + "last_updated": "2025-06-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 20.0, + "output": 80.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "kilo/openai/o4-mini", + "name": "OpenAI: o4 Mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.275 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "kilo/openai/o4-mini-deep-research", + "name": "OpenAI: o4 Mini Deep Research", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2024-06-26", + "last_updated": "2025-06-27", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "kilo/openrouter/aurora-alpha", + "name": "Aurora Alpha (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-09", + "last_updated": "2026-02-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 50000 + } + }, + { + "id": "kilo/perplexity/sonar", + "name": "Perplexity: Sonar", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 1.0 + }, + "limit": { + "context": 127072, + "output": 25415 + } + }, + { + "id": "kilo/perplexity/sonar-deep-research", + "name": "Perplexity: Sonar Deep Research", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-01-27", + "last_updated": "2025-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 128000, + "output": 25600 + } + }, + { + "id": "kilo/perplexity/sonar-pro", + "name": "Perplexity: Sonar Pro", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 200000, + "output": 8000 + } + }, + { + "id": "kilo/perplexity/sonar-reasoning-pro", + "name": "Perplexity: Sonar Reasoning Pro", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 128000, + "output": 25600 + } + }, + { + "id": "kilo/prime-intellect/intellect-3", + "name": "Prime Intellect: INTELLECT-3", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-26", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.1 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "kilo/qwen/qwen-2.5-72b-instruct", + "name": "Qwen2.5 72B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.12, + "output": 0.39 + }, + "limit": { + "context": 32768, + "output": 16384 + } + }, + { + "id": "kilo/qwen/qwen-2.5-7b-instruct", + "name": "Qwen: Qwen2.5 7B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.04, + "output": 0.1 + }, + "limit": { + "context": 32768, + "output": 6554 + } + }, + { + "id": "kilo/qwen/qwen-2.5-coder-32b-instruct", + "name": "Qwen2.5 Coder 32B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-11-11", + "last_updated": "2024-11-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.11, + "cache_read": 0.015 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "kilo/qwen/qwen-2.5-vl-7b-instruct", + "name": "Qwen: Qwen2.5-VL 7B Instruct", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-08-28", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 32768, + "output": 6554 + } + }, + { + "id": "kilo/qwen/qwen-max", + "name": "Qwen: Qwen-Max ", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-04-03", + "last_updated": "2025-01-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.6, + "output": 6.4, + "cache_read": 0.32 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "kilo/qwen/qwen-plus", + "name": "Qwen: Qwen-Plus", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-01-25", + "last_updated": "2025-09-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.2, + "cache_read": 0.08 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, + { + "id": "kilo/qwen/qwen-turbo", + "name": "Qwen: Qwen-Turbo", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-01", + "last_updated": "2025-07-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.2, + "cache_read": 0.01 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "kilo/qwen/qwen-vl-max", + "name": "Qwen: Qwen VL Max", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-04-08", + "last_updated": "2025-08-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 3.2 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "kilo/qwen/qwen-vl-plus", + "name": "Qwen: Qwen VL Plus", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-01-25", + "last_updated": "2025-08-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.21, + "output": 0.63, + "cache_read": 0.042 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "kilo/qwen/qwen2.5-coder-7b-instruct", + "name": "Qwen: Qwen2.5 Coder 7B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-09-17", + "last_updated": "2024-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.09 + }, + "limit": { + "context": 32768, + "output": 6554 + } + }, + { + "id": "kilo/qwen/qwen2.5-vl-32b-instruct", + "name": "Qwen: Qwen2.5 VL 32B Instruct", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-24", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.22, + "cache_read": 0.025 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "kilo/qwen/qwen2.5-vl-72b-instruct", + "name": "Qwen: Qwen2.5 VL 72B Instruct", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-02-01", + "last_updated": "2025-02-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.075 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "kilo/qwen/qwen3-14b", + "name": "Qwen: Qwen3 14B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.22, + "cache_read": 0.025 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "kilo/qwen/qwen3-235b-a22b", + "name": "Qwen: Qwen3 235B A22B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.15 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "kilo/qwen/qwen3-235b-a22b-thinking", + "name": "Qwen: Qwen3 235B A22B Thinking 2507", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/qwen/qwen3-30b-a3b", + "name": "Qwen: Qwen3 30B A3B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.22, + "cache_read": 0.03 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "kilo/qwen/qwen3-30b-a3b-instruct", + "name": "Qwen: Qwen3 30B A3B Instruct 2507", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-29", + "last_updated": "2025-07-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.33, + "cache_read": 0.04 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "kilo/qwen/qwen3-30b-a3b-thinking", + "name": "Qwen: Qwen3 30B A3B Thinking 2507", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-29", + "last_updated": "2025-07-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.051, + "output": 0.34 + }, + "limit": { + "context": 32768, + "output": 6554 + } + }, + { + "id": "kilo/qwen/qwen3-32b", + "name": "Qwen: Qwen3 32B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-01", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.24, + "cache_read": 0.04 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "kilo/qwen/qwen3-4b", + "name": "Qwen: Qwen3 4B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-29", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0715, + "output": 0.273 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "kilo/qwen/qwen3-4b:free", + "name": "Qwen: Qwen3 4B (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-30", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 40960, + "output": 8192 + } + }, + { + "id": "kilo/qwen/qwen3-8b", + "name": "Qwen: Qwen3 8B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.05 + }, + "limit": { + "context": 32000, + "output": 8192 + } + }, + { + "id": "kilo/qwen/qwen3-coder", + "name": "Qwen: Qwen3 Coder 480B A35B", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 1.0, + "cache_read": 0.022 + }, + "limit": { + "context": 262144, + "output": 52429 + } + }, + { + "id": "kilo/qwen/qwen3-coder-30b-a3b-instruct", + "name": "Qwen: Qwen3 Coder 30B A3B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-31", + "last_updated": "2025-07-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.27 + }, + "limit": { + "context": 160000, + "output": 32768 + } + }, + { + "id": "kilo/qwen/qwen3-coder-flash", + "name": "Qwen: Qwen3 Coder Flash", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.5, + "cache_read": 0.06 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "kilo/qwen/qwen3-coder-next", + "name": "Qwen: Qwen3 Coder Next", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-02", + "last_updated": "2026-02-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.3, + "cache_read": 0.035 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "kilo/qwen/qwen3-coder-plus", + "name": "Qwen: Qwen3 Coder Plus", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-01", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "kilo/qwen/qwen3-coder:exacto", + "name": "Qwen: Qwen3 Coder 480B A35B (exacto)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 1.8, + "cache_read": 0.022 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "kilo/qwen/qwen3-coder:free", + "name": "Qwen: Qwen3 Coder 480B A35B (free)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "kilo/qwen/qwen3-max", + "name": "Qwen: Qwen3 Max", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 6.0, + "cache_read": 0.24 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "kilo/qwen/qwen3-max-thinking", + "name": "Qwen: Qwen3 Max Thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-23", + "last_updated": "2026-01-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 6.0 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "kilo/qwen/qwen3-next-80b-a3b-instruct", + "name": "Qwen: Qwen3 Next 80B A3B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-11", + "last_updated": "2025-09-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 1.1 + }, + "limit": { + "context": 262144, + "output": 52429 + } + }, + { + "id": "kilo/qwen/qwen3-next-80b-a3b-instruct:free", + "name": "Qwen: Qwen3 Next 80B A3B Instruct (free)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-11", + "last_updated": "2025-09-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 52429 + } + }, + { + "id": "kilo/qwen/qwen3-next-80b-a3b-thinking", + "name": "Qwen: Qwen3 Next 80B A3B Thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-11", + "last_updated": "2025-09-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.2 + }, + "limit": { + "context": 128000, + "output": 25600 + } + }, + { + "id": "kilo/qwen/qwen3-vl-235b-a22b-instruct", + "name": "Qwen: Qwen3 VL 235B A22B Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-23", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.88, + "cache_read": 0.11 + }, + "limit": { + "context": 262144, + "output": 52429 + } + }, + { + "id": "kilo/qwen/qwen3-vl-235b-a22b-thinking", + "name": "Qwen: Qwen3 VL 235B A22B Thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-24", + "last_updated": "2025-09-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "kilo/qwen/qwen3-vl-30b-a3b-instruct", + "name": "Qwen: Qwen3 VL 30B A3B Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-05", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.52 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "kilo/qwen/qwen3-vl-30b-a3b-thinking", + "name": "Qwen: Qwen3 VL 30B A3B Thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-11", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "kilo/qwen/qwen3-vl-32b-instruct", + "name": "Qwen: Qwen3 VL 32B Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-21", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.104, + "output": 0.416 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "kilo/qwen/qwen3-vl-8b-instruct", + "name": "Qwen: Qwen3 VL 8B Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-15", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.5 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "kilo/qwen/qwen3-vl-8b-thinking", + "name": "Qwen: Qwen3 VL 8B Thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-15", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.117, + "output": 1.365 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "kilo/qwen/qwen3.5-397b-a17b", + "name": "Qwen: Qwen3.5 397B A17B", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-15", + "last_updated": "2026-02-15", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 3.6 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "kilo/qwen/qwen3.5-plus-02-15", + "name": "Qwen: Qwen3.5 Plus 2026-02-15", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-15", + "last_updated": "2026-02-15", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.4 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "kilo/qwen/qwq-32b", + "name": "Qwen: QwQ 32B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-28", + "last_updated": "2025-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.4 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "kilo/stepfun/step-3.5-flash", + "name": "StepFun: Step 3.5 Flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-29", + "last_updated": "2026-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3, + "cache_read": 0.02 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "kilo/stepfun/step-3.5-flash:free", + "name": "StepFun: Step 3.5 Flash (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-29", + "last_updated": "2026-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "kilo/tencent/hunyuan-a13b-instruct", + "name": "Tencent: Hunyuan A13B Instruct", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-06-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "kilo/tngtech/deepseek-r1t-chimera", + "name": "TNG: DeepSeek R1T Chimera", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-29", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.15 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "kilo/tngtech/deepseek-r1t2-chimera", + "name": "TNG: DeepSeek R1T2 Chimera", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-08", + "last_updated": "2025-07-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.85, + "cache_read": 0.125 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "kilo/tngtech/tng-r1t-chimera", + "name": "TNG: R1T Chimera", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-26", + "last_updated": "2026-01-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.85, + "cache_read": 0.125 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "kilo/writer/palmyra-x5", + "name": "Writer: Palmyra X5", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-28", + "last_updated": "2025-04-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 6.0 + }, + "limit": { + "context": 1040000, + "output": 8192 + } + }, + { + "id": "kilo/x-ai/grok-3", + "name": "xAI: Grok 3", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-02-17", + "last_updated": "2025-02-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/x-ai/grok-3-beta", + "name": "xAI: Grok 3 Beta", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-02-17", + "last_updated": "2025-02-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/x-ai/grok-3-mini", + "name": "xAI: Grok 3 Mini", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-02-17", + "last_updated": "2025-02-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.5, + "cache_read": 0.075 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/x-ai/grok-3-mini-beta", + "name": "xAI: Grok 3 Mini Beta", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-02-17", + "last_updated": "2025-02-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.5, + "cache_read": 0.075 + }, + "limit": { + "context": 131072, + "output": 26215 + } + }, + { + "id": "kilo/x-ai/grok-4", + "name": "xAI: Grok 4", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 256000, + "output": 51200 + } + }, + { + "id": "kilo/x-ai/grok-4-fast", + "name": "xAI: Grok 4 Fast", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-19", + "last_updated": "2025-08-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "kilo/x-ai/grok-4.1-fast", + "name": "xAI: Grok 4.1 Fast", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "kilo/x-ai/grok-code-fast-1", + "name": "xAI: Grok Code Fast 1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-26", + "last_updated": "2025-08-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.5, + "cache_read": 0.02 + }, + "limit": { + "context": 256000, + "output": 10000 + } + }, + { + "id": "kilo/xiaomi/mimo-v2-flash", + "name": "Xiaomi: MiMo-V2-Flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-14", + "last_updated": "2025-12-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.29, + "cache_read": 0.045 + }, + "limit": { + "context": 262144, + "output": 52429 + } + }, + { + "id": "kilo/z-ai/glm-4.5", + "name": "Z.ai: GLM 4.5", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 1.55, + "cache_read": 0.175 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "kilo/z-ai/glm-4.5-air", + "name": "Z.ai: GLM 4.5 Air", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.85, + "cache_read": 0.025 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "kilo/z-ai/glm-4.5-air:free", + "name": "Z.ai: GLM 4.5 Air (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 96000 + } + }, + { + "id": "kilo/z-ai/glm-4.5v", + "name": "Z.ai: GLM 4.5V", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-11", + "last_updated": "2025-08-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.8, + "cache_read": 0.11 + }, + "limit": { + "context": 65536, + "output": 16384 + } + }, + { + "id": "kilo/z-ai/glm-4.6", + "name": "Z.ai: GLM 4.6", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.35, + "output": 1.5, + "cache_read": 0.175 + }, + "limit": { + "context": 202752, + "output": 65536 + } + }, + { + "id": "kilo/z-ai/glm-4.6:exacto", + "name": "Z.ai: GLM 4.6 (exacto)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.44, + "output": 1.76, + "cache_read": 0.11 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "kilo/z-ai/glm-4.6v", + "name": "Z.ai: GLM 4.6V", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-30", + "last_updated": "2026-01-10", + "modalities": { + "input": [ + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "kilo/z-ai/glm-4.7", + "name": "Z.ai: GLM 4.7", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 1.5, + "cache_read": 0.2 + }, + "limit": { + "context": 202752, + "output": 65535 + } + }, + { + "id": "kilo/z-ai/glm-4.7-flash", + "name": "Z.ai: GLM 4.7 Flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 202752, + "output": 40551 + } + }, + { + "id": "kilo/z-ai/glm-5", + "name": "Z.ai: GLM 5", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 2.55 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "kilo/z-ai/glm-5:free", + "name": "Z.ai: GLM 5 (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 202800, + "output": 131072 + } + }, + { + "id": "kimi-for-coding/k2p5", + "name": "Kimi K2.5", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "kimi-for-coding/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-11", + "last_updated": "2025-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "kuae-cloud-coding-plan/GLM-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "lmstudio/openai/gpt-oss-20b", + "name": "GPT OSS 20B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "lmstudio/qwen/qwen3-30b-a3b", + "name": "Qwen3 30B A3B 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 16384 + } + }, + { + "id": "lmstudio/qwen/qwen3-coder-30b", + "name": "Qwen3 Coder 30B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "lucidquery/lucidnova-rf1-100b", + "name": "LucidNova RF1 100B", + "family": "nova", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-09-16", + "release_date": "2024-12-28", + "last_updated": "2025-09-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 5.0 + }, + "limit": { + "context": 120000, + "output": 8000 + } + }, + { + "id": "lucidquery/lucidquery-nexus-coder", + "name": "LucidQuery Nexus Coder", + "family": "lucid", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-01", + "release_date": "2025-09-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 5.0 + }, + "limit": { + "context": 250000, + "output": 60000 + } + }, + { + "id": "meganova/MiniMaxAI/MiniMax-M2.1", + "name": "MiniMax M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.28, + "output": 1.2 + }, + "limit": { + "context": 196608, + "output": 131072 + } + }, + { + "id": "meganova/MiniMaxAI/MiniMax-M2.5", + "name": "MiniMax M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "meganova/Qwen/Qwen2.5-VL-32B-Instruct", + "name": "Qwen2.5 VL 32B Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-24", + "last_updated": "2025-03-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "meganova/Qwen/Qwen3-235B-A22B-Instruct", + "name": "Qwen3 235B A22B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.6 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "meganova/Qwen/Qwen3.5-Plus", + "name": "Qwen3.5 Plus", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-02", + "last_updated": "2026-02", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.4 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, + { + "id": "meganova/XiaomiMiMo/MiMo-V2-Flash", + "name": "MiMo V2 Flash", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 262144, + "output": 32000 + } + }, + { + "id": "meganova/deepseek-ai/DeepSeek-R1", + "name": "DeepSeek R1 0528", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-05-28", + "last_updated": "2025-05-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 2.15 + }, + "limit": { + "context": 163840, + "output": 64000 + } + }, + { + "id": "meganova/deepseek-ai/DeepSeek-V3", + "name": "DeepSeek V3 0324", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-24", + "last_updated": "2025-03-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.88 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "meganova/deepseek-ai/DeepSeek-V3.1", + "name": "DeepSeek V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-25", + "last_updated": "2025-08-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.0 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "meganova/deepseek-ai/DeepSeek-V3.2", + "name": "DeepSeek V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-03", + "last_updated": "2025-12-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.26, + "output": 0.38 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "meganova/deepseek-ai/DeepSeek-V3.2-Exp", + "name": "DeepSeek V3.2 Exp", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-10", + "last_updated": "2025-10-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 0.4 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "meganova/meta-llama/Llama-3.3-70B-Instruct", + "name": "Llama 3.3 70B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "meganova/mistralai/Mistral-Nemo-Instruct", + "name": "Mistral Nemo Instruct 2407", + "family": "mistral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.04 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "meganova/mistralai/Mistral-Small-3.2-24B-Instruct", + "name": "Mistral Small 3.2 24B Instruct", + "family": "mistral-small", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-06-20", + "last_updated": "2025-06-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "meganova/moonshotai/Kimi-K2-Thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.6 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "meganova/moonshotai/Kimi-K2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-01", + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 2.8 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "meganova/zai-org/GLM-4.6", + "name": "GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 1.9 + }, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "meganova/zai-org/GLM-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "meganova/zai-org/GLM-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 2.56 + }, + "limit": { + "context": 202752, + "output": 131072 + } + }, { "id": "meta-llama/cerebras-llama-4-maverick-17b-128e-instruct", "name": "Cerebras-Llama-4-Maverick-17B-128E-Instruct", @@ -7873,6 +45111,470 @@ "output": 4096 } }, + { + "id": "minimax-cn-coding-plan/MiniMax-M2", + "name": "MiniMax-M2", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 196608, + "output": 128000 + } + }, + { + "id": "minimax-cn-coding-plan/MiniMax-M2.1", + "name": "MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "minimax-cn-coding-plan/MiniMax-M2.5", + "name": "MiniMax-M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "minimax-cn-coding-plan/MiniMax-M2.5-highspeed", + "name": "MiniMax-M2.5-highspeed", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-13", + "last_updated": "2026-02-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "minimax-cn/MiniMax-M2", + "name": "MiniMax-M2", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 196608, + "output": 128000 + } + }, + { + "id": "minimax-cn/MiniMax-M2.1", + "name": "MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "minimax-cn/MiniMax-M2.5", + "name": "MiniMax-M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03, + "cache_write": 0.375 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "minimax-cn/MiniMax-M2.5-highspeed", + "name": "MiniMax-M2.5-highspeed", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-13", + "last_updated": "2026-02-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.4, + "cache_read": 0.06, + "cache_write": 0.375 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "minimax-coding-plan/MiniMax-M2", + "name": "MiniMax-M2", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 196608, + "output": 128000 + } + }, + { + "id": "minimax-coding-plan/MiniMax-M2.1", + "name": "MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "minimax-coding-plan/MiniMax-M2.5", + "name": "MiniMax-M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "minimax-coding-plan/MiniMax-M2.5-highspeed", + "name": "MiniMax-M2.5-highspeed", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-13", + "last_updated": "2026-02-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "minimax/MiniMax-M2", + "name": "MiniMax-M2", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 196608, + "output": 128000 + } + }, + { + "id": "minimax/MiniMax-M2.1", + "name": "MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "minimax/MiniMax-M2.5", + "name": "MiniMax-M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03, + "cache_write": 0.375 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "minimax/MiniMax-M2.5-highspeed", + "name": "MiniMax-M2.5-highspeed", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-13", + "last_updated": "2026-02-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.4, + "cache_read": 0.06, + "cache_write": 0.375 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, { "id": "mistralai/codestral", "name": "Codestral", @@ -8428,6 +46130,8248 @@ "output": 128000 } }, + { + "id": "moark/GLM-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.5, + "output": 14.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "moark/MiniMax-M2.1", + "name": "MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.1, + "output": 8.4 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "modelscope/Qwen/Qwen3-235B-A22B-Instruct", + "name": "Qwen3 235B A22B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04-28", + "last_updated": "2025-07-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "modelscope/Qwen/Qwen3-235B-A22B-Thinking", + "name": "Qwen3-235B-A22B-Thinking-2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "modelscope/Qwen/Qwen3-30B-A3B-Instruct", + "name": "Qwen3 30B A3B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 16384 + } + }, + { + "id": "modelscope/Qwen/Qwen3-30B-A3B-Thinking", + "name": "Qwen3 30B A3B Thinking 2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-30", + "last_updated": "2025-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "modelscope/Qwen/Qwen3-Coder-30B-A3B-Instruct", + "name": "Qwen3 Coder 30B A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-31", + "last_updated": "2025-07-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "modelscope/ZhipuAI/GLM-4.5", + "name": "GLM-4.5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "modelscope/ZhipuAI/GLM-4.6", + "name": "GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 202752, + "output": 98304 + } + }, + { + "id": "moonshotai-cn/kimi-k2-0711-preview", + "name": "Kimi K2 0711", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-14", + "last_updated": "2025-07-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.15 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "moonshotai-cn/kimi-k2-0905-preview", + "name": "Kimi K2 0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "moonshotai-cn/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "moonshotai-cn/kimi-k2-thinking-turbo", + "name": "Kimi K2 Thinking Turbo", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.15, + "output": 8.0, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "moonshotai-cn/kimi-k2-turbo-preview", + "name": "Kimi K2 Turbo", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.4, + "output": 10.0, + "cache_read": 0.6 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "moonshotai-cn/kimi-k2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0, + "cache_read": 0.1 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "moonshotai/kimi-k2-0711-preview", + "name": "Kimi K2 0711", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-14", + "last_updated": "2025-07-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.15 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "moonshotai/kimi-k2-0905-preview", + "name": "Kimi K2 0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "moonshotai/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "moonshotai/kimi-k2-thinking-turbo", + "name": "Kimi K2 Thinking Turbo", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.15, + "output": 8.0, + "cache_read": 0.15 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "moonshotai/kimi-k2-turbo-preview", + "name": "Kimi K2 Turbo", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.4, + "output": 10.0, + "cache_read": 0.6 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "moonshotai/kimi-k2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0, + "cache_read": 0.1 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "morph/auto", + "name": "Auto", + "family": "auto", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-06-01", + "last_updated": "2024-06-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.85, + "output": 1.55 + }, + "limit": { + "context": 32000, + "output": 32000 + } + }, + { + "id": "morph/morph-v3-fast", + "name": "Morph v3 Fast", + "family": "morph", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-08-15", + "last_updated": "2024-08-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 1.2 + }, + "limit": { + "context": 16000, + "output": 16000 + } + }, + { + "id": "morph/morph-v3-large", + "name": "Morph v3 Large", + "family": "morph", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-08-15", + "last_updated": "2024-08-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.9, + "output": 1.9 + }, + "limit": { + "context": 32000, + "output": 32000 + } + }, + { + "id": "nano-gpt/deepseek/deepseek-r1", + "name": "Deepseek R1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-01-20", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/deepseek/deepseek-v3.2:thinking", + "name": "Deepseek V3.2 Thinking", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-01", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/meta-llama/llama-3.3-70b-instruct", + "name": "Llama 3.3 70b Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/meta-llama/llama-4-maverick", + "name": "Llama 4 Maverick", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-04-05", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/minimax/minimax-m2.1", + "name": "Minimax M2.1", + "family": "minimax", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/minimax/minimax-m2.5", + "name": "MiniMax M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "nano-gpt/minimax/minimax-m2.5-official", + "name": "MiniMax M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "nano-gpt/mistralai/devstral-2-123b-instruct", + "name": "Devstral 2 123b Instruct 2512", + "family": "mistral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-11", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "nano-gpt/mistralai/ministral-14b-instruct", + "name": "Ministral 14b Instruct 2512", + "family": "mistral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2025-12-01", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "nano-gpt/mistralai/mistral-large-3-675b-instruct", + "name": "Mistral Large 3 675b Instruct 2512", + "family": "mistral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-02", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "nano-gpt/moonshotai/kimi-k2-instruct", + "name": "Kimi K2 Instruct", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-07-18", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "nano-gpt/moonshotai/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2024-11-01", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "nano-gpt/moonshotai/kimi-k2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-26", + "last_updated": "2026-01-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.9 + }, + "limit": { + "context": 256000, + "output": 65536 + } + }, + { + "id": "nano-gpt/moonshotai/kimi-k2.5-thinking", + "name": "Kimi K2.5 Thinking", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-26", + "last_updated": "2026-01-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.9 + }, + "limit": { + "context": 256000, + "output": 65536 + } + }, + { + "id": "nano-gpt/nousresearch/hermes-4-405b:thinking", + "name": "Hermes 4 405b Thinking", + "family": "hermes", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2024-08-13", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/nvidia/llama-3_3-nemotron-super-49b-v1_5", + "name": "Llama 3 3 Nemotron Super 49B V1 5", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-08", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/openai/gpt-oss-120b", + "name": "GPT Oss 120b", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-06-23", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/qwen/qwen3-235b-a22b-thinking", + "name": "Qwen3 235B A22B Thinking 2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-07-01", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 262144, + "output": 8192 + } + }, + { + "id": "nano-gpt/qwen/qwen3-coder", + "name": "Qwen3 Coder", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-15", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 106000, + "output": 8192 + } + }, + { + "id": "nano-gpt/qwen/qwen3.5-397b-a17b", + "name": "Qwen3.5 397B A17B", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.6 + }, + "limit": { + "context": 258000, + "output": 8192 + } + }, + { + "id": "nano-gpt/qwen/qwen3.5-397b-a17b-thinking", + "name": "Qwen3.5 397B A17B Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.6 + }, + "limit": { + "context": 258000, + "output": 8192 + } + }, + { + "id": "nano-gpt/qwen/qwen3.5-plus", + "name": "Qwen3.5 Plus", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.4 + }, + "limit": { + "context": 983600, + "output": 8192 + } + }, + { + "id": "nano-gpt/qwen/qwen3.5-plus-thinking", + "name": "Qwen3.5 Plus Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.4 + }, + "limit": { + "context": 983600, + "output": 8192 + } + }, + { + "id": "nano-gpt/zai-org/glm-4.5-air", + "name": "GLM 4.5 Air", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/zai-org/glm-4.5-air:thinking", + "name": "GLM 4.5 Air Thinking", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-07", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/zai-org/glm-4.6", + "name": "GLM 4.6", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-11-15", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "nano-gpt/zai-org/glm-4.6:thinking", + "name": "GLM 4.6 Thinking", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-07", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/zai-org/glm-4.7", + "name": "GLM 4.7", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 204800, + "output": 8192 + } + }, + { + "id": "nano-gpt/zai-org/glm-4.7:thinking", + "name": "GLM 4.7 Thinking", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-07", + "last_updated": "2025-12-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nano-gpt/zai-org/glm-5", + "name": "GLM 5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.8, + "output": 2.56 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "nano-gpt/zai-org/glm-5-original", + "name": "GLM 5 Original", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.8, + "output": 2.56 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "nano-gpt/zai-org/glm-5-original:thinking", + "name": "GLM 5 Original Thinking", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.8, + "output": 2.56 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "nano-gpt/zai-org/glm-5:thinking", + "name": "GLM 5 Thinking", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.8, + "output": 2.56 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "nebius/BAAI/bge-en-icl", + "name": "BGE-ICL", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-06", + "release_date": "2024-07-30", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 0 + } + }, + { + "id": "nebius/BAAI/bge-multilingual-gemma2", + "name": "bge-multilingual-gemma2", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-06", + "release_date": "2024-07-30", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 0 + } + }, + { + "id": "nebius/MiniMaxAI/minimax-m2.1", + "name": "MiniMax-M2.1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-10", + "release_date": "2026-02-01", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03, + "cache_write": 0.375 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/NousResearch/hermes-4-405b", + "name": "Hermes-4-405B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2026-01-30", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/NousResearch/hermes-4-70b", + "name": "Hermes-4-70B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2026-01-30", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.4, + "cache_read": 0.013, + "cache_write": 0.16 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/PrimeIntellect/intellect-3", + "name": "INTELLECT-3", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-10", + "release_date": "2026-01-25", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.1, + "cache_read": 0.02, + "cache_write": 0.25 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/black-forest-labs/flux-dev", + "name": "FLUX.1-dev", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-07", + "release_date": "2024-08-01", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 77, + "output": 0 + } + }, + { + "id": "nebius/black-forest-labs/flux-schnell", + "name": "FLUX.1-schnell", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-07", + "release_date": "2024-08-01", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 77, + "output": 0 + } + }, + { + "id": "nebius/deepseek-ai/deepseek-r1", + "name": "DeepSeek-R1-0528", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2026-01-15", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.8, + "output": 2.4, + "cache_read": 0.08, + "cache_write": 1.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "nebius/deepseek-ai/deepseek-r1-0528-fast", + "name": "DeepSeek R1 0528 Fast", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-01", + "last_updated": "2025-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 6.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "nebius/deepseek-ai/deepseek-v3", + "name": "DeepSeek-V3-0324", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-03-24", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 1.5, + "cache_read": 0.05, + "cache_write": 0.1875 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/deepseek-ai/deepseek-v3-0324-fast", + "name": "DeepSeek-V3-0324 (Fast)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-03-24", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.75, + "output": 2.25, + "cache_read": 0.075, + "cache_write": 0.28125 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/deepseek-ai/deepseek-v3.2", + "name": "DeepSeek-V3.2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2026-01-20", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.45, + "cache_read": 0.03, + "cache_write": 0.375 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/google/gemma-2-2b-it", + "name": "Gemma-2-2b-it", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2024-07-31", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.06, + "cache_read": 0.002, + "cache_write": 0.025 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, + { + "id": "nebius/google/gemma-2-9b-it-fast", + "name": "Gemma-2-9b-it (Fast)", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2024-06-27", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.09, + "cache_read": 0.003, + "cache_write": 0.0375 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, + { + "id": "nebius/google/gemma-3-27b-it", + "name": "Gemma-3-27b-it", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-10", + "release_date": "2026-01-20", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3, + "cache_read": 0.01, + "cache_write": 0.125 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/google/gemma-3-27b-it-fast", + "name": "Gemma-3-27b-it (Fast)", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-10", + "release_date": "2026-01-20", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.6, + "cache_read": 0.02, + "cache_write": 0.25 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/intfloat/e5-mistral-7b-instruct", + "name": "e5-mistral-7b-instruct", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2023-12", + "release_date": "2024-01-01", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 0 + } + }, + { + "id": "nebius/meta-llama/Llama-3.3-70B-Instruct", + "name": "Llama-3.3-70B-Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2025-12-05", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.4, + "cache_read": 0.013, + "cache_write": 0.16 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/meta-llama/llama-3.3-70b-instruct-fast", + "name": "Llama-3.3-70B-Instruct (Fast)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2025-12-05", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.75, + "cache_read": 0.025, + "cache_write": 0.31 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/meta-llama/llama-guard-3-8b", + "name": "Llama-Guard-3-8B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-04", + "release_date": "2024-04-18", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.06, + "cache_read": 0.002, + "cache_write": 0.025 + }, + "limit": { + "context": 8192, + "output": 1024 + } + }, + { + "id": "nebius/meta-llama/meta-llama-3.1-8b-instruct", + "name": "Meta-Llama-3.1-8B-Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-07-23", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.06, + "cache_read": 0.002, + "cache_write": 0.025 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nebius/meta-llama/meta-llama-3.1-8b-instruct-fast", + "name": "Meta-Llama-3.1-8B-Instruct (Fast)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-07-23", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.09, + "cache_read": 0.003, + "cache_write": 0.03 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nebius/moonshotai/Kimi-K2.5", + "name": "Kimi-K2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-12-15", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 2.5, + "cache_read": 0.05, + "cache_write": 0.625 + }, + "limit": { + "context": 262144, + "output": 8192 + } + }, + { + "id": "nebius/moonshotai/kimi-k2-instruct", + "name": "Kimi-K2-Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-10", + "release_date": "2026-01-05", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 2.4, + "cache_read": 0.05, + "cache_write": 0.625 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "nebius/moonshotai/kimi-k2-thinking", + "name": "Kimi-K2-Thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-10", + "release_date": "2026-01-05", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.06, + "cache_write": 0.75 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "nebius/nvidia/llama-3_1-nemotron-ultra-253b-v1", + "name": "Llama-3.1-Nemotron-Ultra-253B-v1", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-15", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.8, + "cache_read": 0.06, + "cache_write": 0.75 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nebius/nvidia/nemotron-nano-v2-12b", + "name": "Nemotron-Nano-V2-12b", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-15", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.2, + "cache_read": 0.007, + "cache_write": 0.08 + }, + "limit": { + "context": 32000, + "output": 4096 + } + }, + { + "id": "nebius/nvidia/nvidia-nemotron-3-nano-30b-a3b", + "name": "Nemotron-3-Nano-30B-A3B", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2025-08-10", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.24, + "cache_read": 0.006, + "cache_write": 0.075 + }, + "limit": { + "context": 32000, + "output": 4096 + } + }, + { + "id": "nebius/openai/gpt-oss-120b", + "name": "gpt-oss-120b", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2026-01-10", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.015, + "cache_write": 0.18 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/openai/gpt-oss-20b", + "name": "gpt-oss-20b", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2026-01-10", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.2, + "cache_read": 0.005, + "cache_write": 0.06 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nebius/qwen/qwen2.5-coder-7b-fast", + "name": "Qwen2.5-Coder-7B (Fast)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2024-09-19", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.09, + "cache_read": 0.003, + "cache_write": 0.03 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/qwen/qwen2.5-vl-72b-instruct", + "name": "Qwen2.5-VL-72B-Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-20", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.75, + "cache_read": 0.025, + "cache_write": 0.31 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/qwen/qwen3-235b-a22b-instruct", + "name": "Qwen3 235B A22B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-25", + "last_updated": "2025-10-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 262144, + "output": 8192 + } + }, + { + "id": "nebius/qwen/qwen3-235b-a22b-thinking", + "name": "Qwen3 235B A22B Thinking 2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-25", + "last_updated": "2025-10-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 262144, + "output": 8192 + } + }, + { + "id": "nebius/qwen/qwen3-30b-a3b-instruct", + "name": "Qwen3-30B-A3B-Instruct-2507", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2026-01-28", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3, + "cache_read": 0.01, + "cache_write": 0.125 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/qwen/qwen3-30b-a3b-thinking", + "name": "Qwen3-30B-A3B-Thinking-2507", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2026-01-28", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3, + "cache_read": 0.01, + "cache_write": 0.125 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "nebius/qwen/qwen3-32b", + "name": "Qwen3-32B", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2026-01-28", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3, + "cache_read": 0.01, + "cache_write": 0.125 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/qwen/qwen3-32b-fast", + "name": "Qwen3-32B (Fast)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2026-01-28", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.6, + "cache_read": 0.02, + "cache_write": 0.25 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/qwen/qwen3-coder-30b-a3b-instruct", + "name": "Qwen3-Coder-30B-A3B-Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2026-01-28", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3, + "cache_read": 0.01, + "cache_write": 0.125 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nebius/qwen/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-10-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.8 + }, + "limit": { + "context": 262144, + "output": 66536 + } + }, + { + "id": "nebius/qwen/qwen3-embedding-8b", + "name": "Qwen3-Embedding-8B", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2025-10", + "release_date": "2026-01-10", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.01, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 0 + } + }, + { + "id": "nebius/qwen/qwen3-next-80b-a3b-thinking", + "name": "Qwen3-Next-80B-A3B-Thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2026-01-28", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.2, + "cache_read": 0.015, + "cache_write": 0.18 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "nebius/zai-org/glm-4.5", + "name": "GLM-4.5", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-11-15", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.06, + "cache_write": 0.75 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nebius/zai-org/glm-4.5-air", + "name": "GLM-4.5-Air", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-11-15", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.2, + "cache_read": 0.02, + "cache_write": 0.25 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nebius/zai-org/glm-4.7-fp8", + "name": "GLM-4.7 (FP8)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2026-01-15", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.0, + "cache_read": 0.04, + "cache_write": 0.5 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nova/nova-2-lite-v1", + "name": "Nova 2 Lite", + "family": "nova-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "nova/nova-2-pro-v1", + "name": "Nova 2 Pro", + "family": "nova-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-03", + "last_updated": "2026-01-03", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "novita-ai/baichuan/baichuan-m2-32b", + "name": "baichuan-m2-32b", + "family": "baichuan", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-08-13", + "last_updated": "2025-08-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.07 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "novita-ai/baidu/ernie-4.5-21B-a3b", + "name": "ERNIE 4.5 21B A3B", + "family": "ernie", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-06-30", + "last_updated": "2025-06-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 120000, + "output": 8000 + } + }, + { + "id": "novita-ai/baidu/ernie-4.5-21B-a3b-thinking", + "name": "ERNIE-4.5-21B-A3B-Thinking", + "family": "ernie", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-09-19", + "last_updated": "2025-09-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "novita-ai/baidu/ernie-4.5-300b-a47b-paddle", + "name": "ERNIE 4.5 300B A47B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-06-30", + "last_updated": "2025-06-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.28, + "output": 1.1 + }, + "limit": { + "context": 123000, + "output": 12000 + } + }, + { + "id": "novita-ai/baidu/ernie-4.5-vl-28b-a3b", + "name": "ERNIE 4.5 VL 28B A3B", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-30", + "last_updated": "2025-06-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.4, + "output": 5.6 + }, + "limit": { + "context": 30000, + "output": 8000 + } + }, + { + "id": "novita-ai/baidu/ernie-4.5-vl-28b-a3b-thinking", + "name": "ERNIE-4.5-VL-28B-A3B-Thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-26", + "last_updated": "2025-11-26", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.39, + "output": 0.39 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "novita-ai/baidu/ernie-4.5-vl-424b-a47b", + "name": "ERNIE 4.5 VL 424B A47B", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-06-30", + "last_updated": "2025-06-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.42, + "output": 1.25 + }, + "limit": { + "context": 123000, + "output": 16000 + } + }, + { + "id": "novita-ai/deepseek/deepseek-ocr", + "name": "DeepSeek-OCR", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-10-24", + "last_updated": "2025-10-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.03 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "novita-ai/deepseek/deepseek-ocr-2", + "name": "deepseek/deepseek-ocr-2", + "attachment": true, + "reasoning": false, + "tool_call": false, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.03 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "novita-ai/deepseek/deepseek-prover-v2-671b", + "name": "Deepseek Prover V2 671B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-30", + "last_updated": "2025-04-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.5 + }, + "limit": { + "context": 160000, + "output": 160000 + } + }, + { + "id": "novita-ai/deepseek/deepseek-r1", + "name": "DeepSeek R1 0528", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-05-28", + "last_updated": "2025-05-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.5, + "cache_read": 0.35 + }, + "limit": { + "context": 163840, + "output": 32768 + } + }, + { + "id": "novita-ai/deepseek/deepseek-r1-0528-qwen3-8b", + "name": "DeepSeek R1 0528 Qwen3 8B", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-05-29", + "last_updated": "2025-05-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.09 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "novita-ai/deepseek/deepseek-r1-distill-llama-70b", + "name": "DeepSeek R1 Distill LLama 70B", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-01-27", + "last_updated": "2025-01-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.8, + "output": 0.8 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "novita-ai/deepseek/deepseek-r1-turbo", + "name": "DeepSeek R1 (Turbo)\t", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-05", + "last_updated": "2025-03-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.5 + }, + "limit": { + "context": 64000, + "output": 16000 + } + }, + { + "id": "novita-ai/deepseek/deepseek-v3", + "name": "DeepSeek V3 0324", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-03-25", + "last_updated": "2025-03-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.12, + "cache_read": 0.135 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "novita-ai/deepseek/deepseek-v3-turbo", + "name": "DeepSeek V3 (Turbo)\t", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-05", + "last_updated": "2025-03-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 1.3 + }, + "limit": { + "context": 64000, + "output": 16000 + } + }, + { + "id": "novita-ai/deepseek/deepseek-v3.1", + "name": "DeepSeek V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-21", + "last_updated": "2025-08-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.0, + "cache_read": 0.135 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/deepseek/deepseek-v3.1-terminus", + "name": "Deepseek V3.1 Terminus", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-22", + "last_updated": "2025-09-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.0, + "cache_read": 0.135 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/deepseek/deepseek-v3.2", + "name": "Deepseek V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.269, + "output": 0.4, + "cache_read": 0.1345 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "novita-ai/deepseek/deepseek-v3.2-exp", + "name": "Deepseek V3.2 Exp", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 0.41 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "novita-ai/google/gemma-3-27b-it", + "name": "Gemma 3 27B", + "family": "gemma", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-25", + "last_updated": "2025-03-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.119, + "output": 0.2 + }, + "limit": { + "context": 98304, + "output": 16384 + } + }, + { + "id": "novita-ai/gryphe/mythomax-l2-13b", + "name": "Mythomax L2 13B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-04-25", + "last_updated": "2024-04-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.09 + }, + "limit": { + "context": 4096, + "output": 3200 + } + }, + { + "id": "novita-ai/kwaipilot/kat-coder", + "name": "KAT-Coder-Pro V1(Free)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "novita-ai/kwaipilot/kat-coder-pro", + "name": "Kat Coder Pro", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-05", + "last_updated": "2026-01-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.06 + }, + "limit": { + "context": 256000, + "output": 128000 + } + }, + { + "id": "novita-ai/meta-llama/llama-3-70b-instruct", + "name": "Llama3 70B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-04-25", + "last_updated": "2024-04-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.51, + "output": 0.74 + }, + "limit": { + "context": 8192, + "output": 8000 + } + }, + { + "id": "novita-ai/meta-llama/llama-3-8b-instruct", + "name": "Llama 3 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-04-25", + "last_updated": "2024-04-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.04, + "output": 0.04 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "novita-ai/meta-llama/llama-3.1-8b-instruct", + "name": "Llama 3.1 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-07-24", + "last_updated": "2024-07-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.05 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "novita-ai/meta-llama/llama-3.3-70b-instruct", + "name": "Llama 3.3 70B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-07", + "last_updated": "2024-12-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.135, + "output": 0.4 + }, + "limit": { + "context": 131072, + "output": 120000 + } + }, + { + "id": "novita-ai/meta-llama/llama-4-maverick-17b-128e-instruct-fp8", + "name": "Llama 4 Maverick Instruct", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-06", + "last_updated": "2025-04-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 0.85 + }, + "limit": { + "context": 1048576, + "output": 8192 + } + }, + { + "id": "novita-ai/meta-llama/llama-4-scout-17b-16e-instruct", + "name": "Llama 4 Scout Instruct", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-06", + "last_updated": "2025-04-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.18, + "output": 0.59 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "novita-ai/microsoft/wizardlm-2-8x22b", + "name": "Wizardlm 2 8x22B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-04-24", + "last_updated": "2024-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.62, + "output": 0.62 + }, + "limit": { + "context": 65535, + "output": 8000 + } + }, + { + "id": "novita-ai/minimax/minimax-m2", + "name": "MiniMax-M2", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "novita-ai/minimax/minimax-m2.1", + "name": "Minimax M2.1", + "family": "minimax", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "novita-ai/minimax/minimax-m2.5", + "name": "MiniMax M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03 + }, + "limit": { + "context": 204800, + "output": 131100 + } + }, + { + "id": "novita-ai/minimaxai/minimax-m1-80k", + "name": "MiniMax M1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.2 + }, + "limit": { + "context": 1000000, + "output": 40000 + } + }, + { + "id": "novita-ai/mistralai/mistral-nemo", + "name": "Mistral Nemo", + "family": "mistral-nemo", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-07-30", + "last_updated": "2024-07-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.04, + "output": 0.17 + }, + "limit": { + "context": 60288, + "output": 16000 + } + }, + { + "id": "novita-ai/moonshotai/kimi-k2", + "name": "Kimi K2 0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "novita-ai/moonshotai/kimi-k2-instruct", + "name": "Kimi K2 Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-11", + "last_updated": "2025-07-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.57, + "output": 2.3 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "novita-ai/moonshotai/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-07", + "last_updated": "2025-11-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.5 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "novita-ai/moonshotai/kimi-k2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0, + "cache_read": 0.1 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "novita-ai/nousresearch/hermes-2-pro-llama-3-8b", + "name": "Hermes 2 Pro Llama 3 8B", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-06-27", + "last_updated": "2024-06-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.14 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "novita-ai/openai/gpt-oss-120b", + "name": "OpenAI GPT OSS 120B", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-06", + "last_updated": "2025-08-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.25 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/openai/gpt-oss-20b", + "name": "OpenAI: GPT OSS 20B", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-08-06", + "last_updated": "2025-08-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.04, + "output": 0.15 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/paddlepaddle/paddleocr-vl", + "name": "PaddleOCR-VL", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-10-22", + "last_updated": "2025-10-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.02 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "novita-ai/qwen/qwen-2.5-72b-instruct", + "name": "Qwen 2.5 72B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-10-15", + "last_updated": "2024-10-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.38, + "output": 0.4 + }, + "limit": { + "context": 32000, + "output": 8192 + } + }, + { + "id": "novita-ai/qwen/qwen-mt-plus", + "name": "Qwen MT Plus", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-09-03", + "last_updated": "2025-09-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.75 + }, + "limit": { + "context": 16384, + "output": 8192 + } + }, + { + "id": "novita-ai/qwen/qwen2.5-7b-instruct", + "name": "Qwen2.5 7B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.07 + }, + "limit": { + "context": 32000, + "output": 32000 + } + }, + { + "id": "novita-ai/qwen/qwen2.5-vl-72b-instruct", + "name": "Qwen2.5 VL 72B Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-25", + "last_updated": "2025-03-25", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.8, + "output": 0.8 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "novita-ai/qwen/qwen3-235b-a22b-fp8", + "name": "Qwen3 235B A22B", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-29", + "last_updated": "2025-04-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 40960, + "output": 20000 + } + }, + { + "id": "novita-ai/qwen/qwen3-235b-a22b-instruct", + "name": "Qwen3 235B A22B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-22", + "last_updated": "2025-07-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.58 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "novita-ai/qwen/qwen3-235b-a22b-thinking", + "name": "Qwen3 235B A22b Thinking 2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 3.0 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/qwen/qwen3-30b-a3b-fp8", + "name": "Qwen3 30B A3B", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-29", + "last_updated": "2025-04-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.45 + }, + "limit": { + "context": 40960, + "output": 20000 + } + }, + { + "id": "novita-ai/qwen/qwen3-32b-fp8", + "name": "Qwen3 32B", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-29", + "last_updated": "2025-04-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.45 + }, + "limit": { + "context": 40960, + "output": 20000 + } + }, + { + "id": "novita-ai/qwen/qwen3-4b-fp8", + "name": "Qwen3 4B", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-29", + "last_updated": "2025-04-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.03, + "output": 0.03 + }, + "limit": { + "context": 128000, + "output": 20000 + } + }, + { + "id": "novita-ai/qwen/qwen3-8b-fp8", + "name": "Qwen3 8B", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-29", + "last_updated": "2025-04-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.035, + "output": 0.138 + }, + "limit": { + "context": 128000, + "output": 20000 + } + }, + { + "id": "novita-ai/qwen/qwen3-coder-30b-a3b-instruct", + "name": "Qwen3 Coder 30b A3B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-09", + "last_updated": "2025-10-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.27 + }, + "limit": { + "context": 160000, + "output": 32768 + } + }, + { + "id": "novita-ai/qwen/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.3 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "novita-ai/qwen/qwen3-coder-next", + "name": "Qwen3 Coder Next", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-03", + "last_updated": "2026-02-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.5 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "novita-ai/qwen/qwen3-max", + "name": "Qwen3 Max", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-24", + "last_updated": "2025-09-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.11, + "output": 8.45 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "novita-ai/qwen/qwen3-next-80b-a3b-instruct", + "name": "Qwen3 Next 80B A3B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-10", + "last_updated": "2025-09-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.5 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/qwen/qwen3-next-80b-a3b-thinking", + "name": "Qwen3 Next 80B A3B Thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-10", + "last_updated": "2025-09-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.5 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/qwen/qwen3-omni-30b-a3b-instruct", + "name": "Qwen3 Omni 30B A3B Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-09-24", + "last_updated": "2025-09-24", + "modalities": { + "input": [ + "text", + "video", + "audio", + "image" + ], + "output": [ + "text", + "audio" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.97 + }, + "limit": { + "context": 65536, + "output": 16384 + } + }, + { + "id": "novita-ai/qwen/qwen3-omni-30b-a3b-thinking", + "name": "Qwen3 Omni 30B A3B Thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-24", + "last_updated": "2025-09-24", + "modalities": { + "input": [ + "text", + "audio", + "video", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.25, + "output": 0.97 + }, + "limit": { + "context": 65536, + "output": 16384 + } + }, + { + "id": "novita-ai/qwen/qwen3-vl-235b-a22b-instruct", + "name": "Qwen3 VL 235B A22B Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-24", + "last_updated": "2025-09-24", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.5 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/qwen/qwen3-vl-235b-a22b-thinking", + "name": "Qwen3 VL 235B A22B Thinking", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-09-24", + "last_updated": "2025-09-24", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.98, + "output": 3.95 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/qwen/qwen3-vl-30b-a3b-instruct", + "name": "qwen/qwen3-vl-30b-a3b-instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-11", + "last_updated": "2025-10-11", + "modalities": { + "input": [ + "text", + "video", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.7 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/qwen/qwen3-vl-30b-a3b-thinking", + "name": "qwen/qwen3-vl-30b-a3b-thinking", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-11", + "last_updated": "2025-10-11", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.0 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/qwen/qwen3-vl-8b-instruct", + "name": "qwen/qwen3-vl-8b-instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-17", + "last_updated": "2025-10-17", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.5 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/qwen/qwen3.5-397b-a17b", + "name": "Qwen3.5-397B-A17B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.6 + }, + "limit": { + "context": 262144, + "output": 64000 + } + }, + { + "id": "novita-ai/sao10k/L3-8B-Stheno-v3.2", + "name": "L3 8B Stheno V3.2", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-29", + "last_updated": "2024-11-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.05 + }, + "limit": { + "context": 8192, + "output": 32000 + } + }, + { + "id": "novita-ai/sao10k/l3-70b-euryale-v2.1", + "name": "L3 70B Euryale V2.1\t", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-06-18", + "last_updated": "2024-06-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.48, + "output": 1.48 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "novita-ai/sao10k/l3-8b-lunaris", + "name": "Sao10k L3 8B Lunaris\t", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-11-28", + "last_updated": "2024-11-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.05 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "novita-ai/sao10k/l31-70b-euryale-v2.2", + "name": "L31 70B Euryale V2.2", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-19", + "last_updated": "2024-09-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.48, + "output": 1.48 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "novita-ai/skywork/r1v4-lite", + "name": "Skywork R1V4-Lite", + "family": "skywork", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "novita-ai/xiaomimimo/mimo-v2-flash", + "name": "XiaomiMiMo/MiMo-V2-Flash", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-12-19", + "last_updated": "2025-12-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3, + "cache_read": 0.3 + }, + "limit": { + "context": 262144, + "output": 32000 + } + }, + { + "id": "novita-ai/zai-org/autoglm-phone-9b-multilingual", + "name": "AutoGLM-Phone-9B-Multilingual", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-10", + "last_updated": "2025-12-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.035, + "output": 0.138 + }, + "limit": { + "context": 65536, + "output": 65536 + } + }, + { + "id": "novita-ai/zai-org/glm-4.5", + "name": "GLM-4.5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "novita-ai/zai-org/glm-4.5-air", + "name": "GLM 4.5 Air", + "family": "glm-air", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-10-13", + "last_updated": "2025-10-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.13, + "output": 0.85 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "novita-ai/zai-org/glm-4.5v", + "name": "GLM 4.5V", + "family": "glmv", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-08-11", + "last_updated": "2025-08-11", + "modalities": { + "input": [ + "text", + "video", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.8, + "cache_read": 0.11 + }, + "limit": { + "context": 65536, + "output": 16384 + } + }, + { + "id": "novita-ai/zai-org/glm-4.6", + "name": "GLM 4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.2, + "cache_read": 0.11 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "novita-ai/zai-org/glm-4.6v", + "name": "GLM 4.6V", + "family": "glmv", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "video", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.9, + "cache_read": 0.055 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "novita-ai/zai-org/glm-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "novita-ai/zai-org/glm-4.7-flash", + "name": "GLM-4.7-Flash", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "novita-ai/zai-org/glm-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.2 + }, + "limit": { + "context": 202800, + "output": 131072 + } + }, + { + "id": "nvidia/black-forest-labs/flux.1-dev", + "name": "FLUX.1-dev", + "family": "flux", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2024-08-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 4096, + "output": 0 + } + }, + { + "id": "nvidia/deepseek-ai/deepseek-coder-6.7b-instruct", + "name": "Deepseek Coder 6.7b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2023-10-29", + "last_updated": "2023-10-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/deepseek-ai/deepseek-r1", + "name": "Deepseek R1", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/deepseek-ai/deepseek-v3.1", + "name": "DeepSeek V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-08-20", + "last_updated": "2025-08-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/deepseek-ai/deepseek-v3.1-terminus", + "name": "DeepSeek V3.1 Terminus", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-09-22", + "last_updated": "2025-09-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/deepseek-ai/deepseek-v3.2", + "name": "DeepSeek V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "nvidia/google/codegemma-1.1-7b", + "name": "Codegemma 1.1 7b", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-04-30", + "last_updated": "2024-04-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/google/codegemma-7b", + "name": "Codegemma 7b", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-03-21", + "last_updated": "2024-03-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/google/gemma-2-27b-it", + "name": "Gemma 2 27b It", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-06-24", + "last_updated": "2024-06-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/google/gemma-2-2b-it", + "name": "Gemma 2 2b It", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-16", + "last_updated": "2024-07-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/google/gemma-3-12b-it", + "name": "Gemma 3 12b It", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-01", + "last_updated": "2025-03-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/google/gemma-3-1b-it", + "name": "Gemma 3 1b It", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-10", + "last_updated": "2025-03-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/google/gemma-3-27b-it", + "name": "Gemma-3-27B-IT", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-12-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "nvidia/google/gemma-3n-e2b-it", + "name": "Gemma 3n E2b It", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-06-12", + "last_updated": "2025-06-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/google/gemma-3n-e4b-it", + "name": "Gemma 3n E4b It", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-06-03", + "last_updated": "2025-06-03", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/meta/codellama-70b", + "name": "Codellama 70b", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-01-29", + "last_updated": "2024-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/meta/llama-3.1-405b-instruct", + "name": "Llama 3.1 405b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-16", + "last_updated": "2024-07-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/meta/llama-3.1-70b-instruct", + "name": "Llama 3.1 70b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-16", + "last_updated": "2024-07-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/meta/llama-3.2-11b-vision-instruct", + "name": "Llama 3.2 11b Vision Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-09-18", + "last_updated": "2024-09-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/meta/llama-3.2-1b-instruct", + "name": "Llama 3.2 1b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-09-18", + "last_updated": "2024-09-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/meta/llama-3.3-70b-instruct", + "name": "Llama 3.3 70b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-26", + "last_updated": "2024-11-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/meta/llama-4-maverick-17b-128e-instruct", + "name": "Llama 4 Maverick 17b 128e Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-02", + "release_date": "2025-04-01", + "last_updated": "2025-04-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/meta/llama-4-scout-17b-16e-instruct", + "name": "Llama 4 Scout 17b 16e Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-02", + "release_date": "2025-04-02", + "last_updated": "2025-04-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/meta/llama3-70b-instruct", + "name": "Llama3 70b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-04-17", + "last_updated": "2024-04-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/meta/llama3-8b-instruct", + "name": "Llama3 8b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-04-17", + "last_updated": "2024-04-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/microsoft/phi-3-medium-128k-instruct", + "name": "Phi 3 Medium 128k Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-05-07", + "last_updated": "2024-05-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/microsoft/phi-3-medium-4k-instruct", + "name": "Phi 3 Medium 4k Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-05-07", + "last_updated": "2024-05-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 4000, + "output": 4096 + } + }, + { + "id": "nvidia/microsoft/phi-3-small-128k-instruct", + "name": "Phi 3 Small 128k Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-05-07", + "last_updated": "2024-05-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/microsoft/phi-3-small-8k-instruct", + "name": "Phi 3 Small 8k Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-05-07", + "last_updated": "2024-05-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 8000, + "output": 4096 + } + }, + { + "id": "nvidia/microsoft/phi-3-vision-128k-instruct", + "name": "Phi 3 Vision 128k Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-05-19", + "last_updated": "2024-05-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/microsoft/phi-3.5-moe-instruct", + "name": "Phi 3.5 Moe Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-08-17", + "last_updated": "2024-08-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/microsoft/phi-3.5-vision-instruct", + "name": "Phi 3.5 Vision Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-08-16", + "last_updated": "2024-08-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/microsoft/phi-4-mini-instruct", + "name": "Phi-4-Mini", + "family": "phi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-12-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "nvidia/minimaxai/minimax-m2", + "name": "MiniMax-M2", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-10-27", + "last_updated": "2025-10-31", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "nvidia/minimaxai/minimax-m2.1", + "name": "MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "nvidia/mistralai/codestral-22b-instruct-v0.1", + "name": "Codestral 22b Instruct V0.1", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-05-29", + "last_updated": "2024-05-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/mistralai/devstral-2-123b-instruct", + "name": "Devstral-2-123B-Instruct-2512", + "family": "devstral", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2025-12-08", + "last_updated": "2025-12-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "nvidia/mistralai/mamba-codestral-7b-v0.1", + "name": "Mamba Codestral 7b V0.1", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-07-16", + "last_updated": "2024-07-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/mistralai/ministral-14b-instruct", + "name": "Ministral 3 14B Instruct 2512", + "family": "ministral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-12", + "release_date": "2025-12-01", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "nvidia/mistralai/mistral-large-2-instruct", + "name": "Mistral Large 2 Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-24", + "last_updated": "2024-07-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/mistralai/mistral-large-3-675b-instruct", + "name": "Mistral Large 3 675B Instruct 2512", + "family": "mistral-large", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-02", + "last_updated": "2025-12-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "nvidia/mistralai/mistral-small-3.1-24b-instruct", + "name": "Mistral Small 3.1 24b Instruct 2503", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-11", + "last_updated": "2025-03-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/moonshotai/kimi-k2-instruct", + "name": "Kimi K2 Instruct", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-01", + "release_date": "2025-01-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/moonshotai/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-11", + "last_updated": "2025-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "nvidia/moonshotai/kimi-k2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "nvidia/nvidia/cosmos-nemotron-34b", + "name": "Cosmos Nemotron 34B", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "nvidia/nvidia/llama-3.1-nemotron-51b-instruct", + "name": "Llama 3.1 Nemotron 51b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-22", + "last_updated": "2024-09-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/llama-3.1-nemotron-70b-instruct", + "name": "Llama 3.1 Nemotron 70b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-10-12", + "last_updated": "2024-10-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/llama-3.1-nemotron-ultra-253b-v1", + "name": "Llama-3.1-Nemotron-Ultra-253B-v1", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-07-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "nvidia/nvidia/llama-3.3-nemotron-super-49b-v1", + "name": "Llama 3.3 Nemotron Super 49b V1", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-16", + "last_updated": "2025-03-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/llama-3.3-nemotron-super-49b-v1.5", + "name": "Llama 3.3 Nemotron Super 49b V1.5", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-16", + "last_updated": "2025-03-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/llama-embed-nemotron-8b", + "name": "Llama Embed Nemotron 8B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2025-03", + "release_date": "2025-03-18", + "last_updated": "2025-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 2048 + } + }, + { + "id": "nvidia/nvidia/llama3-chatqa-1.5-70b", + "name": "Llama3 Chatqa 1.5 70b", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-04-28", + "last_updated": "2024-04-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/nemoretriever-ocr-v1", + "name": "NeMo Retriever OCR v1", + "family": "nemoretriever", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 0, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/nemotron-3-nano-30b-a3b", + "name": "nemotron-3-nano-30b-a3b", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2024-12", + "last_updated": "2024-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "nvidia/nvidia/nemotron-4-340b-instruct", + "name": "Nemotron 4 340b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-06-13", + "last_updated": "2024-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/nvidia-nemotron-nano-9b-v2", + "name": "nvidia-nemotron-nano-9b-v2", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2025-08-18", + "last_updated": "2025-08-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "nvidia/nvidia/parakeet-tdt-0.6b-v2", + "name": "Parakeet TDT 0.6B v2", + "family": "parakeet", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2024-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 0, + "output": 4096 + } + }, + { + "id": "nvidia/openai/gpt-oss-120b", + "name": "GPT-OSS-120B", + "family": "gpt-oss", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2025-08-04", + "last_updated": "2025-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/openai/whisper-large-v3", + "name": "Whisper Large v3", + "family": "whisper", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2023-09", + "release_date": "2023-09-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 0, + "output": 4096 + } + }, + { + "id": "nvidia/qwen/qwen2.5-coder-32b-instruct", + "name": "Qwen2.5 Coder 32b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-06", + "last_updated": "2024-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/qwen/qwen2.5-coder-7b-instruct", + "name": "Qwen2.5 Coder 7b Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-17", + "last_updated": "2024-09-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/qwen/qwen3-235b-a22b", + "name": "Qwen3-235B-A22B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-12-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "nvidia/qwen/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 66536 + } + }, + { + "id": "nvidia/qwen/qwen3-next-80b-a3b-instruct", + "name": "Qwen3-Next-80B-A3B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-12-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 16384 + } + }, + { + "id": "nvidia/qwen/qwen3-next-80b-a3b-thinking", + "name": "Qwen3-Next-80B-A3B-Thinking", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-12-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 16384 + } + }, + { + "id": "nvidia/qwen/qwq-32b", + "name": "Qwq 32b", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-05", + "last_updated": "2025-03-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/z-ai/glm4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "nvidia/z-ai/glm5", + "name": "GLM5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 202752, + "output": 131000 + } + }, + { + "id": "ollama-cloud/cogito-2.1:671b", + "name": "cogito-2.1:671b", + "family": "cogito", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-11-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 163840, + "output": 32000 + } + }, + { + "id": "ollama-cloud/deepseek-v3.1:671b", + "name": "deepseek-v3.1:671b", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-08-21", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "ollama-cloud/deepseek-v3.2", + "name": "deepseek-v3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-06-15", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 163840, + "output": 65536 + } + }, + { + "id": "ollama-cloud/devstral-2:123b", + "name": "devstral-2:123b", + "family": "devstral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2025-12-09", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "ollama-cloud/devstral-small-2:24b", + "name": "devstral-small-2:24b", + "family": "devstral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "release_date": "2025-12-09", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "ollama-cloud/gemini-3-flash-preview", + "name": "gemini-3-flash-preview", + "family": "gemini-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "ollama-cloud/gemini-3-pro-preview", + "name": "gemini-3-pro-preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2025-11-18", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 1048576, + "output": 64000 + } + }, + { + "id": "ollama-cloud/gemma3:12b", + "name": "gemma3:12b", + "family": "gemma", + "attachment": true, + "reasoning": false, + "tool_call": false, + "release_date": "2024-12-01", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "ollama-cloud/gemma3:27b", + "name": "gemma3:27b", + "family": "gemma", + "attachment": true, + "reasoning": false, + "tool_call": false, + "release_date": "2025-07-27", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "ollama-cloud/gemma3:4b", + "name": "gemma3:4b", + "family": "gemma", + "attachment": true, + "reasoning": false, + "tool_call": false, + "release_date": "2024-12-01", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "ollama-cloud/glm-4.6", + "name": "glm-4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-09-29", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "ollama-cloud/glm-4.7", + "name": "glm-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-12-22", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "ollama-cloud/glm-5", + "name": "glm-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "ollama-cloud/gpt-oss:120b", + "name": "gpt-oss:120b", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-08-05", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "ollama-cloud/gpt-oss:20b", + "name": "gpt-oss:20b", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-08-05", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "ollama-cloud/kimi-k2-thinking", + "name": "kimi-k2-thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "ollama-cloud/kimi-k2.5", + "name": "kimi-k2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "ollama-cloud/kimi-k2:1t", + "name": "kimi-k2:1t", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "knowledge": "2024-10", + "release_date": "2025-07-11", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "ollama-cloud/minimax-m2", + "name": "minimax-m2", + "family": "minimax", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2025-10-23", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 204800, + "output": 128000 + } + }, + { + "id": "ollama-cloud/minimax-m2.1", + "name": "minimax-m2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-12-23", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "ollama-cloud/minimax-m2.5", + "name": "minimax-m2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "knowledge": "2025-01", + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "ollama-cloud/ministral-3:14b", + "name": "ministral-3:14b", + "family": "ministral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "release_date": "2024-12-01", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 128000 + } + }, + { + "id": "ollama-cloud/ministral-3:3b", + "name": "ministral-3:3b", + "family": "ministral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "release_date": "2024-10-22", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 128000 + } + }, + { + "id": "ollama-cloud/ministral-3:8b", + "name": "ministral-3:8b", + "family": "ministral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "release_date": "2024-12-01", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 128000 + } + }, + { + "id": "ollama-cloud/mistral-large-3:675b", + "name": "mistral-large-3:675b", + "family": "mistral-large", + "attachment": true, + "reasoning": false, + "tool_call": true, + "release_date": "2025-12-02", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "ollama-cloud/nemotron-3-nano:30b", + "name": "nemotron-3-nano:30b", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-12-15", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "ollama-cloud/qwen3-coder-next", + "name": "qwen3-coder-next", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2026-02-02", + "last_updated": "2026-02-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "ollama-cloud/qwen3-coder:480b", + "name": "qwen3-coder:480b", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2025-07-22", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "ollama-cloud/qwen3-next:80b", + "name": "qwen3-next:80b", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-09-15", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "ollama-cloud/qwen3-vl:235b", + "name": "qwen3-vl:235b", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2025-09-22", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "ollama-cloud/qwen3-vl:235b-instruct", + "name": "qwen3-vl:235b-instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "release_date": "2025-09-22", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "ollama-cloud/qwen3.5:397b", + "name": "qwen3.5:397b", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-02-15", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 81920 + } + }, + { + "id": "ollama-cloud/rnj-1:8b", + "name": "rnj-1:8b", + "family": "rnj", + "attachment": false, + "reasoning": false, + "tool_call": true, + "release_date": "2025-12-06", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 32768, + "output": 4096 + } + }, { "id": "openai/codex-mini", "name": "Codex Mini", @@ -8642,15 +54586,15 @@ }, { "id": "openai/gpt-4o", - "name": "GPT-4o", + "name": "GPT-4o (2024-11-20)", "family": "gpt", "attachment": true, "reasoning": false, "tool_call": true, "temperature": true, "knowledge": "2023-09", - "release_date": "2024-05-13", - "last_updated": "2024-08-06", + "release_date": "2024-11-20", + "last_updated": "2024-11-20", "modalities": { "input": [ "text", @@ -9621,6 +55565,1165 @@ "output": 1536 } }, + { + "id": "opencode/big-pickle", + "name": "Big Pickle", + "family": "big-pickle", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-10-17", + "last_updated": "2025-10-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "opencode/claude-3.5-haiku", + "name": "Claude Haiku 3.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07-31", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 4.0, + "cache_read": 0.08, + "cache_write": 1.0 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "opencode/claude-haiku-4.5", + "name": "Claude Haiku 4.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "opencode/claude-opus-4.1", + "name": "Claude Opus 4.1", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "opencode/claude-opus-4.5", + "name": "Claude Opus 4.5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-11-24", + "last_updated": "2025-11-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "opencode/claude-opus-4.6", + "name": "Claude Opus 4.6", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "opencode/claude-sonnet-4", + "name": "Claude Sonnet 4", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "opencode/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "opencode/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "opencode/gemini-3-flash", + "name": "Gemini 3 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "opencode/gemini-3-pro", + "name": "Gemini 3 Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "opencode/gemini-3.1-pro", + "name": "Gemini 3.1 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "opencode/glm-4.6", + "name": "GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.1 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "opencode/glm-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.1 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "opencode/glm-4.7-free", + "name": "GLM-4.7 Free", + "family": "glm-free", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "opencode/glm-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.2 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "opencode/glm-5-free", + "name": "GLM-5 Free", + "family": "glm-free", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "opencode/gpt-5", + "name": "GPT-5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.07, + "output": 8.5, + "cache_read": 0.107 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opencode/gpt-5-codex", + "name": "GPT-5 Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.07, + "output": 8.5, + "cache_read": 0.107 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opencode/gpt-5-nano", + "name": "GPT-5 Nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opencode/gpt-5.1", + "name": "GPT-5.1", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.07, + "output": 8.5, + "cache_read": 0.107 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opencode/gpt-5.1-codex", + "name": "GPT-5.1 Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.07, + "output": 8.5, + "cache_read": 0.107 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opencode/gpt-5.1-codex-max", + "name": "GPT-5.1 Codex Max", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opencode/gpt-5.1-codex-mini", + "name": "GPT-5.1 Codex Mini", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.025 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opencode/gpt-5.2", + "name": "GPT-5.2", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opencode/gpt-5.2-codex", + "name": "GPT-5.2 Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-01-14", + "last_updated": "2026-01-14", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "opencode/grok-code", + "name": "Grok Code Fast 1", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-20", + "last_updated": "2025-08-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "opencode/kimi-k2", + "name": "Kimi K2", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.5, + "cache_read": 0.4 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "opencode/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.5, + "cache_read": 0.4 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "opencode/kimi-k2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.0, + "cache_read": 0.08 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "opencode/kimi-k2.5-free", + "name": "Kimi K2.5 Free", + "family": "kimi-free", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "opencode/minimax-m2.1", + "name": "MiniMax M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.1 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "opencode/minimax-m2.1-free", + "name": "MiniMax M2.1 Free", + "family": "minimax-free", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "opencode/minimax-m2.5", + "name": "MiniMax M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.06 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "opencode/minimax-m2.5-free", + "name": "MiniMax M2.5 Free", + "family": "minimax-free", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "opencode/qwen3-coder", + "name": "Qwen3 Coder", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 1.8 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "opencode/trinity-large-preview-free", + "name": "Trinity Large Preview", + "family": "trinity", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2026-01-28", + "last_updated": "2026-01-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, { "id": "openrouter/allenai/molmo-2-8b:free", "name": "Molmo2 8B (free)", @@ -9949,6 +57052,37 @@ "output": 64000 } }, + { + "id": "openrouter/anthropic/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "openrouter/arcee-ai/trinity-large-preview:free", "name": "Trinity Large Preview", @@ -10024,8 +57158,7 @@ "text" ], "output": [ - "image", - "text" + "image" ] }, "open_weights": false, @@ -10055,8 +57188,7 @@ "text" ], "output": [ - "image", - "text" + "image" ] }, "open_weights": true, @@ -10086,8 +57218,7 @@ "text" ], "output": [ - "image", - "text" + "image" ] }, "open_weights": false, @@ -10117,8 +57248,7 @@ "text" ], "output": [ - "image", - "text" + "image" ] }, "open_weights": false, @@ -10148,8 +57278,7 @@ "text" ], "output": [ - "image", - "text" + "image" ] }, "open_weights": true, @@ -10995,6 +58124,39 @@ "output": 66000 } }, + { + "id": "openrouter/google/gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, { "id": "openrouter/google/gemma-2-9b-it", "name": "Gemma 2 9B", @@ -13276,6 +60438,33 @@ "output": 100000 } }, + { + "id": "openrouter/openrouter/aurora-alpha", + "name": "Aurora Alpha", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-09", + "last_updated": "2026-02-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 50000 + } + }, { "id": "openrouter/openrouter/sherlock-dash-alpha", "name": "Sherlock Dash Alpha", @@ -13336,6 +60525,35 @@ "output": 0 } }, + { + "id": "openrouter/prime-intellect/intellect-3", + "name": "Intellect 3", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-01-15", + "last_updated": "2025-01-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.1 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, { "id": "openrouter/qwen/qwen-2.5-coder-32b-instruct", "name": "Qwen2.5 Coder 32B Instruct", @@ -14065,6 +61283,68 @@ "output": 262144 } }, + { + "id": "openrouter/qwen/qwen3.5-397b-a17b", + "name": "Qwen3.5 397B A17B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.6 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "openrouter/qwen/qwen3.5-plus-02-15", + "name": "Qwen3.5 Plus 2026-02-15", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.4 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, { "id": "openrouter/qwen/qwq-32b:free", "name": "QwQ 32B (free)", @@ -14877,7 +62157,7 @@ }, { "id": "openrouter/z-ai/glm-4.7-flash", - "name": "GLM-4.7", + "name": "GLM-4.7-Flash", "family": "glm", "attachment": false, "reasoning": true, @@ -14932,6 +62212,13345 @@ "output": 131000 } }, + { + "id": "ovhcloud/deepseek-r1-distill-llama-70b", + "name": "DeepSeek-R1-Distill-Llama-70B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-30", + "last_updated": "2025-01-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.74, + "output": 0.74 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "ovhcloud/gpt-oss-120b", + "name": "gpt-oss-120b", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-08-28", + "last_updated": "2025-08-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.47 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "ovhcloud/gpt-oss-20b", + "name": "gpt-oss-20b", + "attachment": false, + "reasoning": true, + "tool_call": true, + "release_date": "2025-08-28", + "last_updated": "2025-08-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.05, + "output": 0.18 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "ovhcloud/llama-3.1-8b-instruct", + "name": "Llama-3.1-8B-Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-11", + "last_updated": "2025-06-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.11, + "output": 0.11 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "ovhcloud/meta-llama-3_3-70b-instruct", + "name": "Meta-Llama-3_3-70B-Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-01", + "last_updated": "2025-04-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.74, + "output": 0.74 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "ovhcloud/mistral-7b-instruct-v0.3", + "name": "Mistral-7B-Instruct-v0.3", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-01", + "last_updated": "2025-04-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.11, + "output": 0.11 + }, + "limit": { + "context": 65536, + "output": 65536 + } + }, + { + "id": "ovhcloud/mistral-nemo-instruct", + "name": "Mistral-Nemo-Instruct-2407", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-20", + "last_updated": "2024-11-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.14 + }, + "limit": { + "context": 65536, + "output": 65536 + } + }, + { + "id": "ovhcloud/mistral-small-3.2-24b-instruct", + "name": "Mistral-Small-3.2-24B-Instruct-2506", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-16", + "last_updated": "2025-07-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.31 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "ovhcloud/mixtral-8x7b-instruct-v0.1", + "name": "Mixtral-8x7B-Instruct-v0.1", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-04-01", + "last_updated": "2025-04-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 0.7 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "ovhcloud/qwen2.5-coder-32b-instruct", + "name": "Qwen2.5-Coder-32B-Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-24", + "last_updated": "2025-03-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.96, + "output": 0.96 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "ovhcloud/qwen2.5-vl-72b-instruct", + "name": "Qwen2.5-VL-72B-Instruct", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-31", + "last_updated": "2025-03-31", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.01, + "output": 1.01 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "ovhcloud/qwen3-32b", + "name": "Qwen3-32B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-16", + "last_updated": "2025-07-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.25 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "ovhcloud/qwen3-coder-30b-a3b-instruct", + "name": "Qwen3-Coder-30B-A3B-Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-28", + "last_updated": "2025-10-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.26 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "perplexity/sonar", + "name": "Sonar", + "family": "sonar", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-09-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 1.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "perplexity/sonar-deep-research", + "name": "Perplexity Sonar Deep Research", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2025-02-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "perplexity/sonar-pro", + "name": "Sonar Pro", + "family": "sonar-pro", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-09-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "perplexity/sonar-reasoning-pro", + "name": "Sonar Reasoning Pro", + "family": "sonar-reasoning", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-09-01", + "release_date": "2024-01-01", + "last_updated": "2025-09-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "poe/anthropic/claude-haiku-3", + "name": "Claude-Haiku-3", + "family": "claude-haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-03-09", + "last_updated": "2024-03-09", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.21, + "output": 1.1, + "cache_read": 0.021, + "cache_write": 0.26 + }, + "limit": { + "context": 189096, + "output": 8192 + } + }, + { + "id": "poe/anthropic/claude-haiku-3.5", + "name": "Claude-Haiku-3.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-10-01", + "last_updated": "2024-10-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.68, + "output": 3.4, + "cache_read": 0.068, + "cache_write": 0.85 + }, + "limit": { + "context": 189096, + "output": 8192 + } + }, + { + "id": "poe/anthropic/claude-haiku-4.5", + "name": "Claude-Haiku-4.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.85, + "output": 4.3, + "cache_read": 0.085, + "cache_write": 1.1 + }, + "limit": { + "context": 192000, + "output": 64000 + } + }, + { + "id": "poe/anthropic/claude-opus-4", + "name": "Claude-Opus-4", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-05-21", + "last_updated": "2025-05-21", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 13.0, + "output": 64.0, + "cache_read": 1.3, + "cache_write": 16.0 + }, + "limit": { + "context": 192512, + "output": 28672 + } + }, + { + "id": "poe/anthropic/claude-opus-4.1", + "name": "Claude-Opus-4.1", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 13.0, + "output": 64.0, + "cache_read": 1.3, + "cache_write": 16.0 + }, + "limit": { + "context": 196608, + "output": 32000 + } + }, + { + "id": "poe/anthropic/claude-opus-4.5", + "name": "Claude-Opus-4.5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-21", + "last_updated": "2025-11-21", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 4.3, + "output": 21.0, + "cache_read": 0.43, + "cache_write": 5.3 + }, + "limit": { + "context": 196608, + "output": 64000 + } + }, + { + "id": "poe/anthropic/claude-opus-4.6", + "name": "Claude-Opus-4.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-02-04", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 4.3, + "output": 21.0, + "cache_read": 0.43, + "cache_write": 5.3 + }, + "limit": { + "context": 983040, + "output": 128000 + } + }, + { + "id": "poe/anthropic/claude-sonnet-3.5", + "name": "Claude-Sonnet-3.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-06-05", + "last_updated": "2024-06-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.6, + "output": 13.0, + "cache_read": 0.26, + "cache_write": 3.2 + }, + "limit": { + "context": 189096, + "output": 8192 + } + }, + { + "id": "poe/anthropic/claude-sonnet-3.5-june", + "name": "Claude-Sonnet-3.5-June", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-11-18", + "last_updated": "2024-11-18", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.6, + "output": 13.0, + "cache_read": 0.26, + "cache_write": 3.2 + }, + "limit": { + "context": 189096, + "output": 8192 + } + }, + { + "id": "poe/anthropic/claude-sonnet-3.7", + "name": "Claude-Sonnet-3.7", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-02-19", + "last_updated": "2025-02-19", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.6, + "output": 13.0, + "cache_read": 0.26, + "cache_write": 3.2 + }, + "limit": { + "context": 196608, + "output": 128000 + } + }, + { + "id": "poe/anthropic/claude-sonnet-4", + "name": "Claude-Sonnet-4", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-05-21", + "last_updated": "2025-05-21", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.6, + "output": 13.0, + "cache_read": 0.26, + "cache_write": 3.2 + }, + "limit": { + "context": 983040, + "output": 64000 + } + }, + { + "id": "poe/anthropic/claude-sonnet-4.5", + "name": "Claude-Sonnet-4.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-09-26", + "last_updated": "2025-09-26", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.6, + "output": 13.0, + "cache_read": 0.26, + "cache_write": 3.2 + }, + "limit": { + "context": 983040, + "output": 32768 + } + }, + { + "id": "poe/anthropic/claude-sonnet-4.6", + "name": "Claude-Sonnet-4.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.6, + "output": 13.0, + "cache_read": 0.26, + "cache_write": 3.2 + }, + "limit": { + "context": 983040, + "output": 128000 + } + }, + { + "id": "poe/cerebras/gpt-oss-120b-cs", + "name": "gpt-oss-120b-cs", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-06", + "last_updated": "2025-08-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "poe/cerebras/llama-3.1-8b-cs", + "name": "llama-3.1-8b-cs", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-05-13", + "last_updated": "2025-05-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "poe/cerebras/llama-3.3-70b-cs", + "name": "llama-3.3-70b-cs", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-05-13", + "last_updated": "2025-05-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "poe/cerebras/qwen3-235b-2507-cs", + "name": "qwen3-235b-2507-cs", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-06", + "last_updated": "2025-08-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "poe/cerebras/qwen3-32b-cs", + "name": "qwen3-32b-cs", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-05-15", + "last_updated": "2025-05-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "poe/elevenlabs/elevenlabs-music", + "name": "ElevenLabs-Music", + "family": "elevenlabs", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-29", + "last_updated": "2025-08-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "audio" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 2000, + "output": 0 + } + }, + { + "id": "poe/elevenlabs/elevenlabs-v2.5-turbo", + "name": "ElevenLabs-v2.5-Turbo", + "family": "elevenlabs", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-10-28", + "last_updated": "2024-10-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "audio" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 0 + } + }, + { + "id": "poe/elevenlabs/elevenlabs-v3", + "name": "ElevenLabs-v3", + "family": "elevenlabs", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-06-05", + "last_updated": "2025-06-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "audio" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 0 + } + }, + { + "id": "poe/google/gemini-2.0-flash", + "name": "Gemini-2.0-Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.42 + }, + "limit": { + "context": 990000, + "output": 8192 + } + }, + { + "id": "poe/google/gemini-2.0-flash-lite", + "name": "Gemini-2.0-Flash-Lite", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-02-05", + "last_updated": "2025-02-05", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.052, + "output": 0.21 + }, + "limit": { + "context": 990000, + "output": 8192 + } + }, + { + "id": "poe/google/gemini-2.5-flash", + "name": "Gemini-2.5-Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-04-26", + "last_updated": "2025-04-26", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.21, + "output": 1.8, + "cache_read": 0.021 + }, + "limit": { + "context": 1065535, + "output": 65535 + } + }, + { + "id": "poe/google/gemini-2.5-flash-lite", + "name": "Gemini-2.5-Flash-Lite", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-06-19", + "last_updated": "2025-06-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 1024000, + "output": 64000 + } + }, + { + "id": "poe/google/gemini-2.5-pro", + "name": "Gemini-2.5-Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-02-05", + "last_updated": "2025-02-05", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.87, + "output": 7.0, + "cache_read": 0.087 + }, + "limit": { + "context": 1065535, + "output": 65535 + } + }, + { + "id": "poe/google/gemini-3-flash", + "name": "Gemini-3-Flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-10-07", + "last_updated": "2025-10-07", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.4, + "cache_read": 0.04 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "poe/google/gemini-3-pro", + "name": "Gemini-3-Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-10-22", + "last_updated": "2025-10-22", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.6, + "output": 9.6, + "cache_read": 0.16 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "poe/google/gemini-deep-research", + "name": "gemini-deep-research", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.6, + "output": 9.6 + }, + "limit": { + "context": 1048576, + "output": 0 + } + }, + { + "id": "poe/google/imagen-3", + "name": "Imagen-3", + "family": "imagen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-10-15", + "last_updated": "2024-10-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "poe/google/imagen-3-fast", + "name": "Imagen-3-Fast", + "family": "imagen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-10-17", + "last_updated": "2024-10-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "poe/google/imagen-4", + "name": "Imagen-4", + "family": "imagen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "poe/google/imagen-4-fast", + "name": "Imagen-4-Fast", + "family": "imagen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-06-25", + "last_updated": "2025-06-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "poe/google/imagen-4-ultra", + "name": "Imagen-4-Ultra", + "family": "imagen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-05-24", + "last_updated": "2025-05-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "poe/google/lyria", + "name": "Lyria", + "family": "lyria", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-06-04", + "last_updated": "2025-06-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "audio" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "poe/google/nano-banana", + "name": "Nano-Banana", + "family": "nano-banana", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-21", + "last_updated": "2025-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 0.21, + "output": 1.8, + "cache_read": 0.021 + }, + "limit": { + "context": 65536, + "output": 0 + } + }, + { + "id": "poe/google/nano-banana-pro", + "name": "Nano-Banana-Pro", + "family": "nano-banana", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 65536, + "output": 0 + } + }, + { + "id": "poe/google/veo-2", + "name": "Veo-2", + "family": "veo", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-12-02", + "last_updated": "2024-12-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "poe/google/veo-3", + "name": "Veo-3", + "family": "veo", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-05-21", + "last_updated": "2025-05-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "poe/google/veo-3-fast", + "name": "Veo-3-Fast", + "family": "veo", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-10-13", + "last_updated": "2025-10-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "poe/google/veo-3.1", + "name": "Veo-3.1", + "family": "veo", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "poe/google/veo-3.1-fast", + "name": "Veo-3.1-Fast", + "family": "veo", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "poe/ideogramai/ideogram", + "name": "Ideogram", + "family": "ideogram", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-04-03", + "last_updated": "2024-04-03", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 150, + "output": 0 + } + }, + { + "id": "poe/ideogramai/ideogram-v2", + "name": "Ideogram-v2", + "family": "ideogram", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-08-21", + "last_updated": "2024-08-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 150, + "output": 0 + } + }, + { + "id": "poe/ideogramai/ideogram-v2a", + "name": "Ideogram-v2a", + "family": "ideogram", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-02-27", + "last_updated": "2025-02-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 150, + "output": 0 + } + }, + { + "id": "poe/ideogramai/ideogram-v2a-turbo", + "name": "Ideogram-v2a-Turbo", + "family": "ideogram", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-02-27", + "last_updated": "2025-02-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 150, + "output": 0 + } + }, + { + "id": "poe/lumalabs/ray2", + "name": "Ray2", + "family": "ray", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-02-20", + "last_updated": "2025-02-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 5000, + "output": 0 + } + }, + { + "id": "poe/novita/glm-4.6", + "name": "GLM-4.6", + "family": "glm", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "poe/novita/glm-4.6v", + "name": "glm-4.6v", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-09", + "last_updated": "2025-12-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 131000, + "output": 32768 + } + }, + { + "id": "poe/novita/glm-4.7", + "name": "glm-4.7", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 205000, + "output": 131072 + } + }, + { + "id": "poe/novita/glm-4.7-flash", + "name": "glm-4.7-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 65500 + } + }, + { + "id": "poe/novita/glm-4.7-n", + "name": "glm-4.7-n", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 205000, + "output": 131072 + } + }, + { + "id": "poe/novita/kimi-k2-thinking", + "name": "kimi-k2-thinking", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-07", + "last_updated": "2025-11-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 0 + } + }, + { + "id": "poe/novita/kimi-k2.5", + "name": "kimi-k2.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 262144 + } + }, + { + "id": "poe/novita/minimax-m2.1", + "name": "minimax-m2.1", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-26", + "last_updated": "2025-12-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 205000, + "output": 131072 + } + }, + { + "id": "poe/openai/chatgpt-4o", + "name": "ChatGPT-4o-Latest", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-08-14", + "last_updated": "2024-08-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 4.5, + "output": 14.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "poe/openai/dall-e-3", + "name": "DALL-E-3", + "family": "dall-e", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2023-11-06", + "last_updated": "2023-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 800, + "output": 0 + } + }, + { + "id": "poe/openai/gpt-3.5-turbo", + "name": "GPT-3.5-Turbo", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2023-09-13", + "last_updated": "2023-09-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.45, + "output": 1.4 + }, + "limit": { + "context": 16384, + "output": 2048 + } + }, + { + "id": "poe/openai/gpt-3.5-turbo-instruct", + "name": "GPT-3.5-Turbo-Instruct", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2023-09-20", + "last_updated": "2023-09-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.4, + "output": 1.8 + }, + "limit": { + "context": 3500, + "output": 1024 + } + }, + { + "id": "poe/openai/gpt-3.5-turbo-raw", + "name": "GPT-3.5-Turbo-Raw", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2023-09-27", + "last_updated": "2023-09-27", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.45, + "output": 1.4 + }, + "limit": { + "context": 4524, + "output": 2048 + } + }, + { + "id": "poe/openai/gpt-4-classic", + "name": "GPT-4-Classic-0314", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-08-26", + "last_updated": "2024-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 27.0, + "output": 54.0 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, + { + "id": "poe/openai/gpt-4-turbo", + "name": "GPT-4-Turbo", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2023-09-13", + "last_updated": "2023-09-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 9.0, + "output": 27.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "poe/openai/gpt-4.1", + "name": "GPT-4.1", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.8, + "output": 7.2, + "cache_read": 0.45 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "poe/openai/gpt-4.1-mini", + "name": "GPT-4.1-mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-04-15", + "last_updated": "2025-04-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.36, + "output": 1.4, + "cache_read": 0.09 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "poe/openai/gpt-4.1-nano", + "name": "GPT-4.1-nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-04-15", + "last_updated": "2025-04-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.36, + "cache_read": 0.022 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "poe/openai/gpt-4o", + "name": "GPT-4o", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-05-13", + "last_updated": "2024-05-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "poe/openai/gpt-4o-aug", + "name": "GPT-4o-Aug", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-11-21", + "last_updated": "2024-11-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.2, + "output": 9.0, + "cache_read": 1.1 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "poe/openai/gpt-4o-mini", + "name": "GPT-4o-mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.54, + "cache_read": 0.068 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "poe/openai/gpt-4o-mini-search", + "name": "GPT-4o-mini-Search", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-03-11", + "last_updated": "2025-03-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.54 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "poe/openai/gpt-4o-search", + "name": "GPT-4o-Search", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-03-11", + "last_updated": "2025-03-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.2, + "output": 9.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "poe/openai/gpt-5", + "name": "GPT-5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 9.0, + "cache_read": 0.11 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-5-chat", + "name": "GPT-5-Chat", + "family": "gpt-codex", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 9.0, + "cache_read": 0.11 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "poe/openai/gpt-5-codex", + "name": "GPT-5-Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 9.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-5-mini", + "name": "GPT-5-mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-06-25", + "last_updated": "2025-06-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.22, + "output": 1.8, + "cache_read": 0.022 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-5-nano", + "name": "GPT-5-nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.045, + "output": 0.36, + "cache_read": 0.0045 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-5-pro", + "name": "GPT-5-Pro", + "family": "gpt-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-10-06", + "last_updated": "2025-10-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 14.0, + "output": 110.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-5.1", + "name": "GPT-5.1", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-12", + "last_updated": "2025-11-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 9.0, + "cache_read": 0.11 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-5.1-codex", + "name": "GPT-5.1-Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-12", + "last_updated": "2025-11-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 9.0, + "cache_read": 0.11 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-5.1-codex-max", + "name": "GPT-5.1-Codex-Max", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 9.0, + "cache_read": 0.11 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-5.1-codex-mini", + "name": "GPT-5.1-Codex-Mini", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-12", + "last_updated": "2025-11-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.22, + "output": 1.8, + "cache_read": 0.022 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-5.1-instant", + "name": "GPT-5.1-Instant", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-12", + "last_updated": "2025-11-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 9.0, + "cache_read": 0.11 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "poe/openai/gpt-5.2", + "name": "GPT-5.2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.6, + "output": 13.0, + "cache_read": 0.16 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-5.2-codex", + "name": "GPT-5.2-Codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-01-14", + "last_updated": "2026-01-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.6, + "output": 13.0, + "cache_read": 0.16 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-5.2-instant", + "name": "GPT-5.2-Instant", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.6, + "output": 13.0, + "cache_read": 0.16 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "poe/openai/gpt-5.2-pro", + "name": "GPT-5.2-Pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 19.0, + "output": 150.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "poe/openai/gpt-image-1", + "name": "GPT-Image-1", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-03-31", + "last_updated": "2025-03-31", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 0 + } + }, + { + "id": "poe/openai/gpt-image-1-mini", + "name": "GPT-Image-1-Mini", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-26", + "last_updated": "2025-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "poe/openai/gpt-image-1.5", + "name": "gpt-image-1.5", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-12-16", + "last_updated": "2025-12-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 0 + } + }, + { + "id": "poe/openai/o1", + "name": "o1", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2024-12-18", + "last_updated": "2024-12-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 14.0, + "output": 54.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "poe/openai/o1-pro", + "name": "o1-pro", + "family": "o-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-03-19", + "last_updated": "2025-03-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 140.0, + "output": 540.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "poe/openai/o3", + "name": "o3", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.8, + "output": 7.2, + "cache_read": 0.45 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "poe/openai/o3-deep-research", + "name": "o3-deep-research", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-06-27", + "last_updated": "2025-06-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 9.0, + "output": 36.0, + "cache_read": 2.2 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "poe/openai/o3-mini", + "name": "o3-mini", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-01-31", + "last_updated": "2025-01-31", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.99, + "output": 4.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "poe/openai/o3-mini-high", + "name": "o3-mini-high", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-01-31", + "last_updated": "2025-01-31", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.99, + "output": 4.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "poe/openai/o3-pro", + "name": "o3-pro", + "family": "o-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-06-10", + "last_updated": "2025-06-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 18.0, + "output": 72.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "poe/openai/o4-mini", + "name": "o4-mini", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.99, + "output": 4.0, + "cache_read": 0.25 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "poe/openai/o4-mini-deep-research", + "name": "o4-mini-deep-research", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-06-27", + "last_updated": "2025-06-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.8, + "output": 7.2, + "cache_read": 0.45 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "poe/openai/sora-2", + "name": "Sora-2", + "family": "sora", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-10-06", + "last_updated": "2025-10-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "poe/openai/sora-2-pro", + "name": "Sora-2-Pro", + "family": "sora", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-10-06", + "last_updated": "2025-10-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "poe/poetools/claude-code", + "name": "claude-code", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-27", + "last_updated": "2025-11-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "poe/runwayml/runway", + "name": "Runway", + "family": "runway", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-10-11", + "last_updated": "2024-10-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256, + "output": 0 + } + }, + { + "id": "poe/runwayml/runway-gen-4-turbo", + "name": "Runway-Gen-4-Turbo", + "family": "runway", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-05-09", + "last_updated": "2025-05-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256, + "output": 0 + } + }, + { + "id": "poe/stabilityai/stablediffusionxl", + "name": "StableDiffusionXL", + "family": "stable-diffusion", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2023-07-09", + "last_updated": "2023-07-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200, + "output": 0 + } + }, + { + "id": "poe/topazlabs-co/topazlabs", + "name": "TopazLabs", + "family": "topazlabs", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-12-03", + "last_updated": "2024-12-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 204, + "output": 0 + } + }, + { + "id": "poe/trytako/tako", + "name": "Tako", + "family": "tako", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2024-08-15", + "last_updated": "2024-08-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 2048, + "output": 0 + } + }, + { + "id": "poe/xai/grok-3", + "name": "Grok 3", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-04-11", + "last_updated": "2025-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "poe/xai/grok-3-mini", + "name": "Grok 3 Mini", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-04-11", + "last_updated": "2025-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.5, + "cache_read": 0.075 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "poe/xai/grok-4", + "name": "Grok-4", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-07-10", + "last_updated": "2025-07-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 256000, + "output": 128000 + } + }, + { + "id": "poe/xai/grok-4-fast", + "name": "Grok-4-Fast-Reasoning", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-09-16", + "last_updated": "2025-09-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 128000 + } + }, + { + "id": "poe/xai/grok-4-fast-non", + "name": "Grok-4-Fast-Non-Reasoning", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-09-16", + "last_updated": "2025-09-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 128000 + } + }, + { + "id": "poe/xai/grok-4.1-fast", + "name": "Grok-4.1-Fast-Reasoning", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "poe/xai/grok-4.1-fast-non", + "name": "Grok-4.1-Fast-Non-Reasoning", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": false, + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "poe/xai/grok-code-fast-1", + "name": "Grok Code Fast 1", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2025-08-22", + "last_updated": "2025-08-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.5, + "cache_read": 0.02 + }, + "limit": { + "context": 256000, + "output": 128000 + } + }, + { + "id": "privatemode-ai/gemma-3-27b", + "name": "Gemma 3 27B", + "family": "gemma", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-03-12", + "last_updated": "2025-03-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "privatemode-ai/gpt-oss-120b", + "name": "gpt-oss-120b", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2025-08-04", + "last_updated": "2025-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "privatemode-ai/qwen3-coder-30b-a3b", + "name": "Qwen3-Coder 30B-A3B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "privatemode-ai/qwen3-embedding-4b", + "name": "Qwen3-Embedding 4B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-06-06", + "last_updated": "2025-06-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32000, + "output": 2560 + } + }, + { + "id": "privatemode-ai/whisper-large-v3", + "name": "Whisper large-v3", + "family": "whisper", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2023-09-01", + "last_updated": "2023-09-01", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 0, + "output": 4096 + } + }, + { + "id": "qihang-ai/claude-haiku-4.5", + "name": "Claude Haiku 4.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-10-01", + "last_updated": "2025-10-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.71 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "qihang-ai/claude-opus-4.5", + "name": "Claude Opus 4.5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-11-01", + "last_updated": "2025-11-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.71, + "output": 3.57 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "qihang-ai/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.43, + "output": 2.14 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "qihang-ai/gemini-2.5-flash", + "name": "Gemini 2.5 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.71 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "qihang-ai/gemini-3-flash-preview", + "name": "Gemini 3 Flash Preview", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.43 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "qihang-ai/gemini-3-pro-preview", + "name": "Gemini 3 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.57, + "output": 3.43 + }, + "limit": { + "context": 1000000, + "output": 65000 + } + }, + { + "id": "qihang-ai/gpt-5-mini", + "name": "GPT-5-Mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09-30", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.04, + "output": 0.29 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "qihang-ai/gpt-5.2", + "name": "GPT-5.2", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "qihang-ai/gpt-5.2-codex", + "name": "GPT-5.2 Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 1.14 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "qiniu-ai/MiniMax-M1", + "name": "MiniMax M1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1000000, + "output": 80000 + } + }, + { + "id": "qiniu-ai/claude-3.5-haiku", + "name": "Claude 3.5 Haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-26", + "last_updated": "2025-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "qiniu-ai/claude-3.5-sonnet", + "name": "Claude 3.5 Sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-09", + "last_updated": "2025-09-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 8200 + } + }, + { + "id": "qiniu-ai/claude-3.7-sonnet", + "name": "Claude 3.7 Sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "qiniu-ai/claude-4.0-opus", + "name": "Claude 4.0 Opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/claude-4.0-sonnet", + "name": "Claude 4.0 Sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "qiniu-ai/claude-4.1-opus", + "name": "Claude 4.1 Opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-06", + "last_updated": "2025-08-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/claude-4.5-haiku", + "name": "Claude 4.5 Haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-16", + "last_updated": "2025-10-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "qiniu-ai/claude-4.5-opus", + "name": "Claude 4.5 Opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-25", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 200000 + } + }, + { + "id": "qiniu-ai/claude-4.5-sonnet", + "name": "Claude 4.5 Sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "qiniu-ai/deepseek-r1", + "name": "DeepSeek-R1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/deepseek-v3", + "name": "DeepSeek-V3-0324", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 16000 + } + }, + { + "id": "qiniu-ai/deepseek-v3.1", + "name": "DeepSeek-V3.1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-19", + "last_updated": "2025-08-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/deepseek/deepseek-math-v2", + "name": "Deepseek/Deepseek-Math-V2", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-12-04", + "last_updated": "2025-12-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 160000, + "output": 160000 + } + }, + { + "id": "qiniu-ai/deepseek/deepseek-v3.1-terminus", + "name": "DeepSeek/DeepSeek-V3.1-Terminus", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-22", + "last_updated": "2025-09-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/deepseek/deepseek-v3.1-terminus-thinking", + "name": "DeepSeek/DeepSeek-V3.1-Terminus-Thinking", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-09-22", + "last_updated": "2025-09-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/deepseek/deepseek-v3.2-251201", + "name": "Deepseek/DeepSeek-V3.2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/deepseek/deepseek-v3.2-exp", + "name": "DeepSeek/DeepSeek-V3.2-Exp", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/deepseek/deepseek-v3.2-exp-thinking", + "name": "DeepSeek/DeepSeek-V3.2-Exp-Thinking", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/doubao-1.5-pro-32k", + "name": "Doubao 1.5 Pro 32k", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 12000 + } + }, + { + "id": "qiniu-ai/doubao-1.5-thinking-pro", + "name": "Doubao 1.5 Thinking Pro", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 16000 + } + }, + { + "id": "qiniu-ai/doubao-1.5-vision-pro", + "name": "Doubao 1.5 Vision Pro", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 16000 + } + }, + { + "id": "qiniu-ai/doubao-seed-1.6", + "name": "Doubao-Seed 1.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-15", + "last_updated": "2025-08-15", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/doubao-seed-1.6-flash", + "name": "Doubao-Seed 1.6 Flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-15", + "last_updated": "2025-08-15", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/doubao-seed-1.6-thinking", + "name": "Doubao-Seed 1.6 Thinking", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-15", + "last_updated": "2025-08-15", + "modalities": { + "input": [ + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/gemini-2.0-flash", + "name": "Gemini 2.0 Flash", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1048576, + "output": 8192 + } + }, + { + "id": "qiniu-ai/gemini-2.0-flash-lite", + "name": "Gemini 2.0 Flash Lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1048576, + "output": 8192 + } + }, + { + "id": "qiniu-ai/gemini-2.5-flash", + "name": "Gemini 2.5 Flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1048576, + "output": 64000 + } + }, + { + "id": "qiniu-ai/gemini-2.5-flash-image", + "name": "Gemini 2.5 Flash Image", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-10-22", + "last_updated": "2025-10-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "qiniu-ai/gemini-2.5-flash-lite", + "name": "Gemini 2.5 Flash Lite", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1048576, + "output": 64000 + } + }, + { + "id": "qiniu-ai/gemini-2.5-pro", + "name": "Gemini 2.5 Pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "qiniu-ai/gemini-3.0-flash-preview", + "name": "Gemini 3.0 Flash Preview", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-18", + "last_updated": "2025-12-18", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "qiniu-ai/gemini-3.0-pro-image-preview", + "name": "Gemini 3.0 Pro Image Preview", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-20", + "last_updated": "2025-11-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 32768, + "output": 8192 + } + }, + { + "id": "qiniu-ai/gemini-3.0-pro-preview", + "name": "Gemini 3.0 Pro Preview", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-19", + "last_updated": "2025-11-19", + "modalities": { + "input": [ + "text", + "image", + "video", + "pdf", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "qiniu-ai/glm-4.5", + "name": "GLM 4.5", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "qiniu-ai/glm-4.5-air", + "name": "GLM 4.5 Air", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 131000, + "output": 4096 + } + }, + { + "id": "qiniu-ai/gpt-oss-120b", + "name": "gpt-oss-120b", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-06", + "last_updated": "2025-08-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "qiniu-ai/gpt-oss-20b", + "name": "gpt-oss-20b", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-06", + "last_updated": "2025-08-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "qiniu-ai/kimi-k2", + "name": "Kimi K2", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "qiniu-ai/kling-v2-6", + "name": "Kling-V2 6", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-01-13", + "last_updated": "2026-01-13", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "video" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 99999999, + "output": 99999999 + } + }, + { + "id": "qiniu-ai/meituan/longcat-flash-chat", + "name": "Meituan/Longcat-Flash-Chat", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-05", + "last_updated": "2025-11-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "qiniu-ai/mimo-v2-flash", + "name": "Mimo-V2-Flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "qiniu-ai/minimax/minimax-m2", + "name": "Minimax/Minimax-M2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-28", + "last_updated": "2025-10-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "qiniu-ai/minimax/minimax-m2.1", + "name": "Minimax/Minimax-M2.1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 204800, + "output": 128000 + } + }, + { + "id": "qiniu-ai/moonshotai/kimi-k2", + "name": "Kimi K2 0905", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-08", + "last_updated": "2025-09-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 100000 + } + }, + { + "id": "qiniu-ai/moonshotai/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-07", + "last_updated": "2025-11-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 100000 + } + }, + { + "id": "qiniu-ai/openai/gpt-5", + "name": "OpenAI/GPT-5", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-19", + "last_updated": "2025-09-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "qiniu-ai/openai/gpt-5.2", + "name": "OpenAI/GPT-5.2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "qiniu-ai/qwen-max", + "name": "Qwen2.5-Max-2025-01-25", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "qiniu-ai/qwen-turbo", + "name": "Qwen-Turbo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 1000000, + "output": 4096 + } + }, + { + "id": "qiniu-ai/qwen-vl-max", + "name": "Qwen VL-MAX-2025-01-25", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "qiniu-ai/qwen2.5-vl-72b-instruct", + "name": "Qwen 2.5 VL 72B Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "qiniu-ai/qwen2.5-vl-7b-instruct", + "name": "Qwen 2.5 VL 7B Instruct", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "qiniu-ai/qwen3-235b-a22b", + "name": "Qwen 3 235B A22B", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "qiniu-ai/qwen3-235b-a22b-instruct", + "name": "Qwen3 235b A22B Instruct 2507", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-12", + "last_updated": "2025-08-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 262144, + "output": 64000 + } + }, + { + "id": "qiniu-ai/qwen3-235b-a22b-thinking", + "name": "Qwen3 235B A22B Thinking 2507", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-12", + "last_updated": "2025-08-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 262144, + "output": 4096 + } + }, + { + "id": "qiniu-ai/qwen3-30b-a3b", + "name": "Qwen3 30B A3B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 40000, + "output": 4096 + } + }, + { + "id": "qiniu-ai/qwen3-32b", + "name": "Qwen3 32B", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 40000, + "output": 4096 + } + }, + { + "id": "qiniu-ai/qwen3-coder-480b-a35b-instruct", + "name": "Qwen3 Coder 480B A35B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-14", + "last_updated": "2025-08-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 262000, + "output": 4096 + } + }, + { + "id": "qiniu-ai/qwen3-max", + "name": "Qwen3 Max", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-24", + "last_updated": "2025-09-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "qiniu-ai/qwen3-max-preview", + "name": "Qwen3 Max Preview", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-06", + "last_updated": "2025-09-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "qiniu-ai/qwen3-next-80b-a3b-instruct", + "name": "Qwen3 Next 80B A3B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-12", + "last_updated": "2025-09-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "qiniu-ai/qwen3-next-80b-a3b-thinking", + "name": "Qwen3 Next 80B A3B Thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-12", + "last_updated": "2025-09-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "qiniu-ai/stepfun-ai/gelab-zero-4b-preview", + "name": "Stepfun-Ai/Gelab Zero 4b Preview", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 8192, + "output": 4096 + } + }, + { + "id": "qiniu-ai/x-ai/grok-4-fast", + "name": "x-AI/Grok-4-Fast", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-20", + "last_updated": "2025-09-20", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "qiniu-ai/x-ai/grok-4-fast-non", + "name": "X-Ai/Grok-4-Fast-Non-Reasoning", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-18", + "last_updated": "2025-12-18", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "qiniu-ai/x-ai/grok-4.1-fast", + "name": "x-AI/Grok-4.1-Fast", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-20", + "last_updated": "2025-11-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "qiniu-ai/x-ai/grok-4.1-fast-non", + "name": "X-Ai/Grok 4.1 Fast Non Reasoning", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-19", + "last_updated": "2025-12-19", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 2000000, + "output": 2000000 + } + }, + { + "id": "qiniu-ai/x-ai/grok-code-fast-1", + "name": "x-AI/Grok-Code-Fast 1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-02", + "last_updated": "2025-09-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 10000 + } + }, + { + "id": "qiniu-ai/z-ai/autoglm-phone-9b", + "name": "Z-Ai/Autoglm Phone 9b", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 12800, + "output": 4096 + } + }, + { + "id": "qiniu-ai/z-ai/glm-4.6", + "name": "Z-AI/GLM 4.6", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-11", + "last_updated": "2025-10-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 200000 + } + }, + { + "id": "qiniu-ai/z-ai/glm-4.7", + "name": "Z-Ai/GLM 4.7", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 200000, + "output": 200000 + } + }, + { + "id": "requesty/anthropic/claude-3.7-sonnet", + "name": "Claude Sonnet 3.7", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-01", + "release_date": "2025-02-19", + "last_updated": "2025-02-19", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "requesty/anthropic/claude-haiku-4.5", + "name": "Claude Haiku 4.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-01", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 62000 + } + }, + { + "id": "requesty/anthropic/claude-opus-4", + "name": "Claude Opus 4", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "requesty/anthropic/claude-opus-4.1", + "name": "Claude Opus 4.1", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "requesty/anthropic/claude-opus-4.5", + "name": "Claude Opus 4.5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-11-24", + "last_updated": "2025-11-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "requesty/anthropic/claude-sonnet-4", + "name": "Claude Sonnet 4", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "requesty/anthropic/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "requesty/google/gemini-2.5-flash", + "name": "Gemini 2.5 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.075, + "cache_write": 0.55 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "requesty/google/gemini-2.5-pro", + "name": "Gemini 2.5 Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.31, + "cache_write": 2.375 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "requesty/google/gemini-3-flash-preview", + "name": "Gemini 3 Flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05, + "cache_write": 1.0 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "requesty/google/gemini-3-pro-preview", + "name": "Gemini 3 Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2, + "cache_write": 4.5 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "requesty/openai/gpt-4.1", + "name": "GPT-4.1", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "requesty/openai/gpt-4.1-mini", + "name": "GPT-4.1 Mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.6, + "cache_read": 0.1 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "requesty/openai/gpt-4o-mini", + "name": "GPT-4o Mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.08 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "requesty/openai/gpt-5", + "name": "GPT-5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "audio", + "image", + "video" + ], + "output": [ + "text", + "audio", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "requesty/openai/gpt-5-mini", + "name": "GPT-5 Mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.03 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "requesty/openai/gpt-5-nano", + "name": "GPT-5 Nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 16000, + "output": 4000 + } + }, + { + "id": "requesty/openai/o4-mini", + "name": "o4 Mini", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.28 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "requesty/xai/grok-4", + "name": "Grok 4", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-09-09", + "last_updated": "2025-09-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75, + "cache_write": 3.0 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "requesty/xai/grok-4-fast", + "name": "Grok 4 Fast", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-09-19", + "last_updated": "2025-09-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05, + "cache_write": 0.2 + }, + "limit": { + "context": 2000000, + "output": 64000 + } + }, + { + "id": "sap-ai-core/anthropic--claude-3-haiku", + "name": "anthropic--claude-3-haiku", + "family": "claude-haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-08-31", + "release_date": "2024-03-13", + "last_updated": "2024-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.25, + "cache_read": 0.03, + "cache_write": 0.3 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "sap-ai-core/anthropic--claude-3-opus", + "name": "anthropic--claude-3-opus", + "family": "claude-opus", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-08-31", + "release_date": "2024-02-29", + "last_updated": "2024-02-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "sap-ai-core/anthropic--claude-3-sonnet", + "name": "anthropic--claude-3-sonnet", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-08-31", + "release_date": "2024-03-04", + "last_updated": "2024-03-04", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "sap-ai-core/anthropic--claude-3.5-sonnet", + "name": "anthropic--claude-3.5-sonnet", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04-30", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "sap-ai-core/anthropic--claude-3.7-sonnet", + "name": "anthropic--claude-3.7-sonnet", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10-31", + "release_date": "2025-02-24", + "last_updated": "2025-02-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "sap-ai-core/anthropic--claude-4-opus", + "name": "anthropic--claude-4-opus", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "sap-ai-core/anthropic--claude-4-sonnet", + "name": "anthropic--claude-4-sonnet", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "sap-ai-core/anthropic--claude-4.5-haiku", + "name": "anthropic--claude-4.5-haiku", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-01", + "last_updated": "2025-10-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "sap-ai-core/anthropic--claude-4.5-opus", + "name": "anthropic--claude-4.5-opus", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04-30", + "release_date": "2025-11-24", + "last_updated": "2025-11-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "sap-ai-core/anthropic--claude-4.5-sonnet", + "name": "anthropic--claude-4.5-sonnet", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "sap-ai-core/gemini-2.5-flash", + "name": "gemini-2.5-flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-25", + "last_updated": "2025-06-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.03 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "sap-ai-core/gemini-2.5-pro", + "name": "gemini-2.5-pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-25", + "last_updated": "2025-06-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "sap-ai-core/gpt-5", + "name": "gpt-5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "sap-ai-core/gpt-5-mini", + "name": "gpt-5-mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.025 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "sap-ai-core/gpt-5-nano", + "name": "gpt-5-nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "scaleway/bge-multilingual-gemma2", + "name": "BGE Multilingual Gemma2", + "family": "gemma", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-07-26", + "last_updated": "2025-06-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.13, + "output": 0.0 + }, + "limit": { + "context": 8191, + "output": 3072 + } + }, + { + "id": "scaleway/deepseek-r1-distill-llama-70b", + "name": "DeepSeek R1 Distill Llama 70B", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.9, + "output": 0.9 + }, + "limit": { + "context": 32000, + "output": 4096 + } + }, + { + "id": "scaleway/devstral-2-123b-instruct", + "name": "Devstral 2 123B Instruct (2512)", + "family": "devstral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-07", + "last_updated": "2026-01-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 256000, + "output": 8192 + } + }, + { + "id": "scaleway/gemma-3-27b-it", + "name": "Gemma-3-27B-IT", + "family": "gemma", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2024-12-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 0.5 + }, + "limit": { + "context": 40000, + "output": 8192 + } + }, + { + "id": "scaleway/gpt-oss-120b", + "name": "GPT-OSS 120B", + "family": "gpt-oss", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-01-01", + "last_updated": "2024-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "scaleway/llama-3.1-8b-instruct", + "name": "Llama 3.1 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2025-01-01", + "last_updated": "2025-01-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "scaleway/llama-3.3-70b-instruct", + "name": "Llama-3.3-70B-Instruct", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.9, + "output": 0.9 + }, + "limit": { + "context": 100000, + "output": 4096 + } + }, + { + "id": "scaleway/mistral-nemo-instruct", + "name": "Mistral Nemo Instruct 2407", + "family": "mistral-nemo", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-25", + "last_updated": "2024-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "scaleway/mistral-small-3.2-24b-instruct", + "name": "Mistral Small 3.2 24B Instruct (2506)", + "family": "mistral-small", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-20", + "last_updated": "2025-06-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.35 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "scaleway/pixtral-12b", + "name": "Pixtral 12B 2409", + "family": "pixtral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-25", + "last_updated": "2024-09-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "scaleway/qwen3-235b-a22b-instruct", + "name": "Qwen3 235B A22B Instruct 2507", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-01", + "last_updated": "2025-07-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.75, + "output": 2.25 + }, + "limit": { + "context": 260000, + "output": 8192 + } + }, + { + "id": "scaleway/qwen3-coder-30b-a3b-instruct", + "name": "Qwen3-Coder 30B-A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "scaleway/voxtral-small-24b", + "name": "Voxtral Small 24B 2507", + "family": "voxtral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-01", + "last_updated": "2025-07-01", + "modalities": { + "input": [ + "text", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.35 + }, + "limit": { + "context": 32000, + "output": 8192 + } + }, + { + "id": "scaleway/whisper-large-v3", + "name": "Whisper Large v3", + "family": "whisper", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "knowledge": "2023-09", + "release_date": "2023-09-01", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.003, + "output": 0.0 + }, + "limit": { + "context": 0, + "output": 4096 + } + }, + { + "id": "siliconflow-cn/ByteDance-Seed/Seed-OSS-36B-Instruct", + "name": "ByteDance-Seed/Seed-OSS-36B-Instruct", + "family": "seed", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.21, + "output": 0.57 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Kwaipilot/KAT-Dev", + "name": "Kwaipilot/KAT-Dev", + "family": "kat-coder", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-27", + "last_updated": "2026-01-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "siliconflow-cn/PaddlePaddle/PaddleOCR-VL", + "name": "PaddlePaddle/PaddleOCR-VL", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-10-16", + "last_updated": "2025-10-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "siliconflow-cn/PaddlePaddle/PaddleOCR-VL-1.5", + "name": "PaddlePaddle/PaddleOCR-VL-1.5", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-01-29", + "last_updated": "2026-01-29", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 16384, + "output": 16384 + } + }, + { + "id": "siliconflow-cn/Pro/MiniMaxAI/MiniMax-M2.1", + "name": "Pro/MiniMaxAI/MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 197000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/Pro/MiniMaxAI/MiniMax-M2.5", + "name": "Pro/MiniMaxAI/MiniMax-M2.5", + "family": "minimax", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-13", + "last_updated": "2026-02-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.22 + }, + "limit": { + "context": 192000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/Pro/deepseek-ai/DeepSeek-R1", + "name": "Pro/deepseek-ai/DeepSeek-R1", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-28", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 2.18 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3", + "name": "Pro/deepseek-ai/DeepSeek-V3", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-26", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.0 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3.1-Terminus", + "name": "Pro/deepseek-ai/DeepSeek-V3.1-Terminus", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-29", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 1.0 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3.2", + "name": "Pro/deepseek-ai/DeepSeek-V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-03", + "last_updated": "2025-12-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.42 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow-cn/Pro/moonshotai/Kimi-K2-Instruct", + "name": "Pro/moonshotai/Kimi-K2-Instruct-0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-08", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Pro/moonshotai/Kimi-K2-Thinking", + "name": "Pro/moonshotai/Kimi-K2-Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-07", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.55, + "output": 2.5 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Pro/moonshotai/Kimi-K2.5", + "name": "Pro/moonshotai/Kimi-K2.5", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.55, + "output": 3.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Pro/zai-org/GLM-4.7", + "name": "Pro/zai-org/GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 205000, + "output": 205000 + } + }, + { + "id": "siliconflow-cn/Pro/zai-org/GLM-5", + "name": "Pro/zai-org/GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 3.2 + }, + "limit": { + "context": 205000, + "output": 205000 + } + }, + { + "id": "siliconflow-cn/Qwen/QwQ-32B", + "name": "Qwen/QwQ-32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-06", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.58 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen2.5-14B-Instruct", + "name": "Qwen/Qwen2.5-14B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen2.5-32B-Instruct", + "name": "Qwen/Qwen2.5-32B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-19", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.18 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen2.5-72B-Instruct", + "name": "Qwen/Qwen2.5-72B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.59, + "output": 0.59 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen2.5-72B-Instruct-128K", + "name": "Qwen/Qwen2.5-72B-Instruct-128K", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.59, + "output": 0.59 + }, + "limit": { + "context": 131000, + "output": 4000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen2.5-7B-Instruct", + "name": "Qwen/Qwen2.5-7B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.05 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen2.5-Coder-32B-Instruct", + "name": "Qwen/Qwen2.5-Coder-32B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-11", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.18 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen2.5-VL-32B-Instruct", + "name": "Qwen/Qwen2.5-VL-32B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-24", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.27 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen2.5-VL-72B-Instruct", + "name": "Qwen/Qwen2.5-VL-72B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-28", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.59, + "output": 0.59 + }, + "limit": { + "context": 131000, + "output": 4000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-14B", + "name": "Qwen/Qwen3-14B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-235B-A22B-Instruct", + "name": "Qwen/Qwen3-235B-A22B-Instruct-2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-23", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.6 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-235B-A22B-Thinking", + "name": "Qwen/Qwen3-235B-A22B-Thinking-2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.13, + "output": 0.6 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-30B-A3B-Instruct", + "name": "Qwen/Qwen3-30B-A3B-Instruct-2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.3 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-30B-A3B-Thinking", + "name": "Qwen/Qwen3-30B-A3B-Thinking-2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-31", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.3 + }, + "limit": { + "context": 262000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-32B", + "name": "Qwen/Qwen3-32B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-8B", + "name": "Qwen/Qwen3-8B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.06, + "output": 0.06 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-Coder-30B-A3B-Instruct", + "name": "Qwen/Qwen3-Coder-30B-A3B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-01", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-Coder-480B-A35B-Instruct", + "name": "Qwen/Qwen3-Coder-480B-A35B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-31", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-Next-80B-A3B-Instruct", + "name": "Qwen/Qwen3-Next-80B-A3B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 1.4 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-Next-80B-A3B-Thinking", + "name": "Qwen/Qwen3-Next-80B-A3B-Thinking", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-25", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-Omni-30B-A3B-Captioner", + "name": "Qwen/Qwen3-Omni-30B-A3B-Captioner", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 66000, + "output": 66000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-Omni-30B-A3B-Instruct", + "name": "Qwen/Qwen3-Omni-30B-A3B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 66000, + "output": 66000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-Omni-30B-A3B-Thinking", + "name": "Qwen/Qwen3-Omni-30B-A3B-Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 66000, + "output": 66000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Instruct", + "name": "Qwen/Qwen3-VL-235B-A22B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.5 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Thinking", + "name": "Qwen/Qwen3-VL-235B-A22B-Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.45, + "output": 3.5 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Instruct", + "name": "Qwen/Qwen3-VL-30B-A3B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-05", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 1.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Thinking", + "name": "Qwen/Qwen3-VL-30B-A3B-Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-11", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 1.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-VL-32B-Instruct", + "name": "Qwen/Qwen3-VL-32B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-21", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-VL-32B-Thinking", + "name": "Qwen/Qwen3-VL-32B-Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-21", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.5 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-VL-8B-Instruct", + "name": "Qwen/Qwen3-VL-8B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-15", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.68 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/Qwen/Qwen3-VL-8B-Thinking", + "name": "Qwen/Qwen3-VL-8B-Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-15", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 2.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/THUDM/GLM-4-32B", + "name": "THUDM/GLM-4-32B-0414", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.27 + }, + "limit": { + "context": 33000, + "output": 33000 + } + }, + { + "id": "siliconflow-cn/THUDM/GLM-4-9B", + "name": "THUDM/GLM-4-9B-0414", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.086, + "output": 0.086 + }, + "limit": { + "context": 33000, + "output": 33000 + } + }, + { + "id": "siliconflow-cn/THUDM/GLM-Z1-32B", + "name": "THUDM/GLM-Z1-32B-0414", + "family": "glm-z", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/THUDM/GLM-Z1-9B", + "name": "THUDM/GLM-Z1-9B-0414", + "family": "glm-z", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.086, + "output": 0.086 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/ascend-tribe/pangu-pro-moe", + "name": "ascend-tribe/pangu-pro-moe", + "family": "pangu", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "release_date": "2025-07-02", + "last_updated": "2026-01-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "siliconflow-cn/baidu/ERNIE-4.5-300B-A47B", + "name": "baidu/ERNIE-4.5-300B-A47B", + "family": "ernie", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-02", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.28, + "output": 1.1 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/deepseek-ai/DeepSeek-OCR", + "name": "deepseek-ai/DeepSeek-OCR", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-10-20", + "last_updated": "2025-10-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 8192 + } + }, + { + "id": "siliconflow-cn/deepseek-ai/DeepSeek-R1", + "name": "deepseek-ai/DeepSeek-R1", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-28", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 2.18 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow-cn/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", + "name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-20", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", + "name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-20", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.18 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/deepseek-ai/DeepSeek-V3", + "name": "deepseek-ai/DeepSeek-V3", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-26", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.0 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow-cn/deepseek-ai/DeepSeek-V3.1-Terminus", + "name": "deepseek-ai/DeepSeek-V3.1-Terminus", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-29", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 1.0 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow-cn/deepseek-ai/DeepSeek-V3.2", + "name": "deepseek-ai/DeepSeek-V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-03", + "last_updated": "2025-12-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.42 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow-cn/deepseek-ai/deepseek-vl2", + "name": "deepseek-ai/deepseek-vl2", + "family": "deepseek", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-13", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.15 + }, + "limit": { + "context": 4000, + "output": 4000 + } + }, + { + "id": "siliconflow-cn/inclusionAI/Ling-flash-2.0", + "name": "inclusionAI/Ling-flash-2.0", + "family": "ling", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/inclusionAI/Ling-mini-2.0", + "name": "inclusionAI/Ling-mini-2.0", + "family": "ling", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-10", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/inclusionAI/Ring-flash-2.0", + "name": "inclusionAI/Ring-flash-2.0", + "family": "ring", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-29", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/moonshotai/Kimi-K2-Instruct", + "name": "moonshotai/Kimi-K2-Instruct-0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-08", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/moonshotai/Kimi-K2-Thinking", + "name": "moonshotai/Kimi-K2-Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-07", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.55, + "output": 2.5 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/stepfun-ai/Step-3.5-Flash", + "name": "stepfun-ai/Step-3.5-Flash", + "family": "step", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow-cn/tencent/Hunyuan-A13B-Instruct", + "name": "tencent/Hunyuan-A13B-Instruct", + "family": "hunyuan", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/tencent/Hunyuan-MT-7B", + "name": "tencent/Hunyuan-MT-7B", + "family": "hunyuan", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 33000, + "output": 33000 + } + }, + { + "id": "siliconflow-cn/zai-org/GLM-4.5-Air", + "name": "zai-org/GLM-4.5-Air", + "family": "glm-air", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.86 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow-cn/zai-org/GLM-4.5V", + "name": "zai-org/GLM-4.5V", + "family": "glm", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-13", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.86 + }, + "limit": { + "context": 66000, + "output": 66000 + } + }, + { + "id": "siliconflow-cn/zai-org/GLM-4.6", + "name": "zai-org/GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.9 + }, + "limit": { + "context": 205000, + "output": 205000 + } + }, + { + "id": "siliconflow-cn/zai-org/GLM-4.6V", + "name": "zai-org/GLM-4.6V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-07", + "last_updated": "2025-12-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/ByteDance-Seed/Seed-OSS-36B-Instruct", + "name": "ByteDance-Seed/Seed-OSS-36B-Instruct", + "family": "seed", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.21, + "output": 0.57 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/MiniMaxAI/MiniMax-M2.1", + "name": "MiniMaxAI/MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 197000, + "output": 131000 + } + }, + { + "id": "siliconflow/Qwen/QwQ-32B", + "name": "Qwen/QwQ-32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-06", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.58 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/Qwen/Qwen2.5-14B-Instruct", + "name": "Qwen/Qwen2.5-14B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow/Qwen/Qwen2.5-32B-Instruct", + "name": "Qwen/Qwen2.5-32B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-19", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.18 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow/Qwen/Qwen2.5-72B-Instruct", + "name": "Qwen/Qwen2.5-72B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.59, + "output": 0.59 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow/Qwen/Qwen2.5-72B-Instruct-128K", + "name": "Qwen/Qwen2.5-72B-Instruct-128K", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.59, + "output": 0.59 + }, + "limit": { + "context": 131000, + "output": 4000 + } + }, + { + "id": "siliconflow/Qwen/Qwen2.5-7B-Instruct", + "name": "Qwen/Qwen2.5-7B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.05 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow/Qwen/Qwen2.5-Coder-32B-Instruct", + "name": "Qwen/Qwen2.5-Coder-32B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-11", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.18 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow/Qwen/Qwen2.5-VL-32B-Instruct", + "name": "Qwen/Qwen2.5-VL-32B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-03-24", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.27 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/Qwen/Qwen2.5-VL-72B-Instruct", + "name": "Qwen/Qwen2.5-VL-72B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-28", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.59, + "output": 0.59 + }, + "limit": { + "context": 131000, + "output": 4000 + } + }, + { + "id": "siliconflow/Qwen/Qwen2.5-VL-7B-Instruct", + "name": "Qwen/Qwen2.5-VL-7B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-28", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.05 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-14B", + "name": "Qwen/Qwen3-14B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-235B-A22B", + "name": "Qwen/Qwen3-235B-A22B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.35, + "output": 1.42 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-235B-A22B-Instruct", + "name": "Qwen/Qwen3-235B-A22B-Instruct-2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-23", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.6 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-235B-A22B-Thinking", + "name": "Qwen/Qwen3-235B-A22B-Thinking-2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.13, + "output": 0.6 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-30B-A3B-Instruct", + "name": "Qwen/Qwen3-30B-A3B-Instruct-2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.3 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-30B-A3B-Thinking", + "name": "Qwen/Qwen3-30B-A3B-Thinking-2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-31", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.3 + }, + "limit": { + "context": 262000, + "output": 131000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-32B", + "name": "Qwen/Qwen3-32B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-8B", + "name": "Qwen/Qwen3-8B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.06, + "output": 0.06 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-Coder-30B-A3B-Instruct", + "name": "Qwen/Qwen3-Coder-30B-A3B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-01", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-Coder-480B-A35B-Instruct", + "name": "Qwen/Qwen3-Coder-480B-A35B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-31", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-Next-80B-A3B-Instruct", + "name": "Qwen/Qwen3-Next-80B-A3B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 1.4 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-Next-80B-A3B-Thinking", + "name": "Qwen/Qwen3-Next-80B-A3B-Thinking", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-25", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-Omni-30B-A3B-Captioner", + "name": "Qwen/Qwen3-Omni-30B-A3B-Captioner", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 66000, + "output": 66000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-Omni-30B-A3B-Instruct", + "name": "Qwen/Qwen3-Omni-30B-A3B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 66000, + "output": 66000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-Omni-30B-A3B-Thinking", + "name": "Qwen/Qwen3-Omni-30B-A3B-Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4 + }, + "limit": { + "context": 66000, + "output": 66000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-VL-235B-A22B-Instruct", + "name": "Qwen/Qwen3-VL-235B-A22B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.5 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-VL-235B-A22B-Thinking", + "name": "Qwen/Qwen3-VL-235B-A22B-Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.45, + "output": 3.5 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-VL-30B-A3B-Instruct", + "name": "Qwen/Qwen3-VL-30B-A3B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-05", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 1.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-VL-30B-A3B-Thinking", + "name": "Qwen/Qwen3-VL-30B-A3B-Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-11", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.29, + "output": 1.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-VL-32B-Instruct", + "name": "Qwen/Qwen3-VL-32B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-21", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-VL-32B-Thinking", + "name": "Qwen/Qwen3-VL-32B-Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-21", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.5 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-VL-8B-Instruct", + "name": "Qwen/Qwen3-VL-8B-Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-15", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.68 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/Qwen/Qwen3-VL-8B-Thinking", + "name": "Qwen/Qwen3-VL-8B-Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-15", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 2.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/THUDM/GLM-4-32B", + "name": "THUDM/GLM-4-32B-0414", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.27 + }, + "limit": { + "context": 33000, + "output": 33000 + } + }, + { + "id": "siliconflow/THUDM/GLM-4-9B", + "name": "THUDM/GLM-4-9B-0414", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.086, + "output": 0.086 + }, + "limit": { + "context": 33000, + "output": 33000 + } + }, + { + "id": "siliconflow/THUDM/GLM-Z1-32B", + "name": "THUDM/GLM-Z1-32B-0414", + "family": "glm-z", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/THUDM/GLM-Z1-9B", + "name": "THUDM/GLM-Z1-9B-0414", + "family": "glm-z", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.086, + "output": 0.086 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/baidu/ERNIE-4.5-300B-A47B", + "name": "baidu/ERNIE-4.5-300B-A47B", + "family": "ernie", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-02", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.28, + "output": 1.1 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/deepseek-ai/DeepSeek-R1", + "name": "deepseek-ai/DeepSeek-R1", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-28", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 2.18 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", + "name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-20", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", + "name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-20", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.18 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/deepseek-ai/DeepSeek-V3", + "name": "deepseek-ai/DeepSeek-V3", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-26", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.0 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow/deepseek-ai/DeepSeek-V3.1", + "name": "deepseek-ai/DeepSeek-V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-25", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 1.0 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow/deepseek-ai/DeepSeek-V3.1-Terminus", + "name": "deepseek-ai/DeepSeek-V3.1-Terminus", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-29", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 1.0 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow/deepseek-ai/DeepSeek-V3.2", + "name": "deepseek-ai/DeepSeek-V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-03", + "last_updated": "2025-12-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.42 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow/deepseek-ai/DeepSeek-V3.2-Exp", + "name": "deepseek-ai/DeepSeek-V3.2-Exp", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-10", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.41 + }, + "limit": { + "context": 164000, + "output": 164000 + } + }, + { + "id": "siliconflow/deepseek-ai/deepseek-vl2", + "name": "deepseek-ai/deepseek-vl2", + "family": "deepseek", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-13", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.15 + }, + "limit": { + "context": 4000, + "output": 4000 + } + }, + { + "id": "siliconflow/inclusionAI/Ling-flash-2.0", + "name": "inclusionAI/Ling-flash-2.0", + "family": "ling", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/inclusionAI/Ling-mini-2.0", + "name": "inclusionAI/Ling-mini-2.0", + "family": "ling", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-10", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.28 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/inclusionAI/Ring-flash-2.0", + "name": "inclusionAI/Ring-flash-2.0", + "family": "ring", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-29", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/meta-llama/Meta-Llama-3.1-8B-Instruct", + "name": "meta-llama/Meta-Llama-3.1-8B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-23", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.06, + "output": 0.06 + }, + "limit": { + "context": 33000, + "output": 4000 + } + }, + { + "id": "siliconflow/moonshotai/Kimi-K2-Instruct", + "name": "moonshotai/Kimi-K2-Instruct-0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-08", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/moonshotai/Kimi-K2-Thinking", + "name": "moonshotai/Kimi-K2-Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-11-07", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.55, + "output": 2.5 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/moonshotai/Kimi-K2.5", + "name": "moonshotai/Kimi-K2.5", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.55, + "output": 3.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/nex-agi/DeepSeek-V3.1-Nex-N1", + "name": "nex-agi/DeepSeek-V3.1-Nex-N1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-01-01", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 2.0 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/openai/gpt-oss-120b", + "name": "openai/gpt-oss-120b", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-13", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.45 + }, + "limit": { + "context": 131000, + "output": 8000 + } + }, + { + "id": "siliconflow/openai/gpt-oss-20b", + "name": "openai/gpt-oss-20b", + "family": "gpt-oss", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-13", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.04, + "output": 0.18 + }, + "limit": { + "context": 131000, + "output": 8000 + } + }, + { + "id": "siliconflow/stepfun-ai/Step-3.5-Flash", + "name": "stepfun-ai/Step-3.5-Flash", + "family": "step", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, + { + "id": "siliconflow/tencent/Hunyuan-A13B-Instruct", + "name": "tencent/Hunyuan-A13B-Instruct", + "family": "hunyuan", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-30", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.57 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/tencent/Hunyuan-MT-7B", + "name": "tencent/Hunyuan-MT-7B", + "family": "hunyuan", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-18", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 33000, + "output": 33000 + } + }, + { + "id": "siliconflow/zai-org/GLM-4.5", + "name": "zai-org/GLM-4.5", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/zai-org/GLM-4.5-Air", + "name": "zai-org/GLM-4.5-Air", + "family": "glm-air", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.86 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/zai-org/GLM-4.5V", + "name": "zai-org/GLM-4.5V", + "family": "glm", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-13", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.86 + }, + "limit": { + "context": 66000, + "output": 66000 + } + }, + { + "id": "siliconflow/zai-org/GLM-4.6", + "name": "zai-org/GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-04", + "last_updated": "2025-11-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.9 + }, + "limit": { + "context": 205000, + "output": 205000 + } + }, + { + "id": "siliconflow/zai-org/GLM-4.6V", + "name": "zai-org/GLM-4.6V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-07", + "last_updated": "2025-12-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "siliconflow/zai-org/GLM-4.7", + "name": "zai-org/GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 205000, + "output": 205000 + } + }, + { + "id": "siliconflow/zai-org/GLM-5", + "name": "zai-org/GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 3.2 + }, + "limit": { + "context": 205000, + "output": 205000 + } + }, + { + "id": "stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", + "name": "Qwen3-VL 235B", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-11-01", + "last_updated": "2024-11-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.64, + "output": 1.91 + }, + "limit": { + "context": 218000, + "output": 8192 + } + }, + { + "id": "stackit/Qwen/Qwen3-VL-Embedding-8B", + "name": "Qwen3-VL Embedding 8B", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2026-02-05", + "last_updated": "2026-02-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 0.09 + }, + "limit": { + "context": 32000, + "output": 4096 + } + }, + { + "id": "stackit/cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic", + "name": "Llama 3.3 70B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-12-05", + "last_updated": "2024-12-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.49, + "output": 0.71 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "stackit/google/gemma-3-27b-it", + "name": "Gemma 3 27B", + "family": "gemma", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-05-17", + "last_updated": "2025-05-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.49, + "output": 0.71 + }, + "limit": { + "context": 37000, + "output": 8192 + } + }, + { + "id": "stackit/intfloat/e5-mistral-7b-instruct", + "name": "E5 Mistral 7B", + "family": "mistral", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2023-12-11", + "last_updated": "2023-12-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.02, + "output": 0.02 + }, + "limit": { + "context": 4096, + "output": 4096 + } + }, + { + "id": "stackit/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", + "name": "Llama 3.1 8B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.16, + "output": 0.27 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "stackit/neuralmagic/Mistral-Nemo-Instruct-2407-FP8", + "name": "Mistral Nemo", + "family": "mistral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-07-01", + "last_updated": "2024-07-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.49, + "output": 0.71 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "stackit/openai/gpt-oss-120b", + "name": "GPT-OSS 120B", + "family": "gpt", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.49, + "output": 0.71 + }, + "limit": { + "context": 131000, + "output": 8192 + } + }, + { + "id": "stepfun/step-1-32k", + "name": "Step 1 (32K)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-01-01", + "last_updated": "2026-02-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.05, + "output": 9.59, + "cache_read": 0.41 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "stepfun/step-2-16k", + "name": "Step 2 (16K)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2025-01-01", + "last_updated": "2026-02-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.21, + "output": 16.44, + "cache_read": 1.04 + }, + "limit": { + "context": 16384, + "output": 8192 + } + }, + { + "id": "stepfun/step-3.5-flash", + "name": "Step 3.5 Flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-01-29", + "last_updated": "2026-02-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.096, + "output": 0.288, + "cache_read": 0.019 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "submodel/Qwen/Qwen3-235B-A22B-Instruct", + "name": "Qwen3 235B A22B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-23", + "last_updated": "2025-08-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.3 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "submodel/Qwen/Qwen3-235B-A22B-Thinking", + "name": "Qwen3 235B A22B Thinking 2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-23", + "last_updated": "2025-08-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "submodel/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-23", + "last_updated": "2025-08-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "submodel/deepseek-ai/DeepSeek-R1", + "name": "DeepSeek R1 0528", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-23", + "last_updated": "2025-08-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 2.15 + }, + "limit": { + "context": 75000, + "output": 163840 + } + }, + { + "id": "submodel/deepseek-ai/DeepSeek-V3", + "name": "DeepSeek V3 0324", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-23", + "last_updated": "2025-08-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 75000, + "output": 163840 + } + }, + { + "id": "submodel/deepseek-ai/DeepSeek-V3.1", + "name": "DeepSeek V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-23", + "last_updated": "2025-08-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 75000, + "output": 163840 + } + }, + { + "id": "submodel/openai/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-23", + "last_updated": "2025-08-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.5 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "submodel/zai-org/GLM-4.5-Air", + "name": "GLM 4.5 Air", + "family": "glm-air", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.5 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "submodel/zai-org/GLM-4.5-FP8", + "name": "GLM 4.5 FP8", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.8 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "synthetic/hf:MiniMaxAI/MiniMax-M2", + "name": "MiniMax-M2", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.19 + }, + "limit": { + "context": 196608, + "output": 131000 + } + }, + { + "id": "synthetic/hf:MiniMaxAI/MiniMax-M2.1", + "name": "MiniMax-M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.19 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "synthetic/hf:Qwen/Qwen2.5-Coder-32B-Instruct", + "name": "Qwen2.5-Coder-32B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-11-11", + "last_updated": "2024-11-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.8, + "output": 0.8 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "synthetic/hf:Qwen/Qwen3-235B-A22B-Instruct", + "name": "Qwen 3 235B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04-28", + "last_updated": "2025-07-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "synthetic/hf:Qwen/Qwen3-235B-A22B-Thinking", + "name": "Qwen3 235B A22B Thinking 2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.65, + "output": 3.0 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "synthetic/hf:Qwen/Qwen3-Coder-480B-A35B-Instruct", + "name": "Qwen 3 Coder 480B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 2.0 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "synthetic/hf:deepseek-ai/DeepSeek-R1", + "name": "DeepSeek R1 (0528)", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-01", + "last_updated": "2025-08-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 8.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "synthetic/hf:deepseek-ai/DeepSeek-V3", + "name": "DeepSeek V3 (0324)", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-01", + "last_updated": "2025-08-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 1.2 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "synthetic/hf:deepseek-ai/DeepSeek-V3.1", + "name": "DeepSeek V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-21", + "last_updated": "2025-08-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.56, + "output": 1.68 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "synthetic/hf:deepseek-ai/DeepSeek-V3.1-Terminus", + "name": "DeepSeek V3.1 Terminus", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-09-22", + "last_updated": "2025-09-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 1.2 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "synthetic/hf:deepseek-ai/DeepSeek-V3.2", + "name": "DeepSeek V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 0.4, + "cache_read": 0.27, + "cache_write": 0.0 + }, + "limit": { + "context": 162816, + "output": 8000 + } + }, + { + "id": "synthetic/hf:meta-llama/Llama-3.1-405B-Instruct", + "name": "Llama-3.1-405B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 3.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "synthetic/hf:meta-llama/Llama-3.1-70B-Instruct", + "name": "Llama-3.1-70B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.9, + "output": 0.9 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "synthetic/hf:meta-llama/Llama-3.1-8B-Instruct", + "name": "Llama-3.1-8B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "synthetic/hf:meta-llama/Llama-3.3-70B-Instruct", + "name": "Llama-3.3-70B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.9, + "output": 0.9 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "synthetic/hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", + "name": "Llama-4-Maverick-17B-128E-Instruct-FP8", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 0.88 + }, + "limit": { + "context": 524000, + "output": 4096 + } + }, + { + "id": "synthetic/hf:meta-llama/Llama-4-Scout-17B-16E-Instruct", + "name": "Llama-4-Scout-17B-16E-Instruct", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 328000, + "output": 4096 + } + }, + { + "id": "synthetic/hf:moonshotai/Kimi-K2-Instruct", + "name": "Kimi K2 0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.2, + "output": 1.2 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "synthetic/hf:moonshotai/Kimi-K2-Thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2025-11-07", + "last_updated": "2025-11-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.19 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "synthetic/hf:moonshotai/Kimi-K2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.19 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "synthetic/hf:nvidia/Kimi-K2.5-NVFP4", + "name": "Kimi K2.5 (NVFP4)", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.19 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, + { + "id": "synthetic/hf:openai/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "synthetic/hf:zai-org/GLM-4.6", + "name": "GLM 4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.19 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "synthetic/hf:zai-org/GLM-4.7", + "name": "GLM 4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.55, + "output": 2.19 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "togetherai/MiniMaxAI/MiniMax-M2.5", + "name": "MiniMax-M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "togetherai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput", + "name": "Qwen3 235B A22B Instruct 2507 FP8", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "togetherai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 2.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "togetherai/Qwen/Qwen3-Coder-Next-FP8", + "name": "Qwen3 Coder Next FP8", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-03", + "release_date": "2026-02-03", + "last_updated": "2026-02-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 1.2 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "togetherai/Qwen/Qwen3-Next-80B-A3B-Instruct", + "name": "Qwen3-Next-80B-A3B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.5 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "togetherai/Qwen/Qwen3.5-397B-A17B", + "name": "Qwen3.5 397B A17B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-16", + "last_updated": "2026-02-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.6 + }, + "limit": { + "context": 262144, + "output": 130000 + } + }, + { + "id": "togetherai/deepseek-ai/DeepSeek-R1", + "name": "DeepSeek R1", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-12-26", + "last_updated": "2025-03-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 3.0, + "output": 7.0 + }, + "limit": { + "context": 163839, + "output": 163839 + } + }, + { + "id": "togetherai/deepseek-ai/DeepSeek-V3", + "name": "DeepSeek V3", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-01-20", + "last_updated": "2025-05-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.25, + "output": 1.25 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "togetherai/deepseek-ai/DeepSeek-V3-1", + "name": "DeepSeek V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2025-08-21", + "last_updated": "2025-08-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.7 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "togetherai/essentialai/Rnj-1-Instruct", + "name": "Rnj-1 Instruct", + "family": "rnj", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-12-05", + "last_updated": "2025-12-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.15 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "togetherai/meta-llama/Llama-3.3-70B-Instruct-Turbo", + "name": "Llama 3.3 70B", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.88, + "output": 0.88 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "togetherai/moonshotai/Kimi-K2-Instruct", + "name": "Kimi K2 Instruct-0905", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "togetherai/moonshotai/Kimi-K2-Thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.2, + "output": 4.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "togetherai/moonshotai/Kimi-K2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-01", + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 2.8 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "togetherai/openai/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "togetherai/zai-org/GLM-4.6", + "name": "GLM 4.6", + "family": "glm", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 200000, + "output": 200000 + } + }, + { + "id": "togetherai/zai-org/GLM-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 2.0 + }, + "limit": { + "context": 200000, + "output": 200000 + } + }, + { + "id": "togetherai/zai-org/GLM-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-11", + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2 + }, + "limit": { + "context": 202752, + "output": 131072 + } + }, + { + "id": "upstage/solar-mini", + "name": "solar-mini", + "family": "solar-mini", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2024-06-12", + "last_updated": "2025-04-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.15 + }, + "limit": { + "context": 32768, + "output": 4096 + } + }, + { + "id": "upstage/solar-pro2", + "name": "solar-pro2", + "family": "solar-pro", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-05-20", + "last_updated": "2025-05-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 0.25 + }, + "limit": { + "context": 65536, + "output": 8192 + } + }, + { + "id": "upstage/solar-pro3", + "name": "solar-pro3", + "family": "solar-pro", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2026-01", + "last_updated": "2026-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 0.25 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "v0/v0-1.0-md", + "name": "v0-1.0-md", + "family": "v0", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "v0/v0-1.5-lg", + "name": "v0-1.5-lg", + "family": "v0", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-09", + "last_updated": "2025-06-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0 + }, + "limit": { + "context": 512000, + "output": 32000 + } + }, + { + "id": "v0/v0-1.5-md", + "name": "v0-1.5-md", + "family": "v0", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-09", + "last_updated": "2025-06-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, { "id": "venice/claude-opus-4.6", "name": "Claude Opus 4.6", @@ -14941,7 +75560,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-02-05", - "last_updated": "2026-02-05", + "last_updated": "2026-02-18", "modalities": { "input": [ "text", @@ -14996,6 +75615,37 @@ "output": 49500 } }, + { + "id": "venice/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-17", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.75, + "output": 18.75, + "cache_read": 0.375, + "cache_write": 4.69 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, { "id": "venice/claude-sonnet-45", "name": "Claude Sonnet 4.5", @@ -15125,6 +75775,39 @@ "output": 49500 } }, + { + "id": "venice/gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-19", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 15.0, + "cache_read": 0.5, + "cache_write": 0.5 + }, + "limit": { + "context": 1000000, + "output": 250000 + } + }, { "id": "venice/google-gemma-3-27b-it", "name": "Google Gemma 3 27B Instruct", @@ -15401,7 +76084,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-02-12", - "last_updated": "2026-02-13", + "last_updated": "2026-02-19", "modalities": { "input": [ "text" @@ -15410,7 +76093,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.4, "output": 1.6, @@ -15451,6 +76134,34 @@ "output": 32000 } }, + { + "id": "venice/olafangensan-glm-4.7-flash-heretic", + "name": "GLM 4.7 Flash Heretic", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-04", + "last_updated": "2026-02-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.8 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, { "id": "venice/openai-gpt-52", "name": "GPT-5.2", @@ -15831,16 +76542,6480 @@ "output": 49500 } }, + { + "id": "vercel/alibaba/qwen-3-14b", + "name": "Qwen3-14B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.06, + "output": 0.24 + }, + "limit": { + "context": 40960, + "output": 16384 + } + }, + { + "id": "vercel/alibaba/qwen-3-235b", + "name": "Qwen3 235B A22B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.13, + "output": 0.6 + }, + "limit": { + "context": 40960, + "output": 16384 + } + }, + { + "id": "vercel/alibaba/qwen-3-30b", + "name": "Qwen3-30B-A3B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.08, + "output": 0.29 + }, + "limit": { + "context": 40960, + "output": 16384 + } + }, + { + "id": "vercel/alibaba/qwen-3-32b", + "name": "Qwen 3.32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 40960, + "output": 16384 + } + }, + { + "id": "vercel/alibaba/qwen3-235b-a22b-thinking", + "name": "Qwen3 235B A22B Thinking 2507", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.9 + }, + "limit": { + "context": 262114, + "output": 262114 + } + }, + { + "id": "vercel/alibaba/qwen3-coder", + "name": "Qwen3 Coder 480B A35B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.38, + "output": 1.53 + }, + "limit": { + "context": 262144, + "output": 66536 + } + }, + { + "id": "vercel/alibaba/qwen3-coder-30b-a3b", + "name": "Qwen 3 Coder 30B A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04", + "last_updated": "2025-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.27 + }, + "limit": { + "context": 160000, + "output": 32768 + } + }, + { + "id": "vercel/alibaba/qwen3-coder-next", + "name": "Qwen3 Coder Next", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-07-22", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.2 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "vercel/alibaba/qwen3-coder-plus", + "name": "Qwen3 Coder Plus", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 5.0 + }, + "limit": { + "context": 1000000, + "output": 1000000 + } + }, + { + "id": "vercel/alibaba/qwen3-embedding-0.6b", + "name": "Qwen3 Embedding 0.6B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-11-14", + "last_updated": "2025-11-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.01, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "vercel/alibaba/qwen3-embedding-4b", + "name": "Qwen3 Embedding 4B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-06-05", + "last_updated": "2025-06-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.02, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "vercel/alibaba/qwen3-embedding-8b", + "name": "Qwen3 Embedding 8B", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-06-05", + "last_updated": "2025-06-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "vercel/alibaba/qwen3-max", + "name": "Qwen3 Max", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 6.0 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "vercel/alibaba/qwen3-max-preview", + "name": "Qwen3 Max Preview", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 6.0, + "cache_read": 0.24 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "vercel/alibaba/qwen3-max-thinking", + "name": "Qwen 3 Max Thinking", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01", + "last_updated": "2025-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.2, + "output": 6.0, + "cache_read": 0.24 + }, + "limit": { + "context": 256000, + "output": 65536 + } + }, + { + "id": "vercel/alibaba/qwen3-next-80b-a3b-instruct", + "name": "Qwen3 Next 80B A3B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-12", + "last_updated": "2025-09-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.09, + "output": 1.1 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, + { + "id": "vercel/alibaba/qwen3-next-80b-a3b-thinking", + "name": "Qwen3 Next 80B A3B Thinking", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-12", + "last_updated": "2025-09-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 1.5 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "vercel/alibaba/qwen3-vl-instruct", + "name": "Qwen3 VL Instruct", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-24", + "last_updated": "2025-09-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 2.8 + }, + "limit": { + "context": 131072, + "output": 129024 + } + }, + { + "id": "vercel/alibaba/qwen3-vl-thinking", + "name": "Qwen3 VL Thinking", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-24", + "last_updated": "2025-09-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.7, + "output": 8.4 + }, + "limit": { + "context": 131072, + "output": 129024 + } + }, + { + "id": "vercel/alibaba/qwen3.5-plus", + "name": "Qwen 3.5 Plus", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-16", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.4, + "cache_read": 0.04, + "cache_write": 0.5 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "vercel/amazon/nova-2-lite", + "name": "Nova 2 Lite", + "family": "nova", + "attachment": true, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-01", + "last_updated": "2024-12-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5 + }, + "limit": { + "context": 1000000, + "output": 1000000 + } + }, + { + "id": "vercel/amazon/nova-lite", + "name": "Nova Lite", + "family": "nova-lite", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-03", + "last_updated": "2024-12-03", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.06, + "output": 0.24, + "cache_read": 0.015 + }, + "limit": { + "context": 300000, + "output": 8192 + } + }, + { + "id": "vercel/amazon/nova-micro", + "name": "Nova Micro", + "family": "nova-micro", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-03", + "last_updated": "2024-12-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.035, + "output": 0.14, + "cache_read": 0.00875 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "vercel/amazon/nova-pro", + "name": "Nova Pro", + "family": "nova-pro", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-03", + "last_updated": "2024-12-03", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 3.2, + "cache_read": 0.2 + }, + "limit": { + "context": 300000, + "output": 8192 + } + }, + { + "id": "vercel/amazon/titan-embed-text-v2", + "name": "Titan Text Embeddings V2", + "family": "titan-embed", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-04", + "last_updated": "2024-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.02, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/anthropic/claude-3-haiku", + "name": "Claude Haiku 3", + "family": "claude-haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-08-31", + "release_date": "2024-03-13", + "last_updated": "2024-03-13", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.25, + "cache_read": 0.03, + "cache_write": 0.3 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "vercel/anthropic/claude-3-opus", + "name": "Claude Opus 3", + "family": "claude-opus", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-08-31", + "release_date": "2024-02-29", + "last_updated": "2024-02-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 4096 + } + }, + { + "id": "vercel/anthropic/claude-3.5-haiku", + "name": "Claude Haiku 3.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07-31", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 4.0, + "cache_read": 0.08, + "cache_write": 1.0 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "vercel/anthropic/claude-3.5-sonnet", + "name": "Claude Sonnet 3.5 v2", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04-30", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 8192 + } + }, + { + "id": "vercel/anthropic/claude-3.7-sonnet", + "name": "Claude Sonnet 3.7", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10-31", + "release_date": "2025-02-19", + "last_updated": "2025-02-19", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "vercel/anthropic/claude-haiku-4.5", + "name": "Claude Haiku 4.5", + "family": "claude-haiku", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02-28", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "vercel/anthropic/claude-opus-4", + "name": "Claude Opus 4", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "vercel/anthropic/claude-opus-4.1", + "name": "Claude Opus 4", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + } + }, + { + "id": "vercel/anthropic/claude-opus-4.5", + "name": "Claude Opus 4.5", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-11-24", + "last_updated": "2025-11-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "vercel/anthropic/claude-opus-4.6", + "name": "Claude Opus 4.6", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-02", + "last_updated": "2026-02", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "vercel/anthropic/claude-sonnet-4", + "name": "Claude Sonnet 4", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03-31", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "vercel/anthropic/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07-31", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "vercel/anthropic/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2026-02-17", + "last_updated": "2026-02-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "vercel/arcee-ai/trinity-large-preview", + "name": "Trinity Large Preview", + "family": "trinity", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-01", + "last_updated": "2025-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.0 + }, + "limit": { + "context": 131000, + "output": 131000 + } + }, + { + "id": "vercel/arcee-ai/trinity-mini", + "name": "Trinity Mini", + "family": "trinity", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-12", + "last_updated": "2025-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.15 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "vercel/bfl/flux-kontext-max", + "name": "FLUX.1 Kontext Max", + "family": "flux", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-06", + "last_updated": "2025-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 512, + "output": 0 + } + }, + { + "id": "vercel/bfl/flux-kontext-pro", + "name": "FLUX.1 Kontext Pro", + "family": "flux", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-06", + "last_updated": "2025-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 512, + "output": 0 + } + }, + { + "id": "vercel/bfl/flux-pro-1.0-fill", + "name": "FLUX.1 Fill [pro]", + "family": "flux", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-10", + "last_updated": "2024-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 512, + "output": 0 + } + }, + { + "id": "vercel/bfl/flux-pro-1.1", + "name": "FLUX1.1 [pro]", + "family": "flux", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-10", + "last_updated": "2024-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 512, + "output": 0 + } + }, + { + "id": "vercel/bfl/flux-pro-1.1-ultra", + "name": "FLUX1.1 [pro] Ultra", + "family": "flux", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-11", + "last_updated": "2024-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 512, + "output": 0 + } + }, + { + "id": "vercel/bytedance/seed-1.6", + "name": "Seed 1.6", + "family": "seed", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09", + "last_updated": "2025-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.05 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "vercel/bytedance/seed-1.8", + "name": "Seed 1.8", + "family": "seed", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-10", + "last_updated": "2025-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.05 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "vercel/cohere/command-a", + "name": "Command A", + "family": "command", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-03-13", + "last_updated": "2025-03-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0 + }, + "limit": { + "context": 256000, + "output": 8000 + } + }, + { + "id": "vercel/cohere/embed-v4.0", + "name": "Embed v4.0", + "family": "cohere-embed", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-04-15", + "last_updated": "2025-04-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.12, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/deepseek/deepseek-r1", + "name": "DeepSeek-R1", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-01-20", + "last_updated": "2025-05-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.35, + "output": 5.4 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "vercel/deepseek/deepseek-v3", + "name": "DeepSeek V3 0324", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-12-26", + "last_updated": "2024-12-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.77, + "output": 0.77 + }, + "limit": { + "context": 163840, + "output": 16384 + } + }, + { + "id": "vercel/deepseek/deepseek-v3.1", + "name": "DeepSeek-V3.1", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-08-21", + "last_updated": "2025-08-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.0 + }, + "limit": { + "context": 163840, + "output": 128000 + } + }, + { + "id": "vercel/deepseek/deepseek-v3.1-terminus", + "name": "DeepSeek V3.1 Terminus", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-09-22", + "last_updated": "2025-09-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.0 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "vercel/deepseek/deepseek-v3.2", + "name": "DeepSeek V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.4, + "cache_read": 0.22 + }, + "limit": { + "context": 163842, + "output": 8000 + } + }, + { + "id": "vercel/deepseek/deepseek-v3.2-exp", + "name": "DeepSeek V3.2 Exp", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.27, + "output": 0.4 + }, + "limit": { + "context": 163840, + "output": 163840 + } + }, + { + "id": "vercel/deepseek/deepseek-v3.2-thinking", + "name": "DeepSeek V3.2 Thinking", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.28, + "output": 0.42, + "cache_read": 0.03 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "vercel/google/gemini-2.0-flash", + "name": "Gemini 2.0 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.025 + }, + "limit": { + "context": 1048576, + "output": 8192 + } + }, + { + "id": "vercel/google/gemini-2.0-flash-lite", + "name": "Gemini 2.0 Flash Lite", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-06", + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.075, + "output": 0.3 + }, + "limit": { + "context": 1048576, + "output": 8192 + } + }, + { + "id": "vercel/google/gemini-2.5-flash", + "name": "Gemini 2.5 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-20", + "last_updated": "2025-06-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.075 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "vercel/google/gemini-2.5-flash-image", + "name": "Nano Banana (Gemini 2.5 Flash Image)", + "family": "gemini-flash", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-20", + "last_updated": "2025-03-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "vercel/google/gemini-2.5-flash-image-preview", + "name": "Nano Banana Preview (Gemini 2.5 Flash Image Preview)", + "family": "gemini-flash", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-20", + "last_updated": "2025-03-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5 + }, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "vercel/google/gemini-2.5-flash-lite", + "name": "Gemini 2.5 Flash Lite", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "vercel/google/gemini-2.5-flash-lite-preview-09", + "name": "Gemini 2.5 Flash Lite Preview 09-25", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-09-25", + "last_updated": "2025-09-25", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "vercel/google/gemini-2.5-flash-preview-09", + "name": "Gemini 2.5 Flash Preview 09-25", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-09-25", + "last_updated": "2025-09-25", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.03, + "cache_write": 0.383 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "vercel/google/gemini-2.5-pro", + "name": "Gemini 2.5 Pro", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-03-20", + "last_updated": "2025-06-05", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.31 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "vercel/google/gemini-3-flash", + "name": "Gemini 3 Flash", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "vercel/google/gemini-3-pro-image", + "name": "Nano Banana Pro (Gemini 3 Pro Image)", + "family": "gemini-pro", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2025-09", + "last_updated": "2025-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 120.0 + }, + "limit": { + "context": 65536, + "output": 32768 + } + }, + { + "id": "vercel/google/gemini-3-pro-preview", + "name": "Gemini 3 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "vercel/google/gemini-embedding-001", + "name": "Gemini Embedding 001", + "family": "gemini-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-05-20", + "last_updated": "2025-05-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/google/imagen-4.0-fast-generate-001", + "name": "Imagen 4 Fast", + "family": "imagen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-06", + "last_updated": "2025-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "vercel/google/imagen-4.0-generate-001", + "name": "Imagen 4", + "family": "imagen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "vercel/google/imagen-4.0-ultra-generate-001", + "name": "Imagen 4 Ultra", + "family": "imagen", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-05-24", + "last_updated": "2025-05-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 480, + "output": 0 + } + }, + { + "id": "vercel/google/text-embedding-005", + "name": "Text Embedding 005", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-08", + "last_updated": "2024-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.03, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/google/text-multilingual-embedding-002", + "name": "Text Multilingual Embedding 002", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-03", + "last_updated": "2024-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.03, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/inception/mercury-coder-small", + "name": "Mercury Coder Small Beta", + "family": "mercury", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-02-26", + "last_updated": "2025-02-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.0 + }, + "limit": { + "context": 32000, + "output": 16384 + } + }, + { + "id": "vercel/kwaipilot/kat-coder-pro-v1", + "name": "KAT-Coder-Pro V1", + "family": "kat-coder", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-10-24", + "last_updated": "2025-10-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "vercel/meituan/longcat-flash-chat", + "name": "LongCat Flash Chat", + "family": "longcat", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-30", + "last_updated": "2025-08-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "vercel/meituan/longcat-flash-thinking", + "name": "LongCat Flash Thinking", + "family": "longcat", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 1.5 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "vercel/meta/llama-3.1-70b", + "name": "Llama 3.1 70B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 0.4 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "vercel/meta/llama-3.1-8b", + "name": "Llama 3.1 8B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.03, + "output": 0.05 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "vercel/meta/llama-3.2-11b", + "name": "Llama 3.2 11B Vision Instruct", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-09-25", + "last_updated": "2024-09-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.16, + "output": 0.16 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "vercel/meta/llama-3.2-1b", + "name": "Llama 3.2 1B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-09-18", + "last_updated": "2024-09-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "vercel/meta/llama-3.2-3b", + "name": "Llama 3.2 3B Instruct", + "family": "llama", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-09-18", + "last_updated": "2024-09-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.15 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "vercel/meta/llama-3.2-90b", + "name": "Llama 3.2 90B Vision Instruct", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-09-25", + "last_updated": "2024-09-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.72, + "output": 0.72 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "vercel/meta/llama-3.3-70b", + "name": "Llama-3.3-70B-Instruct", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "vercel/meta/llama-4-maverick", + "name": "Llama-4-Maverick-17B-128E-Instruct-FP8", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "vercel/meta/llama-4-scout", + "name": "Llama-4-Scout-17B-16E-Instruct-FP8", + "family": "llama", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-04-05", + "last_updated": "2025-04-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "vercel/minimax/minimax-m2", + "name": "MiniMax M2", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.27, + "output": 1.15, + "cache_read": 0.03, + "cache_write": 0.38 + }, + "limit": { + "context": 262114, + "output": 262114 + } + }, + { + "id": "vercel/minimax/minimax-m2.1", + "name": "MiniMax M2.1", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03, + "cache_write": 0.38 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "vercel/minimax/minimax-m2.1-lightning", + "name": "MiniMax M2.1 Lightning", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.4, + "cache_read": 0.03, + "cache_write": 0.38 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "vercel/minimax/minimax-m2.5", + "name": "MiniMax M2.5", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03, + "cache_write": 0.375 + }, + "limit": { + "context": 204800, + "output": 131000 + } + }, + { + "id": "vercel/mistral/codestral", + "name": "Codestral", + "family": "codestral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-05-29", + "last_updated": "2025-01-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 256000, + "output": 4096 + } + }, + { + "id": "vercel/mistral/codestral-embed", + "name": "Codestral Embed", + "family": "codestral-embed", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-05-28", + "last_updated": "2025-05-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/mistral/devstral-2", + "name": "Devstral 2", + "family": "devstral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-12-09", + "last_updated": "2025-12-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "vercel/mistral/devstral-small", + "name": "Devstral Small 1.1", + "family": "devstral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-05-07", + "last_updated": "2025-05-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "vercel/mistral/devstral-small-2", + "name": "Devstral Small 2", + "family": "devstral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-05-07", + "last_updated": "2025-05-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "vercel/mistral/magistral-medium", + "name": "Magistral Medium", + "family": "magistral-medium", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-03-17", + "last_updated": "2025-03-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 5.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "vercel/mistral/magistral-small", + "name": "Magistral Small", + "family": "magistral-small", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2025-03-17", + "last_updated": "2025-03-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.5, + "output": 1.5 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "vercel/mistral/ministral-14b", + "name": "Ministral 14B", + "family": "ministral", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "vercel/mistral/ministral-3b", + "name": "Ministral 3B", + "family": "ministral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-10-01", + "last_updated": "2024-10-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.04, + "output": 0.04 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "vercel/mistral/ministral-8b", + "name": "Ministral 8B", + "family": "ministral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-10-01", + "last_updated": "2024-10-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "vercel/mistral/mistral-embed", + "name": "Mistral Embed", + "family": "mistral-embed", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2023-12-11", + "last_updated": "2023-12-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/mistral/mistral-large-3", + "name": "Mistral Large 3", + "family": "mistral-large", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-12-02", + "last_updated": "2025-12-02", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.5 + }, + "limit": { + "context": 256000, + "output": 256000 + } + }, + { + "id": "vercel/mistral/mistral-medium", + "name": "Mistral Medium 3.1", + "family": "mistral-medium", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-05-07", + "last_updated": "2025-05-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.0 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "vercel/mistral/mistral-nemo", + "name": "Mistral Nemo", + "family": "mistral-nemo", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-07-01", + "last_updated": "2024-07-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.04, + "output": 0.17 + }, + "limit": { + "context": 60288, + "output": 16000 + } + }, + { + "id": "vercel/mistral/mistral-small", + "name": "Mistral Small", + "family": "mistral-small", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-03", + "release_date": "2024-09-01", + "last_updated": "2024-09-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "vercel/mistral/mixtral-8x22b-instruct", + "name": "Mixtral 8x22B", + "family": "mixtral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-04-17", + "last_updated": "2024-04-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 6.0 + }, + "limit": { + "context": 64000, + "output": 64000 + } + }, + { + "id": "vercel/mistral/pixtral-12b", + "name": "Pixtral 12B", + "family": "pixtral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2024-09-01", + "last_updated": "2024-09-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.15, + "output": 0.15 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "vercel/mistral/pixtral-large", + "name": "Pixtral Large", + "family": "pixtral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2024-11-01", + "last_updated": "2024-11-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 2.0, + "output": 6.0 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "vercel/moonshotai/kimi-k2", + "name": "Kimi K2 Instruct", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-14", + "last_updated": "2025-07-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.0 + }, + "limit": { + "context": 131072, + "output": 16384 + } + }, + { + "id": "vercel/moonshotai/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.47, + "output": 2.0, + "cache_read": 0.14 + }, + "limit": { + "context": 216144, + "output": 216144 + } + }, + { + "id": "vercel/moonshotai/kimi-k2-thinking-turbo", + "name": "Kimi K2 Thinking Turbo", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.15, + "output": 8.0, + "cache_read": 0.15 + }, + "limit": { + "context": 262114, + "output": 262114 + } + }, + { + "id": "vercel/moonshotai/kimi-k2-turbo", + "name": "Kimi K2 Turbo", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2025-09-05", + "last_updated": "2025-09-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.4, + "output": 10.0 + }, + "limit": { + "context": 256000, + "output": 16384 + } + }, + { + "id": "vercel/moonshotai/kimi-k2.5", + "name": "Kimi K2.5", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-01-26", + "last_updated": "2026-01-26", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.2 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "vercel/morph/morph-v3-fast", + "name": "Morph v3 Fast", + "family": "morph", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-08-15", + "last_updated": "2024-08-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 1.2 + }, + "limit": { + "context": 16000, + "output": 16000 + } + }, + { + "id": "vercel/morph/morph-v3-large", + "name": "Morph v3 Large", + "family": "morph", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-08-15", + "last_updated": "2024-08-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.9, + "output": 1.9 + }, + "limit": { + "context": 32000, + "output": 32000 + } + }, + { + "id": "vercel/nvidia/nemotron-3-nano-30b-a3b", + "name": "Nemotron 3 Nano 30B A3B", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12", + "last_updated": "2024-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.06, + "output": 0.24 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "vercel/nvidia/nemotron-nano-12b-v2-vl", + "name": "Nvidia Nemotron Nano 12B V2 VL", + "family": "nemotron", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12", + "last_updated": "2024-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.6 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "vercel/nvidia/nemotron-nano-9b-v2", + "name": "Nvidia Nemotron Nano 9B V2", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-18", + "last_updated": "2025-08-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.04, + "output": 0.16 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "vercel/openai/codex-mini", + "name": "Codex Mini", + "family": "gpt-codex-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-05-16", + "last_updated": "2025-05-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 6.0, + "cache_read": 0.38 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "vercel/openai/gpt-3.5-turbo", + "name": "GPT-3.5 Turbo", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2021-09", + "release_date": "2023-03-01", + "last_updated": "2023-03-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 1.5 + }, + "limit": { + "context": 16385, + "output": 4096 + } + }, + { + "id": "vercel/openai/gpt-3.5-turbo-instruct", + "name": "GPT-3.5 Turbo Instruct", + "family": "gpt", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2021-09", + "release_date": "2023-03-01", + "last_updated": "2023-03-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 2.0 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, + { + "id": "vercel/openai/gpt-4-turbo", + "name": "GPT-4 Turbo", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2023-11-06", + "last_updated": "2024-04-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 30.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "vercel/openai/gpt-4.1", + "name": "GPT-4.1", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "vercel/openai/gpt-4.1-mini", + "name": "GPT-4.1 mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 1.6, + "cache_read": 0.1 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "vercel/openai/gpt-4.1-nano", + "name": "GPT-4.1 nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.03 + }, + "limit": { + "context": 1047576, + "output": 32768 + } + }, + { + "id": "vercel/openai/gpt-4o", + "name": "GPT-4o", + "family": "gpt", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-05-13", + "last_updated": "2024-08-06", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 10.0, + "cache_read": 1.25 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "vercel/openai/gpt-4o-mini", + "name": "GPT-4o mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6, + "cache_read": 0.08 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "vercel/openai/gpt-4o-mini-search-preview", + "name": "GPT 4o Mini Search Preview", + "family": "gpt-mini", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2023-09", + "release_date": "2025-01", + "last_updated": "2025-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.15, + "output": 0.6 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "vercel/openai/gpt-5", + "name": "GPT-5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5-chat", + "name": "GPT-5 Chat", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "vercel/openai/gpt-5-codex", + "name": "GPT-5-Codex", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-09-15", + "last_updated": "2025-09-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5-mini", + "name": "GPT-5 Mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.025 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5-nano", + "name": "GPT-5 Nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.05, + "output": 0.4, + "cache_read": 0.005 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5-pro", + "name": "GPT-5 pro", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 120.0 + }, + "limit": { + "context": 400000, + "output": 272000 + } + }, + { + "id": "vercel/openai/gpt-5.1-codex", + "name": "GPT-5.1-Codex", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5.1-codex-max", + "name": "GPT 5.1 Codex Max", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5.1-codex-mini", + "name": "GPT-5.1 Codex mini", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-05-16", + "last_updated": "2025-05-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.03 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5.1-instant", + "name": "GPT-5.1 Instant", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "vercel/openai/gpt-5.1-thinking", + "name": "GPT 5.1 Thinking", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-10", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.13 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5.2", + "name": "GPT-5.2", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.18 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5.2-chat", + "name": "GPT-5.2 Chat", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.18 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, + { + "id": "vercel/openai/gpt-5.2-codex", + "name": "GPT-5.2-Codex", + "family": "gpt-codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-12", + "last_updated": "2025-12", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-5.2-pro", + "name": "GPT 5.2 ", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 21.0, + "output": 168.0 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vercel/openai/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.5 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "vercel/openai/gpt-oss-20b", + "name": "GPT OSS 20B", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.3 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "vercel/openai/gpt-oss-safeguard-20b", + "name": "gpt-oss-safeguard-20b", + "family": "gpt-oss", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-12-01", + "last_updated": "2024-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.08, + "output": 0.3, + "cache_read": 0.04 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, + { + "id": "vercel/openai/o1", + "name": "o1", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2023-09", + "release_date": "2024-12-05", + "last_updated": "2024-12-05", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 60.0, + "cache_read": 7.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "vercel/openai/o3", + "name": "o3", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0, + "cache_read": 0.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "vercel/openai/o3-deep-research", + "name": "o3-deep-research", + "family": "o", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-10", + "release_date": "2024-06-26", + "last_updated": "2024-06-26", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 10.0, + "output": 40.0, + "cache_read": 2.5 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "vercel/openai/o3-mini", + "name": "o3-mini", + "family": "o-mini", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2024-12-20", + "last_updated": "2025-01-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.55 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "vercel/openai/o3-pro", + "name": "o3 Pro", + "family": "o-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-10", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 20.0, + "output": 80.0 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "vercel/openai/o4-mini", + "name": "o4-mini", + "family": "o-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05", + "release_date": "2025-04-16", + "last_updated": "2025-04-16", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.1, + "output": 4.4, + "cache_read": 0.28 + }, + "limit": { + "context": 200000, + "output": 100000 + } + }, + { + "id": "vercel/openai/text-embedding-3-large", + "name": "text-embedding-3-large", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-01-25", + "last_updated": "2024-01-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.13, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/openai/text-embedding-3-small", + "name": "text-embedding-3-small", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-01-25", + "last_updated": "2024-01-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.02, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/openai/text-embedding-ada-002", + "name": "text-embedding-ada-002", + "family": "text-embedding", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2022-12-15", + "last_updated": "2022-12-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/perplexity/sonar", + "name": "Sonar", + "family": "sonar", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-02", + "release_date": "2025-02-19", + "last_updated": "2025-02-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 1.0 + }, + "limit": { + "context": 127000, + "output": 8000 + } + }, + { + "id": "vercel/perplexity/sonar-pro", + "name": "Sonar Pro", + "family": "sonar-pro", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-02-19", + "last_updated": "2025-02-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 200000, + "output": 8000 + } + }, + { + "id": "vercel/perplexity/sonar-reasoning-pro", + "name": "Sonar Reasoning Pro", + "family": "sonar-reasoning", + "attachment": false, + "reasoning": true, + "tool_call": false, + "temperature": true, + "knowledge": "2025-09", + "release_date": "2025-02-19", + "last_updated": "2025-02-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 8.0 + }, + "limit": { + "context": 127000, + "output": 8000 + } + }, + { + "id": "vercel/prime-intellect/intellect-3", + "name": "INTELLECT 3", + "family": "intellect", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-11-26", + "last_updated": "2025-11-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.1 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "vercel/recraft/recraft-v2", + "name": "Recraft V2", + "family": "recraft", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-03", + "last_updated": "2024-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 512, + "output": 0 + } + }, + { + "id": "vercel/recraft/recraft-v3", + "name": "Recraft V3", + "family": "recraft", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-10", + "last_updated": "2024-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 512, + "output": 0 + } + }, + { + "id": "vercel/vercel/v0-1.0-md", + "name": "v0-1.0-md", + "family": "v0", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "vercel/vercel/v0-1.5-md", + "name": "v0-1.5-md", + "family": "v0", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-06-09", + "last_updated": "2025-06-09", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0 + }, + "limit": { + "context": 128000, + "output": 32000 + } + }, + { + "id": "vercel/voyage/voyage-3-large", + "name": "voyage-3-large", + "family": "voyage", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/voyage/voyage-3.5", + "name": "voyage-3.5", + "family": "voyage", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-05-20", + "last_updated": "2025-05-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.06, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/voyage/voyage-3.5-lite", + "name": "voyage-3.5-lite", + "family": "voyage", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-05-20", + "last_updated": "2025-05-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.02, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/voyage/voyage-code-2", + "name": "voyage-code-2", + "family": "voyage", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-01", + "last_updated": "2024-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.12, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/voyage/voyage-code-3", + "name": "voyage-code-3", + "family": "voyage", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-09", + "last_updated": "2024-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.18, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/voyage/voyage-finance-2", + "name": "voyage-finance-2", + "family": "voyage", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-03", + "last_updated": "2024-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.12, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/voyage/voyage-law-2", + "name": "voyage-law-2", + "family": "voyage", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-03", + "last_updated": "2024-03", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.12, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1536 + } + }, + { + "id": "vercel/xai/grok-2-vision", + "name": "Grok 2 Vision", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-08", + "release_date": "2024-08-20", + "last_updated": "2024-08-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 10.0, + "cache_read": 2.0 + }, + "limit": { + "context": 8192, + "output": 4096 + } + }, + { + "id": "vercel/xai/grok-3", + "name": "Grok 3", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2025-02-17", + "last_updated": "2025-02-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "vercel/xai/grok-3-fast", + "name": "Grok 3 Fast", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2025-02-17", + "last_updated": "2025-02-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 1.25 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "vercel/xai/grok-3-mini", + "name": "Grok 3 Mini", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2025-02-17", + "last_updated": "2025-02-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.5, + "cache_read": 0.075 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "vercel/xai/grok-3-mini-fast", + "name": "Grok 3 Mini Fast", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2025-02-17", + "last_updated": "2025-02-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 4.0, + "cache_read": 0.15 + }, + "limit": { + "context": 131072, + "output": 8192 + } + }, + { + "id": "vercel/xai/grok-4", + "name": "Grok 4", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "vercel/xai/grok-4-fast", + "name": "Grok 4 Fast Reasoning", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 256000 + } + }, + { + "id": "vercel/xai/grok-4-fast-non", + "name": "Grok 4 Fast (Non-Reasoning)", + "family": "grok", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-09-19", + "last_updated": "2025-09-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "vercel/xai/grok-4.1-fast", + "name": "Grok 4.1 Fast Reasoning", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "vercel/xai/grok-4.1-fast-non", + "name": "Grok 4.1 Fast Non-Reasoning", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 30000 + } + }, + { + "id": "vercel/xai/grok-code-fast-1", + "name": "Grok Code Fast 1", + "family": "grok", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2025-08-28", + "last_updated": "2025-08-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.5, + "cache_read": 0.02 + }, + "limit": { + "context": 256000, + "output": 10000 + } + }, + { + "id": "vercel/xai/grok-imagine-image", + "name": "Grok Imagine Image", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-01-28", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "vercel/xai/grok-imagine-image-pro", + "name": "Grok Imagine Image Pro", + "family": "grok", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-01-28", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text", + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "vercel/xiaomi/mimo-v2-flash", + "name": "MiMo V2 Flash", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.29 + }, + "limit": { + "context": 262144, + "output": 32000 + } + }, + { + "id": "vercel/zai/glm-4.5", + "name": "GLM 4.5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "vercel/zai/glm-4.5-air", + "name": "GLM 4.5 Air", + "family": "glm-air", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.1 + }, + "limit": { + "context": 128000, + "output": 96000 + } + }, + { + "id": "vercel/zai/glm-4.5v", + "name": "GLM 4.5V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08", + "release_date": "2025-08-11", + "last_updated": "2025-08-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.8 + }, + "limit": { + "context": 66000, + "output": 66000 + } + }, + { + "id": "vercel/zai/glm-4.6", + "name": "GLM 4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.45, + "output": 1.8 + }, + "limit": { + "context": 200000, + "output": 96000 + } + }, + { + "id": "vercel/zai/glm-4.6v", + "name": "GLM-4.6V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 0.9, + "cache_read": 0.05 + }, + "limit": { + "context": 128000, + "output": 24000 + } + }, + { + "id": "vercel/zai/glm-4.6v-flash", + "name": "GLM-4.6V-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 128000, + "output": 24000 + } + }, + { + "id": "vercel/zai/glm-4.7", + "name": "GLM 4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.43, + "output": 1.75, + "cache_read": 0.08 + }, + "limit": { + "context": 202752, + "output": 120000 + } + }, + { + "id": "vercel/zai/glm-4.7-flashx", + "name": "GLM 4.7 FlashX", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01", + "last_updated": "2025-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.06, + "output": 0.4, + "cache_read": 0.01 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "vercel/zai/glm-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.2 + }, + "limit": { + "context": 202800, + "output": 131072 + } + }, + { + "id": "vivgrid/deepseek-v3.2", + "name": "DeepSeek-V3.2", + "family": "deepseek", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.28, + "output": 0.42 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, + { + "id": "vivgrid/gemini-3-flash-preview", + "name": "Gemini 3 Flash Preview", + "family": "gemini-flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "vivgrid/gemini-3-pro-preview", + "name": "Gemini 3 Pro Preview", + "family": "gemini-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "vivgrid/glm-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.2 + }, + "limit": { + "context": 202752, + "output": 131000 + } + }, + { + "id": "vivgrid/gpt-5-mini", + "name": "GPT-5 Mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-05-30", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.03 + }, + "limit": { + "context": 272000, + "output": 128000 + } + }, + { + "id": "vivgrid/gpt-5.1-codex", + "name": "GPT-5.1 Codex", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vivgrid/gpt-5.1-codex-max", + "name": "GPT-5.1 Codex Max", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2024-09-30", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.125 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vivgrid/gpt-5.2-codex", + "name": "GPT-5.2 Codex", + "family": "gpt-codex", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-01-14", + "last_updated": "2026-01-14", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.175 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "vultr/deepseek-r1-distill-llama-70b", + "name": "DeepSeek R1 Distill Llama 70B", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 121808, + "output": 8192 + } + }, + { + "id": "vultr/deepseek-r1-distill-qwen-32b", + "name": "DeepSeek R1 Distill Qwen 32B", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-01-20", + "last_updated": "2025-01-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 121808, + "output": 8192 + } + }, + { + "id": "vultr/gpt-oss-120b", + "name": "GPT OSS 120B", + "family": "gpt-oss", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-06-23", + "last_updated": "2025-06-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 121808, + "output": 8192 + } + }, + { + "id": "vultr/kimi-k2-instruct", + "name": "Kimi K2 Instruct", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-07-18", + "last_updated": "2024-07-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 58904, + "output": 4096 + } + }, + { + "id": "vultr/qwen2.5-coder-32b-instruct", + "name": "Qwen2.5 Coder 32B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2024-11-06", + "last_updated": "2024-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 12952, + "output": 2048 + } + }, + { + "id": "wandb/Qwen/Qwen3-235B-A22B-Instruct", + "name": "Qwen3 235B A22B Instruct 2507", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-04-28", + "last_updated": "2025-07-21", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "wandb/Qwen/Qwen3-235B-A22B-Thinking", + "name": "Qwen3-235B-A22B-Thinking-2507", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct", + "name": "Qwen3-Coder-480B-A35B-Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 1.5 + }, + "limit": { + "context": 262144, + "output": 66536 + } + }, + { + "id": "wandb/deepseek-ai/DeepSeek-R1", + "name": "DeepSeek-R1-0528", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2025-05-28", + "last_updated": "2025-05-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.35, + "output": 5.4 + }, + "limit": { + "context": 161000, + "output": 163840 + } + }, + { + "id": "wandb/deepseek-ai/DeepSeek-V3", + "name": "DeepSeek-V3-0324", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-03-24", + "last_updated": "2025-03-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.14, + "output": 2.75 + }, + "limit": { + "context": 161000, + "output": 8192 + } + }, + { + "id": "wandb/meta-llama/Llama-3.1-8B-Instruct", + "name": "Meta-Llama-3.1-8B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.22, + "output": 0.22 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "wandb/meta-llama/Llama-3.3-70B-Instruct", + "name": "Llama-3.3-70B-Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "release_date": "2024-12-06", + "last_updated": "2024-12-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.71, + "output": 0.71 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct", + "name": "Llama 4 Scout 17B 16E Instruct", + "family": "llama", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2025-01-31", + "last_updated": "2025-01-31", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.17, + "output": 0.66 + }, + "limit": { + "context": 64000, + "output": 8192 + } + }, + { + "id": "wandb/microsoft/Phi-4-mini-instruct", + "name": "Phi-4-mini-instruct", + "family": "phi", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-10", + "release_date": "2024-12-11", + "last_updated": "2024-12-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.35 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "wandb/moonshotai/Kimi-K2-Instruct", + "name": "Kimi-K2-Instruct", + "family": "kimi", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-10", + "release_date": "2025-07-14", + "last_updated": "2025-07-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.35, + "output": 4.0 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, { "id": "x-ai/grok-2", - "name": "Grok 2 Latest", + "name": "Grok 2 (1212)", "family": "grok", "attachment": false, "reasoning": false, "tool_call": true, "temperature": true, "knowledge": "2024-08", - "release_date": "2024-08-20", + "release_date": "2024-12-12", "last_updated": "2024-12-12", "modalities": { "input": [ @@ -15924,7 +83099,7 @@ }, { "id": "x-ai/grok-3-fast", - "name": "Grok 3 Fast", + "name": "Grok 3 Fast Latest", "family": "grok", "attachment": false, "reasoning": false, @@ -15954,7 +83129,7 @@ }, { "id": "x-ai/grok-3-mini", - "name": "Grok 3 Mini", + "name": "Grok 3 Mini Latest", "family": "grok", "attachment": false, "reasoning": true, @@ -15984,7 +83159,7 @@ }, { "id": "x-ai/grok-3-mini-fast", - "name": "Grok 3 Mini Fast Latest", + "name": "Grok 3 Mini Fast", "family": "grok", "attachment": false, "reasoning": true, @@ -16256,5 +83431,3206 @@ "context": 8192, "output": 4096 } + }, + { + "id": "xiaomi/mimo-v2-flash", + "name": "MiMo-V2-Flash", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.21 + }, + "limit": { + "context": 256000, + "output": 32000 + } + }, + { + "id": "zai-coding-plan/glm-4.5", + "name": "GLM-4.5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zai-coding-plan/glm-4.5-air", + "name": "GLM-4.5-Air", + "family": "glm-air", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zai-coding-plan/glm-4.5-flash", + "name": "GLM-4.5-Flash", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zai-coding-plan/glm-4.5v", + "name": "GLM-4.5V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-08-11", + "last_updated": "2025-08-11", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 64000, + "output": 16384 + } + }, + { + "id": "zai-coding-plan/glm-4.6", + "name": "GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zai-coding-plan/glm-4.6v", + "name": "GLM-4.6V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "zai-coding-plan/glm-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zai-coding-plan/glm-4.7-flash", + "name": "GLM-4.7-Flash", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 200000, + "output": 131072 + } + }, + { + "id": "zai-coding-plan/glm-4.7-flashx", + "name": "GLM-4.7-FlashX", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.07, + "output": 0.4, + "cache_read": 0.01, + "cache_write": 0.0 + }, + "limit": { + "context": 200000, + "output": 131072 + } + }, + { + "id": "zai-coding-plan/glm-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zai/glm-4.5", + "name": "GLM-4.5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zai/glm-4.5-air", + "name": "GLM-4.5-Air", + "family": "glm-air", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.1, + "cache_read": 0.03, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zai/glm-4.5-flash", + "name": "GLM-4.5-Flash", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zai/glm-4.5v", + "name": "GLM-4.5V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-08-11", + "last_updated": "2025-08-11", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.8 + }, + "limit": { + "context": 64000, + "output": 16384 + } + }, + { + "id": "zai/glm-4.6", + "name": "GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zai/glm-4.6v", + "name": "GLM-4.6V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "zai/glm-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zai/glm-4.7-flash", + "name": "GLM-4.7-Flash", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 200000, + "output": 131072 + } + }, + { + "id": "zai/glm-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.2, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zenmux/anthropic/claude-3.5-haiku", + "name": "Claude 3.5 Haiku", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2024-11-04", + "last_updated": "2024-11-04", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.8, + "output": 4.0, + "cache_read": 0.08, + "cache_write": 1.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/anthropic/claude-3.5-sonnet", + "name": "Claude 3.5 Sonnet (Retiring Soon)", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2024-10-22", + "last_updated": "2024-10-22", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/anthropic/claude-3.7-sonnet", + "name": "Claude 3.7 Sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-02-24", + "last_updated": "2025-02-24", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/anthropic/claude-haiku-4.5", + "name": "Claude Haiku 4.5", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-10-15", + "last_updated": "2025-10-15", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/anthropic/claude-opus-4", + "name": "Claude Opus 4", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "image", + "text", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/anthropic/claude-opus-4.1", + "name": "Claude Opus 4.1", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-08-05", + "last_updated": "2025-08-05", + "modalities": { + "input": [ + "image", + "text", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 15.0, + "output": 75.0, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/anthropic/claude-opus-4.5", + "name": "Claude Opus 4.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-11-24", + "last_updated": "2025-11-24", + "modalities": { + "input": [ + "pdf", + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/anthropic/claude-opus-4.6", + "name": "Claude Opus 4.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-02-06", + "last_updated": "2026-02-06", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + } + }, + { + "id": "zenmux/anthropic/claude-sonnet-4", + "name": "Claude Sonnet 4", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-05-22", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "image", + "text", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "zenmux/anthropic/claude-sonnet-4.5", + "name": "Claude Sonnet 4.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "zenmux/anthropic/claude-sonnet-4.6", + "name": "Claude Sonnet 4.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-02-18", + "last_updated": "2026-02-18", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "zenmux/baidu/ernie-5.0-thinking-preview", + "name": "ERNIE 5.0", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-01-22", + "last_updated": "2026-01-22", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.84, + "output": 3.37 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "zenmux/deepseek/deepseek-chat", + "name": "DeepSeek-V3.2 (Non-thinking Mode)", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-12-01", + "last_updated": "2025-12-01", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.28, + "output": 0.42, + "cache_read": 0.03 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "zenmux/deepseek/deepseek-v3.2", + "name": "DeepSeek V3.2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-12-05", + "last_updated": "2025-12-05", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.28, + "output": 0.43 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "zenmux/deepseek/deepseek-v3.2-exp", + "name": "DeepSeek-V3.2-Exp", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-09-29", + "last_updated": "2025-09-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.22, + "output": 0.33 + }, + "limit": { + "context": 163000, + "output": 64000 + } + }, + { + "id": "zenmux/google/gemini-2.5-flash", + "name": "Gemini 2.5 Flash", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "pdf", + "image", + "text", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 2.5, + "cache_read": 0.07, + "cache_write": 1.0 + }, + "limit": { + "context": 1048000, + "output": 64000 + } + }, + { + "id": "zenmux/google/gemini-2.5-flash-lite", + "name": "Gemini 2.5 Flash Lite", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-07-22", + "last_updated": "2025-07-22", + "modalities": { + "input": [ + "pdf", + "image", + "text", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.4, + "cache_read": 0.03, + "cache_write": 1.0 + }, + "limit": { + "context": 1048000, + "output": 64000 + } + }, + { + "id": "zenmux/google/gemini-2.5-pro", + "name": "Gemini 2.5 Pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-06-17", + "last_updated": "2025-06-17", + "modalities": { + "input": [ + "pdf", + "image", + "text", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.31, + "cache_write": 4.5 + }, + "limit": { + "context": 1048000, + "output": 64000 + } + }, + { + "id": "zenmux/google/gemini-3-flash-preview", + "name": "Gemini 3 Flash Preview", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text", + "image", + "pdf", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.05, + "cache_write": 1.0 + }, + "limit": { + "context": 1048000, + "output": 64000 + } + }, + { + "id": "zenmux/google/gemini-3-pro-preview", + "name": "Gemini 3 Pro Preview", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-11-18", + "last_updated": "2025-11-18", + "modalities": { + "input": [ + "text", + "image", + "pdf", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.0, + "output": 12.0, + "cache_read": 0.2, + "cache_write": 4.5 + }, + "limit": { + "context": 1048000, + "output": 64000 + } + }, + { + "id": "zenmux/inclusionai/ling-1t", + "name": "Ling-1T", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-10-09", + "last_updated": "2025-10-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.56, + "output": 2.24, + "cache_read": 0.11 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "zenmux/inclusionai/ring-1t", + "name": "Ring-1T", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-10-12", + "last_updated": "2025-10-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.56, + "output": 2.24, + "cache_read": 0.11 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "zenmux/kuaishou/kat-coder-pro-v1", + "name": "KAT-Coder-Pro-V1", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-10-23", + "last_updated": "2025-10-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.06 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/kuaishou/kat-coder-pro-v1-free", + "name": "KAT-Coder-Pro-V1 Free", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-10-23", + "last_updated": "2025-10-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/minimax/minimax-m2", + "name": "MiniMax M2", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-10-27", + "last_updated": "2025-10-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03, + "cache_write": 0.38 + }, + "limit": { + "context": 204000, + "output": 64000 + } + }, + { + "id": "zenmux/minimax/minimax-m2.1", + "name": "MiniMax M2.1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03, + "cache_write": 0.38 + }, + "limit": { + "context": 204000, + "output": 64000 + } + }, + { + "id": "zenmux/minimax/minimax-m2.5", + "name": "MiniMax M2.5", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-02-13", + "last_updated": "2026-02-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_read": 0.03, + "cache_write": 0.375 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zenmux/minimax/minimax-m2.5-lightning", + "name": "MiniMax: MiniMax M2.5 highspeed", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-02-13", + "last_updated": "2026-02-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 4.8, + "cache_read": 0.06, + "cache_write": 0.75 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zenmux/moonshotai/kimi-k2", + "name": "Kimi K2 0905", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-09-04", + "last_updated": "2025-09-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.15 + }, + "limit": { + "context": 262000, + "output": 64000 + } + }, + { + "id": "zenmux/moonshotai/kimi-k2-thinking", + "name": "Kimi K2 Thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.6, + "output": 2.5, + "cache_read": 0.15 + }, + "limit": { + "context": 262000, + "output": 64000 + } + }, + { + "id": "zenmux/moonshotai/kimi-k2-thinking-turbo", + "name": "Kimi K2 Thinking Turbo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-11-06", + "last_updated": "2025-11-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.15, + "output": 8.0, + "cache_read": 0.15 + }, + "limit": { + "context": 262000, + "output": 64000 + } + }, + { + "id": "zenmux/moonshotai/kimi-k2.5", + "name": "Kimi K2.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-01-27", + "last_updated": "2026-01-27", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.58, + "output": 3.02, + "cache_read": 0.1 + }, + "limit": { + "context": 262000, + "output": 64000 + } + }, + { + "id": "zenmux/openai/gpt-5", + "name": "GPT-5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.12 + }, + "limit": { + "context": 400000, + "output": 64000 + } + }, + { + "id": "zenmux/openai/gpt-5-codex", + "name": "GPT-5 Codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-09-23", + "last_updated": "2025-09-23", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.12 + }, + "limit": { + "context": 400000, + "output": 64000 + } + }, + { + "id": "zenmux/openai/gpt-5.1", + "name": "GPT-5.1", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "image", + "text", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.12 + }, + "limit": { + "context": 400000, + "output": 64000 + } + }, + { + "id": "zenmux/openai/gpt-5.1-chat", + "name": "GPT-5.1 Chat", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "pdf", + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.12 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "zenmux/openai/gpt-5.1-codex", + "name": "GPT-5.1-Codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 10.0, + "cache_read": 0.12 + }, + "limit": { + "context": 400000, + "output": 64000 + } + }, + { + "id": "zenmux/openai/gpt-5.1-codex-mini", + "name": "GPT-5.1-Codex-Mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 2.0, + "cache_read": 0.03 + }, + "limit": { + "context": 400000, + "output": 64000 + } + }, + { + "id": "zenmux/openai/gpt-5.2", + "name": "GPT-5.2", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01-01", + "release_date": "2025-12-11", + "last_updated": "2025-12-11", + "modalities": { + "input": [ + "image", + "text", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.17 + }, + "limit": { + "context": 400000, + "output": 64000 + } + }, + { + "id": "zenmux/openai/gpt-5.2-codex", + "name": "GPT-5.2-Codex", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01-01", + "release_date": "2026-01-15", + "last_updated": "2026-01-15", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.75, + "output": 14.0, + "cache_read": 0.17 + }, + "limit": { + "context": 400000, + "output": 64000 + } + }, + { + "id": "zenmux/qwen/qwen3-coder-plus", + "name": "Qwen3-Coder-Plus", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-07-23", + "last_updated": "2025-07-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 5.0, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 1000000, + "output": 64000 + } + }, + { + "id": "zenmux/qwen/qwen3-max", + "name": "Qwen3-Max-Thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-01-23", + "last_updated": "2026-01-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.2, + "output": 6.0 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/stepfun/step-3", + "name": "Step-3", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-07-31", + "last_updated": "2025-07-31", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.21, + "output": 0.57 + }, + "limit": { + "context": 65536, + "output": 64000 + } + }, + { + "id": "zenmux/stepfun/step-3.5-flash", + "name": "Step 3.5 Flash", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-02-02", + "last_updated": "2026-02-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.3 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/stepfun/step-3.5-flash-free", + "name": "Step 3.5 Flash (Free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-02-02", + "last_updated": "2026-02-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/volcengine/doubao-seed-1.8", + "name": "Doubao-Seed-1.8", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-12-18", + "last_updated": "2025-12-18", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.11, + "output": 0.28, + "cache_read": 0.02, + "cache_write": 0.0024 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/volcengine/doubao-seed-2.0-lite", + "name": "Doubao-Seed-2.0-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-14", + "release_date": "2026-02-14", + "last_updated": "2026-02-14", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.09, + "output": 0.51, + "cache_read": 0.02, + "cache_write": 0.0024 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/volcengine/doubao-seed-2.0-mini", + "name": "Doubao-Seed-2.0-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-14", + "release_date": "2026-02-14", + "last_updated": "2026-02-14", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.03, + "output": 0.28, + "cache_read": 0.01, + "cache_write": 0.0024 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/volcengine/doubao-seed-2.0-pro", + "name": "Doubao-Seed-2.0-pro", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2026-02-14", + "release_date": "2026-02-14", + "last_updated": "2026-02-14", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.45, + "output": 2.24, + "cache_read": 0.09, + "cache_write": 0.0024 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/volcengine/doubao-seed-code", + "name": "Doubao-Seed-Code", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-11-11", + "last_updated": "2025-11-11", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.17, + "output": 1.12, + "cache_read": 0.03 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/x-ai/grok-4", + "name": "Grok 4", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-07-09", + "last_updated": "2025-07-09", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 3.0, + "output": 15.0, + "cache_read": 0.75 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/x-ai/grok-4-fast", + "name": "Grok 4 Fast", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-09-19", + "last_updated": "2025-09-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 64000 + } + }, + { + "id": "zenmux/x-ai/grok-4.1-fast", + "name": "Grok 4.1 Fast", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-11-20", + "last_updated": "2025-11-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 64000 + } + }, + { + "id": "zenmux/x-ai/grok-4.1-fast-non", + "name": "Grok 4.1 Fast Non Reasoning", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-11-20", + "last_updated": "2025-11-20", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 0.5, + "cache_read": 0.05 + }, + "limit": { + "context": 2000000, + "output": 64000 + } + }, + { + "id": "zenmux/x-ai/grok-code-fast-1", + "name": "Grok Code Fast 1", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-08-26", + "last_updated": "2025-08-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.5, + "cache_read": 0.02 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, + { + "id": "zenmux/xiaomi/mimo-v2-flash", + "name": "MiMo-V2-Flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.1, + "output": 0.3, + "cache_read": 0.01 + }, + "limit": { + "context": 262000, + "output": 64000 + } + }, + { + "id": "zenmux/xiaomi/mimo-v2-flash-free", + "name": "MiMo-V2-Flash Free", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-12-17", + "last_updated": "2025-12-17", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262000, + "output": 64000 + } + }, + { + "id": "zenmux/z-ai/glm-4.5", + "name": "GLM 4.5", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.35, + "output": 1.54, + "cache_read": 0.07 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "zenmux/z-ai/glm-4.5-air", + "name": "GLM 4.5 Air", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.11, + "output": 0.56, + "cache_read": 0.02 + }, + "limit": { + "context": 128000, + "output": 64000 + } + }, + { + "id": "zenmux/z-ai/glm-4.6", + "name": "GLM 4.6", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.35, + "output": 1.54, + "cache_read": 0.07 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/z-ai/glm-4.6v", + "name": "GLM 4.6V", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.14, + "output": 0.42, + "cache_read": 0.03 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/z-ai/glm-4.6v-flash", + "name": "GLM 4.6V FlashX", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.02, + "output": 0.21, + "cache_read": 0.0043 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/z-ai/glm-4.6v-flash-free", + "name": "GLM 4.6V Flash (Free)", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/z-ai/glm-4.7", + "name": "GLM 4.7", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2025-12-23", + "last_updated": "2025-12-23", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.28, + "output": 1.14, + "cache_read": 0.06 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/z-ai/glm-4.7-flash-free", + "name": "GLM 4.7 Flash (Free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/z-ai/glm-4.7-flashx", + "name": "GLM 4.7 FlashX", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.07, + "output": 0.42, + "cache_read": 0.01 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "zenmux/z-ai/glm-5", + "name": "GLM 5", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01-01", + "release_date": "2026-02-12", + "last_updated": "2026-02-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.58, + "output": 2.6, + "cache_read": 0.14 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, + { + "id": "zhipuai-coding-plan/glm-4.5", + "name": "GLM-4.5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zhipuai-coding-plan/glm-4.5-air", + "name": "GLM-4.5-Air", + "family": "glm-air", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zhipuai-coding-plan/glm-4.5-flash", + "name": "GLM-4.5-Flash", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zhipuai-coding-plan/glm-4.5v", + "name": "GLM-4.5V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-08-11", + "last_updated": "2025-08-11", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 64000, + "output": 16384 + } + }, + { + "id": "zhipuai-coding-plan/glm-4.6", + "name": "GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zhipuai-coding-plan/glm-4.6v", + "name": "GLM-4.6V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "zhipuai-coding-plan/glm-4.6v-flash", + "name": "GLM-4.6V-Flash", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "zhipuai-coding-plan/glm-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zhipuai-coding-plan/glm-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zhipuai/glm-4.5", + "name": "GLM-4.5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zhipuai/glm-4.5-air", + "name": "GLM-4.5-Air", + "family": "glm-air", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 1.1, + "cache_read": 0.03, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zhipuai/glm-4.5-flash", + "name": "GLM-4.5-Flash", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-07-28", + "last_updated": "2025-07-28", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 131072, + "output": 98304 + } + }, + { + "id": "zhipuai/glm-4.5v", + "name": "GLM-4.5V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-08-11", + "last_updated": "2025-08-11", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 1.8 + }, + "limit": { + "context": 64000, + "output": 16384 + } + }, + { + "id": "zhipuai/glm-4.6", + "name": "GLM-4.6", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-09-30", + "last_updated": "2025-09-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zhipuai/glm-4.6v", + "name": "GLM-4.6V", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-08", + "last_updated": "2025-12-08", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 0.9 + }, + "limit": { + "context": 128000, + "output": 32768 + } + }, + { + "id": "zhipuai/glm-4.7", + "name": "GLM-4.7", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2025-12-22", + "last_updated": "2025-12-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.2, + "cache_read": 0.11, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "zhipuai/glm-4.7-flash", + "name": "GLM-4.7-Flash", + "family": "glm-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-01-19", + "last_updated": "2026-01-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0, + "cache_write": 0.0 + }, + "limit": { + "context": 200000, + "output": 131072 + } + }, + { + "id": "zhipuai/glm-5", + "name": "GLM-5", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-11", + "last_updated": "2026-02-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 3.2, + "cache_read": 0.2, + "cache_write": 0.0 + }, + "limit": { + "context": 204800, + "output": 131072 + } } ] \ No newline at end of file diff --git a/crates/goose/src/providers/canonical/data/provider_metadata.json b/crates/goose/src/providers/canonical/data/provider_metadata.json new file mode 100644 index 0000000000..b1999867a9 --- /dev/null +++ b/crates/goose/src/providers/canonical/data/provider_metadata.json @@ -0,0 +1,807 @@ +[ + { + "id": "evroc", + "display_name": "evroc", + "npm": "@ai-sdk/openai-compatible", + "api": "https://models.think.evroc.com/v1", + "doc": "https://docs.evroc.com/products/think/overview.html", + "env": [ + "EVROC_API_KEY" + ], + "model_count": 13 + }, + { + "id": "privatemode-ai", + "display_name": "Privatemode AI", + "npm": "@ai-sdk/openai-compatible", + "api": "http://localhost:8080/v1", + "doc": "https://docs.privatemode.ai/api/overview", + "env": [ + "PRIVATEMODE_API_KEY", + "PRIVATEMODE_ENDPOINT" + ], + "model_count": 5 + }, + { + "id": "stepfun", + "display_name": "StepFun", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.stepfun.com/v1", + "doc": "https://platform.stepfun.com/docs/zh/overview/concept", + "env": [ + "STEPFUN_API_KEY" + ], + "model_count": 3 + }, + { + "id": "moonshotai-cn", + "display_name": "Moonshot AI (China)", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.moonshot.cn/v1", + "doc": "https://platform.moonshot.cn/docs/api/chat", + "env": [ + "MOONSHOT_API_KEY" + ], + "model_count": 6 + }, + { + "id": "firmware", + "display_name": "Firmware", + "npm": "@ai-sdk/openai-compatible", + "api": "https://app.firmware.ai/api/v1", + "doc": "https://docs.firmware.ai", + "env": [ + "FIRMWARE_API_KEY" + ], + "model_count": 16 + }, + { + "id": "nova", + "display_name": "Nova", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.nova.amazon.com/v1", + "doc": "https://nova.amazon.com/dev/documentation", + "env": [ + "NOVA_API_KEY" + ], + "model_count": 2 + }, + { + "id": "lucidquery", + "display_name": "LucidQuery AI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://lucidquery.com/api/v1", + "doc": "https://lucidquery.com/api/docs", + "env": [ + "LUCIDQUERY_API_KEY" + ], + "model_count": 2 + }, + { + "id": "moonshotai", + "display_name": "Moonshot AI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.moonshot.ai/v1", + "doc": "https://platform.moonshot.ai/docs/api/chat", + "env": [ + "MOONSHOT_API_KEY" + ], + "model_count": 6 + }, + { + "id": "302ai", + "display_name": "302.AI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.302.ai/v1", + "doc": "https://doc.302.ai", + "env": [ + "302AI_API_KEY" + ], + "model_count": 64 + }, + { + "id": "qihang-ai", + "display_name": "QiHang", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.qhaigc.net/v1", + "doc": "https://www.qhaigc.net/docs", + "env": [ + "QIHANG_API_KEY" + ], + "model_count": 9 + }, + { + "id": "zai-coding-plan", + "display_name": "Z.AI Coding Plan", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.z.ai/api/coding/paas/v4", + "doc": "https://docs.z.ai/devpack/overview", + "env": [ + "ZHIPU_API_KEY" + ], + "model_count": 10 + }, + { + "id": "ollama-cloud", + "display_name": "Ollama Cloud", + "npm": "@ai-sdk/openai-compatible", + "api": "https://ollama.com/v1", + "doc": "https://docs.ollama.com/cloud", + "env": [ + "OLLAMA_API_KEY" + ], + "model_count": 33 + }, + { + "id": "xiaomi", + "display_name": "Xiaomi", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.xiaomimimo.com/v1", + "doc": "https://platform.xiaomimimo.com/#/docs", + "env": [ + "XIAOMI_API_KEY" + ], + "model_count": 1 + }, + { + "id": "alibaba", + "display_name": "Alibaba", + "npm": "@ai-sdk/openai-compatible", + "api": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", + "doc": "https://www.alibabacloud.com/help/en/model-studio/models", + "env": [ + "DASHSCOPE_API_KEY" + ], + "model_count": 41 + }, + { + "id": "vultr", + "display_name": "Vultr", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.vultrinference.com/v1", + "doc": "https://api.vultrinference.com/", + "env": [ + "VULTR_API_KEY" + ], + "model_count": 5 + }, + { + "id": "nvidia", + "display_name": "Nvidia", + "npm": "@ai-sdk/openai-compatible", + "api": "https://integrate.api.nvidia.com/v1", + "doc": "https://docs.api.nvidia.com/nim/", + "env": [ + "NVIDIA_API_KEY" + ], + "model_count": 71 + }, + { + "id": "upstage", + "display_name": "Upstage", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.upstage.ai/v1/solar", + "doc": "https://developers.upstage.ai/docs/apis/chat", + "env": [ + "UPSTAGE_API_KEY" + ], + "model_count": 3 + }, + { + "id": "bailing", + "display_name": "Bailing", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.tbox.cn/api/llm/v1/chat/completions", + "doc": "https://alipaytbox.yuque.com/sxs0ba/ling/intro", + "env": [ + "BAILING_API_TOKEN" + ], + "model_count": 2 + }, + { + "id": "github-copilot", + "display_name": "GitHub Copilot", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.githubcopilot.com", + "doc": "https://docs.github.com/en/copilot", + "env": [ + "GITHUB_TOKEN" + ], + "model_count": 22 + }, + { + "id": "jiekou", + "display_name": "Jiekou.AI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.jiekou.ai/openai", + "doc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", + "env": [ + "JIEKOU_API_KEY" + ], + "model_count": 61 + }, + { + "id": "cloudferro-sherlock", + "display_name": "CloudFerro Sherlock", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api-sherlock.cloudferro.com/openai/v1/", + "doc": "https://docs.sherlock.cloudferro.com/", + "env": [ + "CLOUDFERRO_SHERLOCK_API_KEY" + ], + "model_count": 4 + }, + { + "id": "abacus", + "display_name": "Abacus", + "npm": "@ai-sdk/openai-compatible", + "api": "https://routellm.abacus.ai/v1", + "doc": "https://abacus.ai/help/api", + "env": [ + "ABACUS_API_KEY" + ], + "model_count": 55 + }, + { + "id": "nebius", + "display_name": "Nebius Token Factory", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.tokenfactory.nebius.com/v1", + "doc": "https://docs.tokenfactory.nebius.com/", + "env": [ + "NEBIUS_API_KEY" + ], + "model_count": 46 + }, + { + "id": "deepseek", + "display_name": "DeepSeek", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.deepseek.com", + "doc": "https://platform.deepseek.com/api-docs/pricing", + "env": [ + "DEEPSEEK_API_KEY" + ], + "model_count": 2 + }, + { + "id": "alibaba-cn", + "display_name": "Alibaba (China)", + "npm": "@ai-sdk/openai-compatible", + "api": "https://dashscope.aliyuncs.com/compatible-mode/v1", + "doc": "https://www.alibabacloud.com/help/en/model-studio/models", + "env": [ + "DASHSCOPE_API_KEY" + ], + "model_count": 65 + }, + { + "id": "novita-ai", + "display_name": "NovitaAI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.novita.ai/openai", + "doc": "https://novita.ai/docs/guides/introduction", + "env": [ + "NOVITA_API_KEY" + ], + "model_count": 84 + }, + { + "id": "siliconflow-cn", + "display_name": "SiliconFlow (China)", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.siliconflow.cn/v1", + "doc": "https://cloud.siliconflow.com/models", + "env": [ + "SILICONFLOW_CN_API_KEY" + ], + "model_count": 72 + }, + { + "id": "vivgrid", + "display_name": "Vivgrid", + "npm": "@ai-sdk/openai", + "api": "https://api.vivgrid.com/v1", + "doc": "https://docs.vivgrid.com/models", + "env": [ + "VIVGRID_API_KEY" + ], + "model_count": 8 + }, + { + "id": "chutes", + "display_name": "Chutes", + "npm": "@ai-sdk/openai-compatible", + "api": "https://llm.chutes.ai/v1", + "doc": "https://llm.chutes.ai/v1/models", + "env": [ + "CHUTES_API_KEY" + ], + "model_count": 67 + }, + { + "id": "kimi-for-coding", + "display_name": "Kimi For Coding", + "npm": "@ai-sdk/anthropic", + "api": "https://api.kimi.com/coding/v1", + "doc": "https://www.kimi.com/coding/docs/en/third-party-agents.html", + "env": [ + "KIMI_API_KEY" + ], + "model_count": 2 + }, + { + "id": "kuae-cloud-coding-plan", + "display_name": "KUAE Cloud Coding Plan", + "npm": "@ai-sdk/openai-compatible", + "api": "https://coding-plan-endpoint.kuaecloud.net/v1", + "doc": "https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/coding_plan/", + "env": [ + "KUAE_API_KEY" + ], + "model_count": 1 + }, + { + "id": "cortecs", + "display_name": "Cortecs", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.cortecs.ai/v1", + "doc": "https://api.cortecs.ai/v1/models", + "env": [ + "CORTECS_API_KEY" + ], + "model_count": 21 + }, + { + "id": "github-models", + "display_name": "GitHub Models", + "npm": "@ai-sdk/openai-compatible", + "api": "https://models.github.ai/inference", + "doc": "https://docs.github.com/en/github-models", + "env": [ + "GITHUB_TOKEN" + ], + "model_count": 55 + }, + { + "id": "baseten", + "display_name": "Baseten", + "npm": "@ai-sdk/openai-compatible", + "api": "https://inference.baseten.co/v1", + "doc": "https://docs.baseten.co/development/model-apis/overview", + "env": [ + "BASETEN_API_KEY" + ], + "model_count": 8 + }, + { + "id": "moark", + "display_name": "Moark", + "npm": "@ai-sdk/openai-compatible", + "api": "https://moark.com/v1", + "doc": "https://moark.com/docs/openapi/v1#tag/%E6%96%87%E6%9C%AC%E7%94%9F%E6%88%90", + "env": [ + "MOARK_API_KEY" + ], + "model_count": 2 + }, + { + "id": "siliconflow", + "display_name": "SiliconFlow", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.siliconflow.com/v1", + "doc": "https://cloud.siliconflow.com/models", + "env": [ + "SILICONFLOW_API_KEY" + ], + "model_count": 70 + }, + { + "id": "helicone", + "display_name": "Helicone", + "npm": "@ai-sdk/openai-compatible", + "api": "https://ai-gateway.helicone.ai/v1", + "doc": "https://helicone.ai/models", + "env": [ + "HELICONE_API_KEY" + ], + "model_count": 91 + }, + { + "id": "huggingface", + "display_name": "Hugging Face", + "npm": "@ai-sdk/openai-compatible", + "api": "https://router.huggingface.co/v1", + "doc": "https://huggingface.co/docs/inference-providers", + "env": [ + "HF_TOKEN" + ], + "model_count": 20 + }, + { + "id": "opencode", + "display_name": "OpenCode Zen", + "npm": "@ai-sdk/openai-compatible", + "api": "https://opencode.ai/zen/v1", + "doc": "https://opencode.ai/docs/zen", + "env": [ + "OPENCODE_API_KEY" + ], + "model_count": 37 + }, + { + "id": "meganova", + "display_name": "Meganova", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.meganova.ai/v1", + "doc": "https://docs.meganova.ai", + "env": [ + "MEGANOVA_API_KEY" + ], + "model_count": 19 + }, + { + "id": "fastrouter", + "display_name": "FastRouter", + "npm": "@ai-sdk/openai-compatible", + "api": "https://go.fastrouter.ai/api/v1", + "doc": "https://fastrouter.ai/models", + "env": [ + "FASTROUTER_API_KEY" + ], + "model_count": 14 + }, + { + "id": "minimax", + "display_name": "MiniMax (minimax.io)", + "npm": "@ai-sdk/anthropic", + "api": "https://api.minimax.io/anthropic/v1", + "doc": "https://platform.minimax.io/docs/guides/quickstart", + "env": [ + "MINIMAX_API_KEY" + ], + "model_count": 4 + }, + { + "id": "cloudflare-workers-ai", + "display_name": "Cloudflare Workers AI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", + "doc": "https://developers.cloudflare.com/workers-ai/models/", + "env": [ + "CLOUDFLARE_ACCOUNT_ID", + "CLOUDFLARE_API_KEY" + ], + "model_count": 39 + }, + { + "id": "inception", + "display_name": "Inception", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.inceptionlabs.ai/v1/", + "doc": "https://platform.inceptionlabs.ai/docs", + "env": [ + "INCEPTION_API_KEY" + ], + "model_count": 2 + }, + { + "id": "wandb", + "display_name": "Weights & Biases", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.inference.wandb.ai/v1", + "doc": "https://weave-docs.wandb.ai/guides/integrations/inference/", + "env": [ + "WANDB_API_KEY" + ], + "model_count": 10 + }, + { + "id": "zhipuai-coding-plan", + "display_name": "Zhipu AI Coding Plan", + "npm": "@ai-sdk/openai-compatible", + "api": "https://open.bigmodel.cn/api/coding/paas/v4", + "doc": "https://docs.bigmodel.cn/cn/coding-plan/overview", + "env": [ + "ZHIPU_API_KEY" + ], + "model_count": 9 + }, + { + "id": "minimax-cn", + "display_name": "MiniMax (minimaxi.com)", + "npm": "@ai-sdk/anthropic", + "api": "https://api.minimaxi.com/anthropic/v1", + "doc": "https://platform.minimaxi.com/docs/guides/quickstart", + "env": [ + "MINIMAX_API_KEY" + ], + "model_count": 4 + }, + { + "id": "zenmux", + "display_name": "ZenMux", + "npm": "@ai-sdk/anthropic", + "api": "https://zenmux.ai/api/anthropic/v1", + "doc": "https://docs.zenmux.ai", + "env": [ + "ZENMUX_API_KEY" + ], + "model_count": 67 + }, + { + "id": "minimax-coding-plan", + "display_name": "MiniMax Coding Plan (minimax.io)", + "npm": "@ai-sdk/anthropic", + "api": "https://api.minimax.io/anthropic/v1", + "doc": "https://platform.minimax.io/docs/coding-plan/intro", + "env": [ + "MINIMAX_API_KEY" + ], + "model_count": 4 + }, + { + "id": "ovhcloud", + "display_name": "OVHcloud AI Endpoints", + "npm": "@ai-sdk/openai-compatible", + "api": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", + "doc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", + "env": [ + "OVHCLOUD_API_KEY" + ], + "model_count": 13 + }, + { + "id": "iflowcn", + "display_name": "iFlow", + "npm": "@ai-sdk/openai-compatible", + "api": "https://apis.iflow.cn/v1", + "doc": "https://platform.iflow.cn/en/docs", + "env": [ + "IFLOW_API_KEY" + ], + "model_count": 14 + }, + { + "id": "synthetic", + "display_name": "Synthetic", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.synthetic.new/v1", + "doc": "https://synthetic.new/pricing", + "env": [ + "SYNTHETIC_API_KEY" + ], + "model_count": 26 + }, + { + "id": "zhipuai", + "display_name": "Zhipu AI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://open.bigmodel.cn/api/paas/v4", + "doc": "https://docs.z.ai/guides/overview/pricing", + "env": [ + "ZHIPU_API_KEY" + ], + "model_count": 9 + }, + { + "id": "kilo", + "display_name": "Kilo Gateway", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.kilo.ai/api/gateway", + "doc": "https://kilo.ai", + "env": [ + "KILO_API_KEY" + ], + "model_count": 263 + }, + { + "id": "submodel", + "display_name": "submodel", + "npm": "@ai-sdk/openai-compatible", + "api": "https://llm.submodel.ai/v1", + "doc": "https://submodel.gitbook.io", + "env": [ + "SUBMODEL_INSTAGEN_ACCESS_KEY" + ], + "model_count": 9 + }, + { + "id": "nano-gpt", + "display_name": "NanoGPT", + "npm": "@ai-sdk/openai-compatible", + "api": "https://nano-gpt.com/api/v1", + "doc": "https://docs.nano-gpt.com", + "env": [ + "NANO_GPT_API_KEY" + ], + "model_count": 33 + }, + { + "id": "zai", + "display_name": "Z.AI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.z.ai/api/paas/v4", + "doc": "https://docs.z.ai/guides/overview/pricing", + "env": [ + "ZHIPU_API_KEY" + ], + "model_count": 9 + }, + { + "id": "berget", + "display_name": "Berget.AI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.berget.ai/v1", + "doc": "https://api.berget.ai", + "env": [ + "BERGET_API_KEY" + ], + "model_count": 8 + }, + { + "id": "stackit", + "display_name": "STACKIT", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1", + "doc": "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models", + "env": [ + "STACKIT_API_KEY" + ], + "model_count": 8 + }, + { + "id": "inference", + "display_name": "Inference", + "npm": "@ai-sdk/openai-compatible", + "api": "https://inference.net/v1", + "doc": "https://inference.net/models", + "env": [ + "INFERENCE_API_KEY" + ], + "model_count": 9 + }, + { + "id": "requesty", + "display_name": "Requesty", + "npm": "@ai-sdk/openai-compatible", + "api": "https://router.requesty.ai/v1", + "doc": "https://requesty.ai/solution/llm-routing/models", + "env": [ + "REQUESTY_API_KEY" + ], + "model_count": 20 + }, + { + "id": "morph", + "display_name": "Morph", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.morphllm.com/v1", + "doc": "https://docs.morphllm.com/api-reference/introduction", + "env": [ + "MORPH_API_KEY" + ], + "model_count": 3 + }, + { + "id": "qiniu-ai", + "display_name": "Qiniu", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.qnaigc.com.com/v1", + "doc": "https://developer.qiniu.com/aitokenapi", + "env": [ + "Qiniu_API_KEY" + ], + "model_count": 76 + }, + { + "id": "lmstudio", + "display_name": "LMStudio", + "npm": "@ai-sdk/openai-compatible", + "api": "http://127.0.0.1:1234/v1", + "doc": "https://lmstudio.ai/models", + "env": [ + "LMSTUDIO_API_KEY" + ], + "model_count": 3 + }, + { + "id": "friendli", + "display_name": "Friendli", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.friendli.ai/serverless/v1", + "doc": "https://friendli.ai/docs/guides/serverless_endpoints/introduction", + "env": [ + "FRIENDLI_TOKEN" + ], + "model_count": 8 + }, + { + "id": "aihubmix", + "display_name": "AIHubMix", + "npm": "@ai-sdk/openai-compatible", + "api": "https://aihubmix.com/v1", + "doc": "https://docs.aihubmix.com", + "env": [ + "AIHUBMIX_API_KEY" + ], + "model_count": 43 + }, + { + "id": "fireworks-ai", + "display_name": "Fireworks AI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.fireworks.ai/inference/v1/", + "doc": "https://fireworks.ai/docs/", + "env": [ + "FIREWORKS_API_KEY" + ], + "model_count": 13 + }, + { + "id": "io-net", + "display_name": "IO.NET", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.intelligence.io.solutions/api/v1", + "doc": "https://io.net/docs/guides/intelligence/io-intelligence", + "env": [ + "IOINTELLIGENCE_API_KEY" + ], + "model_count": 17 + }, + { + "id": "modelscope", + "display_name": "ModelScope", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api-inference.modelscope.cn/v1", + "doc": "https://modelscope.cn/docs/model-service/API-Inference/intro", + "env": [ + "MODELSCOPE_API_KEY" + ], + "model_count": 7 + }, + { + "id": "meta-llama", + "display_name": "Llama", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.llama.com/compat/v1/", + "doc": "https://llama.developer.meta.com/docs/models", + "env": [ + "LLAMA_API_KEY" + ], + "model_count": 7 + }, + { + "id": "scaleway", + "display_name": "Scaleway", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.scaleway.ai/v1", + "doc": "https://www.scaleway.com/en/docs/generative-apis/", + "env": [ + "SCALEWAY_API_KEY" + ], + "model_count": 14 + }, + { + "id": "poe", + "display_name": "Poe", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.poe.com/v1", + "doc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", + "env": [ + "POE_API_KEY" + ], + "model_count": 114 + }, + { + "id": "minimax-cn-coding-plan", + "display_name": "MiniMax Coding Plan (minimaxi.com)", + "npm": "@ai-sdk/anthropic", + "api": "https://api.minimaxi.com/anthropic/v1", + "doc": "https://platform.minimaxi.com/docs/coding-plan/intro", + "env": [ + "MINIMAX_API_KEY" + ], + "model_count": 4 + } +] \ No newline at end of file diff --git a/crates/goose/src/providers/canonical/registry.rs b/crates/goose/src/providers/canonical/registry.rs index bbb25c9284..da3ed24e34 100644 --- a/crates/goose/src/providers/canonical/registry.rs +++ b/crates/goose/src/providers/canonical/registry.rs @@ -83,6 +83,14 @@ impl CanonicalModelRegistry { self.models.get(&(provider.to_string(), model.to_string())) } + pub fn get_all_models_for_provider(&self, provider: &str) -> Vec { + self.models + .iter() + .filter(|((p, _), _)| p == provider) + .map(|(_, model)| model.clone()) + .collect() + } + pub fn all_models(&self) -> Vec<&CanonicalModel> { self.models.values().collect() } diff --git a/crates/goose/src/providers/catalog.rs b/crates/goose/src/providers/catalog.rs new file mode 100644 index 0000000000..2418fa844c --- /dev/null +++ b/crates/goose/src/providers/catalog.rs @@ -0,0 +1,245 @@ +use once_cell::sync::Lazy; +use serde::{Deserialize, Serialize}; +use std::collections::HashMap; + +use super::canonical::CanonicalModelRegistry; + +const PROVIDER_METADATA_JSON: &str = include_str!("canonical/data/provider_metadata.json"); + +#[derive(Debug, Clone, Serialize, Deserialize)] +struct ProviderMetadataEntry { + pub id: String, + pub display_name: String, + pub npm: Option, + pub api: Option, + pub doc: Option, + pub env: Vec, + pub model_count: usize, +} + +static PROVIDER_METADATA: Lazy> = Lazy::new(|| { + serde_json::from_str::>(PROVIDER_METADATA_JSON) + .unwrap_or_else(|e| { + eprintln!("Failed to parse provider metadata: {}", e); + Vec::new() + }) + .into_iter() + .map(|p| (p.id.clone(), p)) + .collect() +}); + +#[derive(Debug, Clone, PartialEq, Eq)] +pub enum ProviderFormat { + OpenAI, + Anthropic, + Ollama, +} + +impl ProviderFormat { + pub fn as_str(&self) -> &str { + match self { + ProviderFormat::OpenAI => "openai", + ProviderFormat::Anthropic => "anthropic", + ProviderFormat::Ollama => "ollama", + } + } +} + +impl std::str::FromStr for ProviderFormat { + type Err = String; + + fn from_str(s: &str) -> Result { + match s.to_lowercase().as_str() { + "openai" | "openai_compatible" => Ok(ProviderFormat::OpenAI), + "anthropic" | "anthropic_compatible" => Ok(ProviderFormat::Anthropic), + "ollama" | "ollama_compatible" => Ok(ProviderFormat::Ollama), + _ => Err(format!("unknown provider format: {}", s)), + } + } +} + +fn detect_format_from_npm(npm: &str) -> Option { + if npm.contains("openai") { + Some(ProviderFormat::OpenAI) + } else if npm.contains("anthropic") { + Some(ProviderFormat::Anthropic) + } else if npm.contains("ollama") { + Some(ProviderFormat::Ollama) + } else { + None + } +} + +#[derive(Debug, Clone, Serialize, utoipa::ToSchema)] +pub struct ProviderCatalogEntry { + pub id: String, + pub name: String, + pub format: String, + pub api_url: String, + pub model_count: usize, + pub doc_url: String, + pub env_var: String, +} + +#[derive(Debug, Clone, Serialize, utoipa::ToSchema)] +pub struct ProviderTemplate { + pub id: String, + pub name: String, + pub format: String, + pub api_url: String, + pub models: Vec, + pub supports_streaming: bool, + pub env_var: String, + pub doc_url: String, +} + +#[derive(Debug, Clone, Serialize, utoipa::ToSchema)] +pub struct ModelTemplate { + pub id: String, + pub name: String, + pub context_limit: usize, + pub capabilities: ModelCapabilities, + pub deprecated: bool, +} + +#[derive(Debug, Clone, Serialize, utoipa::ToSchema)] +pub struct ModelCapabilities { + pub tool_call: bool, + pub reasoning: bool, + pub attachment: bool, + pub temperature: bool, +} + +pub async fn get_providers_by_format(format: ProviderFormat) -> Vec { + let native_provider_ids = super::init::providers() + .await + .into_iter() + .map(|(metadata, _)| metadata.name) + .collect::>(); + + let mut entries: Vec = PROVIDER_METADATA + .values() + .filter_map(|metadata| { + if native_provider_ids.contains(&metadata.id) { + return None; + } + + let npm = metadata.npm.as_ref()?; + let detected_format = detect_format_from_npm(npm)?; + + if detected_format != format { + return None; + } + + let api_url = metadata.api.as_ref()?.clone(); + + let env_var = metadata.env.first().cloned().unwrap_or_else(|| { + format!("{}_API_KEY", metadata.id.to_uppercase().replace('-', "_")) + }); + + Some(ProviderCatalogEntry { + id: metadata.id.clone(), + name: metadata.display_name.clone(), + format: detected_format.as_str().to_string(), + api_url, + model_count: metadata.model_count, + doc_url: metadata.doc.clone().unwrap_or_default(), + env_var, + }) + }) + .collect(); + + // Sort by name + entries.sort_by(|a, b| a.name.cmp(&b.name)); + entries +} + +pub fn get_provider_template(provider_id: &str) -> Option { + let metadata = PROVIDER_METADATA.get(provider_id)?; + + let npm = metadata.npm.as_ref()?; + let format = detect_format_from_npm(npm)?; + + let api_url = metadata.api.as_ref()?.clone(); + + let models: Vec = CanonicalModelRegistry::bundled() + .ok() + .map(|registry| { + registry + .get_all_models_for_provider(provider_id) + .into_iter() + .map(|model| { + // Extract just the model ID (without provider prefix) + let model_id = model + .id + .strip_prefix(&format!("{}/", provider_id)) + .unwrap_or(&model.id) + .to_string(); + + ModelTemplate { + id: model_id, + name: model.name.clone(), + context_limit: model.limit.context, + capabilities: ModelCapabilities { + tool_call: model.tool_call, + reasoning: model.reasoning.unwrap_or(false), + attachment: model.attachment.unwrap_or(false), + temperature: model.temperature.unwrap_or(false), + }, + deprecated: false, // Canonical models don't have deprecated flag + } + }) + .collect() + }) + .unwrap_or_default(); + + let env_var = metadata + .env + .first() + .cloned() + .unwrap_or_else(|| format!("{}_API_KEY", provider_id.to_uppercase().replace('-', "_"))); + + Some(ProviderTemplate { + id: metadata.id.clone(), + name: metadata.display_name.clone(), + format: format.as_str().to_string(), + api_url, + models, + supports_streaming: true, // Default to true + env_var, + doc_url: metadata.doc.clone().unwrap_or_default(), + }) +} + +#[cfg(test)] +mod tests { + use super::*; + + #[tokio::test] + async fn test_zai_provider() { + let openai_providers = get_providers_by_format(ProviderFormat::OpenAI).await; + let zai = openai_providers.iter().find(|p| p.id == "zai"); + assert!(zai.is_some(), "z.ai should be in catalog"); + + let zai = zai.unwrap(); + println!("Z.AI: {} models", zai.model_count); + assert!(zai.model_count > 0, "z.ai should have models"); + + let template = get_provider_template("zai"); + assert!(template.is_some(), "z.ai should have a template"); + + let template = template.unwrap(); + println!("Z.AI template: {} models", template.models.len()); + for model in template.models.iter().take(3) { + println!( + " - {} ({}K context)", + model.name, + model.context_limit / 1000 + ); + } + assert!( + !template.models.is_empty(), + "z.ai template should have models" + ); + } +} diff --git a/crates/goose/src/providers/mod.rs b/crates/goose/src/providers/mod.rs index 581fc2747e..6b2ce20528 100644 --- a/crates/goose/src/providers/mod.rs +++ b/crates/goose/src/providers/mod.rs @@ -6,6 +6,7 @@ pub mod azureauth; pub mod base; pub mod bedrock; pub mod canonical; +pub mod catalog; pub mod chatgpt_codex; pub mod claude_code; pub(crate) mod cli_common; diff --git a/ui/desktop/openapi.json b/ui/desktop/openapi.json index 29188e7d83..b6dece5553 100644 --- a/ui/desktop/openapi.json +++ b/ui/desktop/openapi.json @@ -1259,6 +1259,78 @@ } } }, + "/config/provider-catalog": { + "get": { + "tags": [ + "super::routes::config_management" + ], + "operationId": "get_provider_catalog", + "parameters": [ + { + "name": "format", + "in": "query", + "description": "Filter by provider format (openai, anthropic, ollama)", + "required": false, + "schema": { + "type": "string", + "nullable": true + } + } + ], + "responses": { + "200": { + "description": "Provider catalog retrieved successfully", + "content": { + "application/json": { + "schema": { + "type": "array", + "items": { + "$ref": "#/components/schemas/ProviderCatalogEntry" + } + } + } + } + }, + "400": { + "description": "Invalid format parameter" + } + } + } + }, + "/config/provider-catalog/{id}": { + "get": { + "tags": [ + "super::routes::config_management" + ], + "operationId": "get_provider_catalog_template", + "parameters": [ + { + "name": "id", + "in": "path", + "description": "Provider ID from models.dev", + "required": true, + "schema": { + "type": "string" + } + } + ], + "responses": { + "200": { + "description": "Provider template retrieved successfully", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/ProviderTemplate" + } + } + } + }, + "404": { + "description": "Provider not found in catalog" + } + } + } + }, "/config/providers": { "get": { "tags": [ @@ -4107,6 +4179,10 @@ "base_url": { "type": "string" }, + "catalog_provider_id": { + "type": "string", + "nullable": true + }, "description": { "type": "string", "nullable": true @@ -5702,6 +5778,29 @@ } } }, + "ModelCapabilities": { + "type": "object", + "required": [ + "tool_call", + "reasoning", + "attachment", + "temperature" + ], + "properties": { + "attachment": { + "type": "boolean" + }, + "reasoning": { + "type": "boolean" + }, + "temperature": { + "type": "boolean" + }, + "tool_call": { + "type": "boolean" + } + } + }, "ModelConfig": { "type": "object", "required": [ @@ -6003,6 +6102,34 @@ } } }, + "ModelTemplate": { + "type": "object", + "required": [ + "id", + "name", + "context_limit", + "capabilities", + "deprecated" + ], + "properties": { + "capabilities": { + "$ref": "#/components/schemas/ModelCapabilities" + }, + "context_limit": { + "type": "integer", + "minimum": 0 + }, + "deprecated": { + "type": "boolean" + }, + "id": { + "type": "string" + }, + "name": { + "type": "string" + } + } + }, "ParseRecipeRequest": { "type": "object", "required": [ @@ -6110,6 +6237,42 @@ } } }, + "ProviderCatalogEntry": { + "type": "object", + "required": [ + "id", + "name", + "format", + "api_url", + "model_count", + "doc_url", + "env_var" + ], + "properties": { + "api_url": { + "type": "string" + }, + "doc_url": { + "type": "string" + }, + "env_var": { + "type": "string" + }, + "format": { + "type": "string" + }, + "id": { + "type": "string" + }, + "model_count": { + "type": "integer", + "minimum": 0 + }, + "name": { + "type": "string" + } + } + }, "ProviderDetails": { "type": "object", "required": [ @@ -6190,6 +6353,48 @@ } } }, + "ProviderTemplate": { + "type": "object", + "required": [ + "id", + "name", + "format", + "api_url", + "models", + "supports_streaming", + "env_var", + "doc_url" + ], + "properties": { + "api_url": { + "type": "string" + }, + "doc_url": { + "type": "string" + }, + "env_var": { + "type": "string" + }, + "format": { + "type": "string" + }, + "id": { + "type": "string" + }, + "models": { + "type": "array", + "items": { + "$ref": "#/components/schemas/ModelTemplate" + } + }, + "name": { + "type": "string" + }, + "supports_streaming": { + "type": "boolean" + } + } + }, "ProviderType": { "type": "string", "enum": [ @@ -7952,6 +8157,10 @@ "api_url": { "type": "string" }, + "catalog_provider_id": { + "type": "string", + "nullable": true + }, "display_name": { "type": "string" }, diff --git a/ui/desktop/package-lock.json b/ui/desktop/package-lock.json index a381a371e8..4cb7434f84 100644 --- a/ui/desktop/package-lock.json +++ b/ui/desktop/package-lock.json @@ -238,6 +238,7 @@ "integrity": "sha512-CGOfOJqWjg2qW/Mb6zNsDm+u5vFQ8DxXfbM09z69p5Z6+mE1ikP2jUXw+j42Pf1XTYED2Rni5f95npYeuwMDQA==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "@babel/code-frame": "^7.29.0", "@babel/generator": "^7.29.0", @@ -607,6 +608,7 @@ } ], "license": "MIT", + "peer": true, "engines": { "node": ">=20.19.0" }, @@ -647,6 +649,7 @@ } ], "license": "MIT", + "peer": true, "engines": { "node": ">=20.19.0" } @@ -1104,6 +1107,7 @@ "integrity": "sha512-zx0EIq78WlY/lBb1uXlziZmDZI4ubcCXIMJ4uGjXzZW0nS19TjSPeXPAjzzTmKQlJUZm0SbmZhPKP7tuQ1SsEw==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "chalk": "^4.1.1", "fs-extra": "^9.0.1", @@ -2737,6 +2741,7 @@ "integrity": "sha512-yl43JD/86CIj3Mz5mvvLJqAOfIup7ncxfJ0Btnl0/v5TouVUyeEdcpknfgc+yMevS/48oH9WAkkw93m7otLb/A==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "@inquirer/checkbox": "^3.0.1", "@inquirer/confirm": "^4.0.1", @@ -3212,6 +3217,7 @@ "resolved": "https://registry.npmjs.org/@modelcontextprotocol/sdk/-/sdk-1.26.0.tgz", "integrity": "sha512-Y5RmPncpiDtTXDbLKswIJzTqu2hyBKxTNsgKqKclDbhIgg1wgtf1fRuvxgTnRfcnxtvvgbIEcqUOzZrJ6iSReg==", "license": "MIT", + "peer": true, "dependencies": { "@hono/node-server": "^1.19.9", "ajv": "^8.17.1", @@ -6536,8 +6542,7 @@ "resolved": "https://registry.npmjs.org/@types/aria-query/-/aria-query-5.0.4.tgz", "integrity": "sha512-rfT93uj5s0PRL7EzccGMs3brplhcrghnDoV26NqKhCAS1hVo+WdNsPvE/yb6ilfr5hi2MEk6d5EWJTKdxg8jVw==", "dev": true, - "license": "MIT", - "peer": true + "license": "MIT" }, "node_modules/@types/babel__core": { "version": "7.20.5", @@ -6825,6 +6830,7 @@ "integrity": "sha512-m0jEgYlYz+mDJZ2+F4v8D1AyQb+QzsNqRuI7xg1VQX/KlKS0qT9r1Mo16yo5F/MtifXFgaofIFsdFMox2SxIbQ==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "undici-types": "~7.16.0" } @@ -6866,6 +6872,7 @@ "resolved": "https://registry.npmjs.org/@types/react/-/react-19.2.14.tgz", "integrity": "sha512-ilcTH/UniCkMdtexkoCN0bI7pMcJDvmQFPvuPvmEaYA/NSfFTAgdUSLAoVjaRJm7+6PvcM+q1zYOwS4wTYMF9w==", "license": "MIT", + "peer": true, "dependencies": { "csstype": "^3.2.2" } @@ -6876,6 +6883,7 @@ "integrity": "sha512-jp2L/eY6fn+KgVVQAOqYItbF0VY/YApe5Mz2F0aykSO8gx31bYCZyvSeYxCHKvzHG5eZjc+zyaS5BrBWya2+kQ==", "devOptional": true, "license": "MIT", + "peer": true, "peerDependencies": { "@types/react": "^19.2.0" } @@ -7016,6 +7024,7 @@ "integrity": "sha512-4z2nCSBfVIMnbuu8uinj+f0o4qOeggYJLbjpPHka3KH1om7e+H9yLKTYgksTaHcGco+NClhhY2vyO3HsMH1RGw==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "@typescript-eslint/scope-manager": "8.55.0", "@typescript-eslint/types": "8.55.0", @@ -7401,6 +7410,7 @@ "integrity": "sha512-CGJ25bc8fRi8Lod/3GHSvXRKi7nBo3kxh0ApW4yCjmrWmRmlT53B5E08XRSZRliygG0aVNxLrBEqPYdz/KcCtQ==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "@vitest/utils": "4.0.18", "fflate": "^0.8.2", @@ -7649,6 +7659,7 @@ "integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==", "dev": true, "license": "MIT", + "peer": true, "bin": { "acorn": "bin/acorn" }, @@ -7721,6 +7732,7 @@ "resolved": "https://registry.npmjs.org/ajv/-/ajv-8.17.1.tgz", "integrity": "sha512-B/gBuNg5SiMTrPkC+A2+cW0RszwxYmn6VYxB/inlBStS5nx6xHIt/ehKRhIMhqusl7a8LjQoZnjCs5vhwxOQ1g==", "license": "MIT", + "peer": true, "dependencies": { "fast-deep-equal": "^3.1.3", "fast-uri": "^3.0.1", @@ -8261,6 +8273,7 @@ } ], "license": "MIT", + "peer": true, "dependencies": { "baseline-browser-mapping": "^2.9.0", "caniuse-lite": "^1.0.30001759", @@ -9563,8 +9576,7 @@ "resolved": "https://registry.npmjs.org/dom-accessibility-api/-/dom-accessibility-api-0.5.16.tgz", "integrity": "sha512-X7BJ2yElsnOJ30pZF4uIIDfBEVgF4XEBxL9Bxhy6dnrm5hkzqmsWHGTiHqRiITNhMyFLyAiWndIJP7Z1NTteDg==", "dev": true, - "license": "MIT", - "peer": true + "license": "MIT" }, "node_modules/dom-helpers": { "version": "5.2.1", @@ -9622,6 +9634,7 @@ "dev": true, "hasInstallScript": true, "license": "MIT", + "peer": true, "dependencies": { "@electron/get": "^2.0.0", "@types/node": "^24.9.0", @@ -10629,6 +10642,7 @@ "integrity": "sha512-LEyamqS7W5HB3ujJyvi0HQK/dtVINZvd5mAAp9eT5S/ujByGjiZLCzPcHVzuXbpJDJF/cxwHlfceVUDZ2lnSTw==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "@eslint-community/eslint-utils": "^4.8.0", "@eslint-community/regexpp": "^4.12.1", @@ -11112,6 +11126,7 @@ "resolved": "https://registry.npmjs.org/express/-/express-5.2.1.tgz", "integrity": "sha512-hIS4idWWai69NezIdRt2xFVofaF4j+6INOpJlVOLDO8zXGpUVEVzIYk12UUi2JzjEzWL3IOAxcTubgz9Po0yXw==", "license": "MIT", + "peer": true, "dependencies": { "accepts": "^2.0.0", "body-parser": "^2.2.1", @@ -12372,6 +12387,7 @@ "resolved": "https://registry.npmjs.org/hono/-/hono-4.12.0.tgz", "integrity": "sha512-NekXntS5M94pUfiVZ8oXXK/kkri+5WpX2/Ik+LVsl+uvw+soj4roXIsPqO+XsWrAw20mOzaXOZf3Q7PfB9A/IA==", "license": "MIT", + "peer": true, "engines": { "node": ">=16.9.0" } @@ -13428,6 +13444,7 @@ "integrity": "sha512-KDYJgZ6T2TKdU8yBfYueq5EPG/EylMsBvCaenWMJb2OXmjgczzwveRCoJ+Hgj1lXPDyasvrgneSn4GBuR1hYyA==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "@acemir/cssom": "^0.9.31", "@asamuzakjp/dom-selector": "^6.7.6", @@ -14670,7 +14687,6 @@ "integrity": "sha512-h5bgJWpxJNswbU7qCrV0tIKQCaS3blPDrqKWx+QxzuzL1zGUzij9XCWLrSLsJPu5t+eWA/ycetzYAO5IOMcWAQ==", "dev": true, "license": "MIT", - "peer": true, "bin": { "lz-string": "bin/bin.js" } @@ -14691,6 +14707,7 @@ "integrity": "sha512-E3ZJh4J3S9KfwdjZhe2afj6R9lGIN5Pher1pF39UGrXRqq/VDaGVIGN13BjHd2u8B61hArAGOnso7nBOouW3TQ==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "@babel/parser": "^7.29.0", "@babel/types": "^7.29.0", @@ -17081,6 +17098,7 @@ } ], "license": "MIT", + "peer": true, "dependencies": { "nanoid": "^3.3.11", "picocolors": "^1.1.1", @@ -17182,7 +17200,6 @@ "integrity": "sha512-Qb1gy5OrP5+zDf2Bvnzdl3jsTf1qXVMazbvCoKhtKqVs4/YK4ozX4gKQJJVyNe+cajNPn0KoC0MC3FUmaHWEmQ==", "dev": true, "license": "MIT", - "peer": true, "dependencies": { "ansi-regex": "^5.0.1", "ansi-styles": "^5.0.0", @@ -17198,7 +17215,6 @@ "integrity": "sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA==", "dev": true, "license": "MIT", - "peer": true, "engines": { "node": ">=10" }, @@ -17554,6 +17570,7 @@ "resolved": "https://registry.npmjs.org/react/-/react-19.2.4.tgz", "integrity": "sha512-9nfp2hYpCwOjAN+8TZFGhtWEwgvWHXqESH8qT89AT/lWklpLON22Lc8pEtnpsZz7VmawabSU0gCjnj8aC0euHQ==", "license": "MIT", + "peer": true, "engines": { "node": ">=0.10.0" } @@ -17563,6 +17580,7 @@ "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.2.4.tgz", "integrity": "sha512-AXJdLo8kgMbimY95O2aKQqsz2iWi9jMgKJhRBAxECE4IFxfcazB2LmzloIoibJI3C12IlY20+KFaLv+71bUJeQ==", "license": "MIT", + "peer": true, "dependencies": { "scheduler": "^0.27.0" }, @@ -17584,8 +17602,7 @@ "resolved": "https://registry.npmjs.org/react-is/-/react-is-17.0.2.tgz", "integrity": "sha512-w2GsyukL62IJnlaff/nRegPQR94C/XXamvMWmSHRJ4y7Ts/4ocGRmTHvOs8PSE6pB3dWOrD/nueuU5sduBsQ4w==", "dev": true, - "license": "MIT", - "peer": true + "license": "MIT" }, "node_modules/react-markdown": { "version": "10.1.0", @@ -19502,7 +19519,8 @@ "version": "4.1.18", "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-4.1.18.tgz", "integrity": "sha512-4+Z+0yiYyEtUVCScyfHCxOYP06L5Ne+JiHhY2IjR2KWMIWhJOYZKLSGZaP5HkZ8+bY0cxfzwDE5uOmzFXyIwxw==", - "license": "MIT" + "license": "MIT", + "peer": true }, "node_modules/tailwindcss-animate": { "version": "1.0.7", @@ -20033,6 +20051,7 @@ "integrity": "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==", "dev": true, "license": "Apache-2.0", + "peer": true, "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" @@ -20457,6 +20476,7 @@ "integrity": "sha512-w+N7Hifpc3gRjZ63vYBXA56dvvRlNWRczTdmCBBa+CotUzAPf5b7YMdMR/8CQoeYE5LX3W4wj6RYTgonm1b9DA==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "esbuild": "^0.27.0", "fdir": "^6.5.0", @@ -20547,6 +20567,7 @@ "integrity": "sha512-hOQuK7h0FGKgBAas7v0mSAsnvrIgAvWmRFjmzpJ7SwFHH3g1k2u37JtYwOwmEKhK6ZO3v9ggDBBm0La1LCK4uQ==", "dev": true, "license": "MIT", + "peer": true, "dependencies": { "@vitest/expect": "4.0.18", "@vitest/mocker": "4.0.18", @@ -21195,6 +21216,7 @@ "resolved": "https://registry.npmjs.org/zod/-/zod-3.25.76.tgz", "integrity": "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ==", "license": "MIT", + "peer": true, "funding": { "url": "https://github.com/sponsors/colinhacks" } diff --git a/ui/desktop/src/api/index.ts b/ui/desktop/src/api/index.ts index 2e65e54472..8af4598d0e 100644 --- a/ui/desktop/src/api/index.ts +++ b/ui/desktop/src/api/index.ts @@ -1,4 +1,4 @@ // This file is auto-generated by @hey-api/openapi-ts -export { addExtension, agentAddExtension, agentRemoveExtension, backupConfig, callTool, cancelDownload, cancelLocalModelDownload, checkProvider, configureProviderOauth, confirmToolAction, createCustomProvider, createRecipe, createSchedule, decodeRecipe, deleteLocalModel, deleteModel, deleteRecipe, deleteSchedule, deleteSession, detectProvider, diagnostics, downloadHfModel, downloadModel, encodeRecipe, exportApp, exportSession, forkSession, getCanonicalModelInfo, getCustomProvider, getDictationConfig, getDownloadProgress, getExtensions, getLocalModelDownloadProgress, getModelSettings, getPrompt, getPrompts, getProviderModels, getRepoFiles, getSession, getSessionExtensions, getSessionInsights, getSlashCommands, getTools, getTunnelStatus, importApp, importSession, initConfig, inspectRunningJob, killRunningJob, listApps, listLocalModels, listModels, listRecipes, listSchedules, listSessions, mcpUiProxy, type Options, parseRecipe, pauseSchedule, providers, readAllConfig, readConfig, readResource, recipeToYaml, recoverConfig, removeConfig, removeCustomProvider, removeExtension, reply, resetPrompt, restartAgent, resumeAgent, runNowHandler, savePrompt, saveRecipe, scanRecipe, scheduleRecipe, searchHfModels, searchSessions, sendTelemetryEvent, sessionsHandler, setConfigProvider, setRecipeSlashCommand, startAgent, startOpenrouterSetup, startTetrateSetup, startTunnel, status, stopAgent, stopTunnel, systemInfo, transcribeDictation, unpauseSchedule, updateAgentProvider, updateCustomProvider, updateFromSession, updateModelSettings, updateSchedule, updateSessionName, updateSessionUserRecipeValues, updateWorkingDir, upsertConfig, upsertPermissions, validateConfig } from './sdk.gen'; -export type { ActionRequired, ActionRequiredData, AddExtensionData, AddExtensionErrors, AddExtensionRequest, AddExtensionResponse, AddExtensionResponses, AgentAddExtensionData, AgentAddExtensionErrors, AgentAddExtensionResponse, AgentAddExtensionResponses, AgentRemoveExtensionData, AgentRemoveExtensionErrors, AgentRemoveExtensionResponse, AgentRemoveExtensionResponses, Annotations, Author, AuthorRequest, BackupConfigData, BackupConfigErrors, BackupConfigResponse, BackupConfigResponses, CallToolData, CallToolErrors, CallToolRequest, CallToolResponse, CallToolResponse2, CallToolResponses, CancelDownloadData, CancelDownloadErrors, CancelDownloadResponses, CancelLocalModelDownloadData, CancelLocalModelDownloadErrors, CancelLocalModelDownloadResponses, ChatRequest, CheckProviderData, CheckProviderRequest, ClientOptions, CommandType, ConfigKey, ConfigKeyQuery, ConfigResponse, ConfigureProviderOauthData, ConfigureProviderOauthErrors, ConfigureProviderOauthResponses, ConfirmToolActionData, ConfirmToolActionErrors, ConfirmToolActionRequest, ConfirmToolActionResponses, Content, Conversation, CreateCustomProviderData, CreateCustomProviderErrors, CreateCustomProviderResponse, CreateCustomProviderResponses, CreateRecipeData, CreateRecipeErrors, CreateRecipeRequest, CreateRecipeResponse, CreateRecipeResponse2, CreateRecipeResponses, CreateScheduleData, CreateScheduleErrors, CreateScheduleRequest, CreateScheduleResponse, CreateScheduleResponses, CspMetadata, DeclarativeProviderConfig, DecodeRecipeData, DecodeRecipeErrors, DecodeRecipeRequest, DecodeRecipeResponse, DecodeRecipeResponse2, DecodeRecipeResponses, DeleteLocalModelData, DeleteLocalModelErrors, DeleteLocalModelResponses, DeleteModelData, DeleteModelErrors, DeleteModelResponses, DeleteRecipeData, DeleteRecipeErrors, DeleteRecipeRequest, DeleteRecipeResponse, DeleteRecipeResponses, DeleteScheduleData, DeleteScheduleErrors, DeleteScheduleResponse, DeleteScheduleResponses, DeleteSessionData, DeleteSessionErrors, DeleteSessionResponses, DetectProviderData, DetectProviderErrors, DetectProviderRequest, DetectProviderResponse, DetectProviderResponse2, DetectProviderResponses, DiagnosticsData, DiagnosticsErrors, DiagnosticsResponse, DiagnosticsResponses, DictationProvider, DictationProviderStatus, DownloadHfModelData, DownloadHfModelErrors, DownloadHfModelResponse, DownloadHfModelResponses, DownloadModelData, DownloadModelErrors, DownloadModelRequest, DownloadModelResponses, DownloadProgress, DownloadStatus, EmbeddedResource, EncodeRecipeData, EncodeRecipeErrors, EncodeRecipeRequest, EncodeRecipeResponse, EncodeRecipeResponse2, EncodeRecipeResponses, Envs, ErrorResponse, ExportAppData, ExportAppError, ExportAppErrors, ExportAppResponse, ExportAppResponses, ExportSessionData, ExportSessionErrors, ExportSessionResponse, ExportSessionResponses, ExtensionConfig, ExtensionData, ExtensionEntry, ExtensionLoadResult, ExtensionQuery, ExtensionResponse, ForkRequest, ForkResponse, ForkSessionData, ForkSessionErrors, ForkSessionResponse, ForkSessionResponses, FrontendToolRequest, GetCanonicalModelInfoData, GetCanonicalModelInfoResponse, GetCanonicalModelInfoResponses, GetCustomProviderData, GetCustomProviderErrors, GetCustomProviderResponse, GetCustomProviderResponses, GetDictationConfigData, GetDictationConfigResponse, GetDictationConfigResponses, GetDownloadProgressData, GetDownloadProgressErrors, GetDownloadProgressResponse, GetDownloadProgressResponses, GetExtensionsData, GetExtensionsErrors, GetExtensionsResponse, GetExtensionsResponses, GetLocalModelDownloadProgressData, GetLocalModelDownloadProgressErrors, GetLocalModelDownloadProgressResponse, GetLocalModelDownloadProgressResponses, GetModelSettingsData, GetModelSettingsErrors, GetModelSettingsResponse, GetModelSettingsResponses, GetPromptData, GetPromptErrors, GetPromptResponse, GetPromptResponses, GetPromptsData, GetPromptsResponse, GetPromptsResponses, GetProviderModelsData, GetProviderModelsErrors, GetProviderModelsResponse, GetProviderModelsResponses, GetRepoFilesData, GetRepoFilesResponse, GetRepoFilesResponses, GetSessionData, GetSessionErrors, GetSessionExtensionsData, GetSessionExtensionsErrors, GetSessionExtensionsResponse, GetSessionExtensionsResponses, GetSessionInsightsData, GetSessionInsightsErrors, GetSessionInsightsResponse, GetSessionInsightsResponses, GetSessionResponse, GetSessionResponses, GetSlashCommandsData, GetSlashCommandsResponse, GetSlashCommandsResponses, GetToolsData, GetToolsErrors, GetToolsQuery, GetToolsResponse, GetToolsResponses, GetTunnelStatusData, GetTunnelStatusResponse, GetTunnelStatusResponses, GooseApp, HfGgufFile, HfModelInfo, HfQuantVariant, Icon, ImageContent, ImportAppData, ImportAppError, ImportAppErrors, ImportAppRequest, ImportAppResponse, ImportAppResponse2, ImportAppResponses, ImportSessionData, ImportSessionErrors, ImportSessionRequest, ImportSessionResponse, ImportSessionResponses, InitConfigData, InitConfigErrors, InitConfigResponse, InitConfigResponses, InspectJobResponse, InspectRunningJobData, InspectRunningJobErrors, InspectRunningJobResponse, InspectRunningJobResponses, JsonObject, KillJobResponse, KillRunningJobData, KillRunningJobResponses, ListAppsData, ListAppsError, ListAppsErrors, ListAppsRequest, ListAppsResponse, ListAppsResponse2, ListAppsResponses, ListLocalModelsData, ListLocalModelsResponse, ListLocalModelsResponses, ListModelsData, ListModelsResponse, ListModelsResponses, ListRecipeResponse, ListRecipesData, ListRecipesErrors, ListRecipesResponse, ListRecipesResponses, ListSchedulesData, ListSchedulesErrors, ListSchedulesResponse, ListSchedulesResponse2, ListSchedulesResponses, ListSessionsData, ListSessionsErrors, ListSessionsResponse, ListSessionsResponses, LoadedProvider, LocalModelResponse, McpAppResource, McpUiProxyData, McpUiProxyErrors, McpUiProxyResponses, Message, MessageContent, MessageEvent, MessageMetadata, ModelConfig, ModelDownloadStatus, ModelInfo, ModelInfoData, ModelInfoQuery, ModelInfoResponse, ModelSettings, ParseRecipeData, ParseRecipeError, ParseRecipeErrors, ParseRecipeRequest, ParseRecipeResponse, ParseRecipeResponse2, ParseRecipeResponses, PauseScheduleData, PauseScheduleErrors, PauseScheduleResponse, PauseScheduleResponses, Permission, PermissionLevel, PermissionsMetadata, PrincipalType, PromptContentResponse, PromptsListResponse, ProviderDetails, ProviderEngine, ProviderMetadata, ProvidersData, ProvidersResponse, ProvidersResponse2, ProvidersResponses, ProviderType, RawAudioContent, RawEmbeddedResource, RawImageContent, RawResource, RawTextContent, ReadAllConfigData, ReadAllConfigResponse, ReadAllConfigResponses, ReadConfigData, ReadConfigErrors, ReadConfigResponses, ReadResourceData, ReadResourceErrors, ReadResourceRequest, ReadResourceResponse, ReadResourceResponse2, ReadResourceResponses, ReasoningContent, Recipe, RecipeManifest, RecipeParameter, RecipeParameterInputType, RecipeParameterRequirement, RecipeToYamlData, RecipeToYamlError, RecipeToYamlErrors, RecipeToYamlRequest, RecipeToYamlResponse, RecipeToYamlResponse2, RecipeToYamlResponses, RecoverConfigData, RecoverConfigErrors, RecoverConfigResponse, RecoverConfigResponses, RedactedThinkingContent, RemoveConfigData, RemoveConfigErrors, RemoveConfigResponse, RemoveConfigResponses, RemoveCustomProviderData, RemoveCustomProviderErrors, RemoveCustomProviderResponse, RemoveCustomProviderResponses, RemoveExtensionData, RemoveExtensionErrors, RemoveExtensionRequest, RemoveExtensionResponse, RemoveExtensionResponses, ReplyData, ReplyErrors, ReplyResponse, ReplyResponses, RepoVariantsResponse, ResetPromptData, ResetPromptErrors, ResetPromptResponse, ResetPromptResponses, ResourceContents, ResourceMetadata, Response, RestartAgentData, RestartAgentErrors, RestartAgentRequest, RestartAgentResponse, RestartAgentResponse2, RestartAgentResponses, ResumeAgentData, ResumeAgentErrors, ResumeAgentRequest, ResumeAgentResponse, ResumeAgentResponse2, ResumeAgentResponses, RetryConfig, Role, RunNowHandlerData, RunNowHandlerErrors, RunNowHandlerResponse, RunNowHandlerResponses, RunNowResponse, SamplingConfig, SavePromptData, SavePromptErrors, SavePromptRequest, SavePromptResponse, SavePromptResponses, SaveRecipeData, SaveRecipeError, SaveRecipeErrors, SaveRecipeRequest, SaveRecipeResponse, SaveRecipeResponse2, SaveRecipeResponses, ScanRecipeData, ScanRecipeRequest, ScanRecipeResponse, ScanRecipeResponse2, ScanRecipeResponses, ScheduledJob, ScheduleRecipeData, ScheduleRecipeErrors, ScheduleRecipeRequest, ScheduleRecipeResponses, SearchHfModelsData, SearchHfModelsErrors, SearchHfModelsResponse, SearchHfModelsResponses, SearchSessionsData, SearchSessionsErrors, SearchSessionsResponse, SearchSessionsResponses, SendTelemetryEventData, SendTelemetryEventResponses, Session, SessionDisplayInfo, SessionExtensionsResponse, SessionInsights, SessionListResponse, SessionsHandlerData, SessionsHandlerErrors, SessionsHandlerResponse, SessionsHandlerResponses, SessionsQuery, SessionType, SetConfigProviderData, SetProviderRequest, SetRecipeSlashCommandData, SetRecipeSlashCommandErrors, SetRecipeSlashCommandResponses, SetSlashCommandRequest, Settings, SetupResponse, SlashCommand, SlashCommandsResponse, StartAgentData, StartAgentError, StartAgentErrors, StartAgentRequest, StartAgentResponse, StartAgentResponses, StartOpenrouterSetupData, StartOpenrouterSetupResponse, StartOpenrouterSetupResponses, StartTetrateSetupData, StartTetrateSetupResponse, StartTetrateSetupResponses, StartTunnelData, StartTunnelError, StartTunnelErrors, StartTunnelResponse, StartTunnelResponses, StatusData, StatusResponse, StatusResponses, StopAgentData, StopAgentErrors, StopAgentRequest, StopAgentResponse, StopAgentResponses, StopTunnelData, StopTunnelError, StopTunnelErrors, StopTunnelResponses, SubRecipe, SuccessCheck, SystemInfo, SystemInfoData, SystemInfoResponse, SystemInfoResponses, SystemNotificationContent, SystemNotificationType, TaskSupport, TelemetryEventRequest, Template, TextContent, ThinkingContent, TokenState, Tool, ToolAnnotations, ToolConfirmationRequest, ToolExecution, ToolInfo, ToolPermission, ToolRequest, ToolResponse, TranscribeDictationData, TranscribeDictationErrors, TranscribeDictationResponse, TranscribeDictationResponses, TranscribeRequest, TranscribeResponse, TunnelInfo, TunnelState, UiMetadata, UnpauseScheduleData, UnpauseScheduleErrors, UnpauseScheduleResponse, UnpauseScheduleResponses, UpdateAgentProviderData, UpdateAgentProviderErrors, UpdateAgentProviderResponses, UpdateCustomProviderData, UpdateCustomProviderErrors, UpdateCustomProviderRequest, UpdateCustomProviderResponse, UpdateCustomProviderResponses, UpdateFromSessionData, UpdateFromSessionErrors, UpdateFromSessionRequest, UpdateFromSessionResponses, UpdateModelSettingsData, UpdateModelSettingsErrors, UpdateModelSettingsResponse, UpdateModelSettingsResponses, UpdateProviderRequest, UpdateScheduleData, UpdateScheduleErrors, UpdateScheduleRequest, UpdateScheduleResponse, UpdateScheduleResponses, UpdateSessionNameData, UpdateSessionNameErrors, UpdateSessionNameRequest, UpdateSessionNameResponses, UpdateSessionUserRecipeValuesData, UpdateSessionUserRecipeValuesError, UpdateSessionUserRecipeValuesErrors, UpdateSessionUserRecipeValuesRequest, UpdateSessionUserRecipeValuesResponse, UpdateSessionUserRecipeValuesResponse2, UpdateSessionUserRecipeValuesResponses, UpdateWorkingDirData, UpdateWorkingDirErrors, UpdateWorkingDirRequest, UpdateWorkingDirResponses, UpsertConfigData, UpsertConfigErrors, UpsertConfigQuery, UpsertConfigResponse, UpsertConfigResponses, UpsertPermissionsData, UpsertPermissionsErrors, UpsertPermissionsQuery, UpsertPermissionsResponse, UpsertPermissionsResponses, ValidateConfigData, ValidateConfigErrors, ValidateConfigResponse, ValidateConfigResponses, WhisperModelResponse, WindowProps } from './types.gen'; +export { addExtension, agentAddExtension, agentRemoveExtension, backupConfig, callTool, cancelDownload, cancelLocalModelDownload, checkProvider, configureProviderOauth, confirmToolAction, createCustomProvider, createRecipe, createSchedule, decodeRecipe, deleteLocalModel, deleteModel, deleteRecipe, deleteSchedule, deleteSession, detectProvider, diagnostics, downloadHfModel, downloadModel, encodeRecipe, exportApp, exportSession, forkSession, getCanonicalModelInfo, getCustomProvider, getDictationConfig, getDownloadProgress, getExtensions, getLocalModelDownloadProgress, getModelSettings, getPrompt, getPrompts, getProviderCatalog, getProviderCatalogTemplate, getProviderModels, getRepoFiles, getSession, getSessionExtensions, getSessionInsights, getSlashCommands, getTools, getTunnelStatus, importApp, importSession, initConfig, inspectRunningJob, killRunningJob, listApps, listLocalModels, listModels, listRecipes, listSchedules, listSessions, mcpUiProxy, type Options, parseRecipe, pauseSchedule, providers, readAllConfig, readConfig, readResource, recipeToYaml, recoverConfig, removeConfig, removeCustomProvider, removeExtension, reply, resetPrompt, restartAgent, resumeAgent, runNowHandler, savePrompt, saveRecipe, scanRecipe, scheduleRecipe, searchHfModels, searchSessions, sendTelemetryEvent, sessionsHandler, setConfigProvider, setRecipeSlashCommand, startAgent, startOpenrouterSetup, startTetrateSetup, startTunnel, status, stopAgent, stopTunnel, systemInfo, transcribeDictation, unpauseSchedule, updateAgentProvider, updateCustomProvider, updateFromSession, updateModelSettings, updateSchedule, updateSessionName, updateSessionUserRecipeValues, updateWorkingDir, upsertConfig, upsertPermissions, validateConfig } from './sdk.gen'; +export type { ActionRequired, ActionRequiredData, AddExtensionData, AddExtensionErrors, AddExtensionRequest, AddExtensionResponse, AddExtensionResponses, AgentAddExtensionData, AgentAddExtensionErrors, AgentAddExtensionResponse, AgentAddExtensionResponses, AgentRemoveExtensionData, AgentRemoveExtensionErrors, AgentRemoveExtensionResponse, AgentRemoveExtensionResponses, Annotations, Author, AuthorRequest, BackupConfigData, BackupConfigErrors, BackupConfigResponse, BackupConfigResponses, CallToolData, CallToolErrors, CallToolRequest, CallToolResponse, CallToolResponse2, CallToolResponses, CancelDownloadData, CancelDownloadErrors, CancelDownloadResponses, CancelLocalModelDownloadData, CancelLocalModelDownloadErrors, CancelLocalModelDownloadResponses, ChatRequest, CheckProviderData, CheckProviderRequest, ClientOptions, CommandType, ConfigKey, ConfigKeyQuery, ConfigResponse, ConfigureProviderOauthData, ConfigureProviderOauthErrors, ConfigureProviderOauthResponses, ConfirmToolActionData, ConfirmToolActionErrors, ConfirmToolActionRequest, ConfirmToolActionResponses, Content, Conversation, CreateCustomProviderData, CreateCustomProviderErrors, CreateCustomProviderResponse, CreateCustomProviderResponses, CreateRecipeData, CreateRecipeErrors, CreateRecipeRequest, CreateRecipeResponse, CreateRecipeResponse2, CreateRecipeResponses, CreateScheduleData, CreateScheduleErrors, CreateScheduleRequest, CreateScheduleResponse, CreateScheduleResponses, CspMetadata, DeclarativeProviderConfig, DecodeRecipeData, DecodeRecipeErrors, DecodeRecipeRequest, DecodeRecipeResponse, DecodeRecipeResponse2, DecodeRecipeResponses, DeleteLocalModelData, DeleteLocalModelErrors, DeleteLocalModelResponses, DeleteModelData, DeleteModelErrors, DeleteModelResponses, DeleteRecipeData, DeleteRecipeErrors, DeleteRecipeRequest, DeleteRecipeResponse, DeleteRecipeResponses, DeleteScheduleData, DeleteScheduleErrors, DeleteScheduleResponse, DeleteScheduleResponses, DeleteSessionData, DeleteSessionErrors, DeleteSessionResponses, DetectProviderData, DetectProviderErrors, DetectProviderRequest, DetectProviderResponse, DetectProviderResponse2, DetectProviderResponses, DiagnosticsData, DiagnosticsErrors, DiagnosticsResponse, DiagnosticsResponses, DictationProvider, DictationProviderStatus, DownloadHfModelData, DownloadHfModelErrors, DownloadHfModelResponse, DownloadHfModelResponses, DownloadModelData, DownloadModelErrors, DownloadModelRequest, DownloadModelResponses, DownloadProgress, DownloadStatus, EmbeddedResource, EncodeRecipeData, EncodeRecipeErrors, EncodeRecipeRequest, EncodeRecipeResponse, EncodeRecipeResponse2, EncodeRecipeResponses, Envs, ErrorResponse, ExportAppData, ExportAppError, ExportAppErrors, ExportAppResponse, ExportAppResponses, ExportSessionData, ExportSessionErrors, ExportSessionResponse, ExportSessionResponses, ExtensionConfig, ExtensionData, ExtensionEntry, ExtensionLoadResult, ExtensionQuery, ExtensionResponse, ForkRequest, ForkResponse, ForkSessionData, ForkSessionErrors, ForkSessionResponse, ForkSessionResponses, FrontendToolRequest, GetCanonicalModelInfoData, GetCanonicalModelInfoResponse, GetCanonicalModelInfoResponses, GetCustomProviderData, GetCustomProviderErrors, GetCustomProviderResponse, GetCustomProviderResponses, GetDictationConfigData, GetDictationConfigResponse, GetDictationConfigResponses, GetDownloadProgressData, GetDownloadProgressErrors, GetDownloadProgressResponse, GetDownloadProgressResponses, GetExtensionsData, GetExtensionsErrors, GetExtensionsResponse, GetExtensionsResponses, GetLocalModelDownloadProgressData, GetLocalModelDownloadProgressErrors, GetLocalModelDownloadProgressResponse, GetLocalModelDownloadProgressResponses, GetModelSettingsData, GetModelSettingsErrors, GetModelSettingsResponse, GetModelSettingsResponses, GetPromptData, GetPromptErrors, GetPromptResponse, GetPromptResponses, GetPromptsData, GetPromptsResponse, GetPromptsResponses, GetProviderCatalogData, GetProviderCatalogErrors, GetProviderCatalogResponse, GetProviderCatalogResponses, GetProviderCatalogTemplateData, GetProviderCatalogTemplateErrors, GetProviderCatalogTemplateResponse, GetProviderCatalogTemplateResponses, GetProviderModelsData, GetProviderModelsErrors, GetProviderModelsResponse, GetProviderModelsResponses, GetRepoFilesData, GetRepoFilesResponse, GetRepoFilesResponses, GetSessionData, GetSessionErrors, GetSessionExtensionsData, GetSessionExtensionsErrors, GetSessionExtensionsResponse, GetSessionExtensionsResponses, GetSessionInsightsData, GetSessionInsightsErrors, GetSessionInsightsResponse, GetSessionInsightsResponses, GetSessionResponse, GetSessionResponses, GetSlashCommandsData, GetSlashCommandsResponse, GetSlashCommandsResponses, GetToolsData, GetToolsErrors, GetToolsQuery, GetToolsResponse, GetToolsResponses, GetTunnelStatusData, GetTunnelStatusResponse, GetTunnelStatusResponses, GooseApp, HfGgufFile, HfModelInfo, HfQuantVariant, Icon, ImageContent, ImportAppData, ImportAppError, ImportAppErrors, ImportAppRequest, ImportAppResponse, ImportAppResponse2, ImportAppResponses, ImportSessionData, ImportSessionErrors, ImportSessionRequest, ImportSessionResponse, ImportSessionResponses, InitConfigData, InitConfigErrors, InitConfigResponse, InitConfigResponses, InspectJobResponse, InspectRunningJobData, InspectRunningJobErrors, InspectRunningJobResponse, InspectRunningJobResponses, JsonObject, KillJobResponse, KillRunningJobData, KillRunningJobResponses, ListAppsData, ListAppsError, ListAppsErrors, ListAppsRequest, ListAppsResponse, ListAppsResponse2, ListAppsResponses, ListLocalModelsData, ListLocalModelsResponse, ListLocalModelsResponses, ListModelsData, ListModelsResponse, ListModelsResponses, ListRecipeResponse, ListRecipesData, ListRecipesErrors, ListRecipesResponse, ListRecipesResponses, ListSchedulesData, ListSchedulesErrors, ListSchedulesResponse, ListSchedulesResponse2, ListSchedulesResponses, ListSessionsData, ListSessionsErrors, ListSessionsResponse, ListSessionsResponses, LoadedProvider, LocalModelResponse, McpAppResource, McpUiProxyData, McpUiProxyErrors, McpUiProxyResponses, Message, MessageContent, MessageEvent, MessageMetadata, ModelCapabilities, ModelConfig, ModelDownloadStatus, ModelInfo, ModelInfoData, ModelInfoQuery, ModelInfoResponse, ModelSettings, ModelTemplate, ParseRecipeData, ParseRecipeError, ParseRecipeErrors, ParseRecipeRequest, ParseRecipeResponse, ParseRecipeResponse2, ParseRecipeResponses, PauseScheduleData, PauseScheduleErrors, PauseScheduleResponse, PauseScheduleResponses, Permission, PermissionLevel, PermissionsMetadata, PrincipalType, PromptContentResponse, PromptsListResponse, ProviderCatalogEntry, ProviderDetails, ProviderEngine, ProviderMetadata, ProvidersData, ProvidersResponse, ProvidersResponse2, ProvidersResponses, ProviderTemplate, ProviderType, RawAudioContent, RawEmbeddedResource, RawImageContent, RawResource, RawTextContent, ReadAllConfigData, ReadAllConfigResponse, ReadAllConfigResponses, ReadConfigData, ReadConfigErrors, ReadConfigResponses, ReadResourceData, ReadResourceErrors, ReadResourceRequest, ReadResourceResponse, ReadResourceResponse2, ReadResourceResponses, ReasoningContent, Recipe, RecipeManifest, RecipeParameter, RecipeParameterInputType, RecipeParameterRequirement, RecipeToYamlData, RecipeToYamlError, RecipeToYamlErrors, RecipeToYamlRequest, RecipeToYamlResponse, RecipeToYamlResponse2, RecipeToYamlResponses, RecoverConfigData, RecoverConfigErrors, RecoverConfigResponse, RecoverConfigResponses, RedactedThinkingContent, RemoveConfigData, RemoveConfigErrors, RemoveConfigResponse, RemoveConfigResponses, RemoveCustomProviderData, RemoveCustomProviderErrors, RemoveCustomProviderResponse, RemoveCustomProviderResponses, RemoveExtensionData, RemoveExtensionErrors, RemoveExtensionRequest, RemoveExtensionResponse, RemoveExtensionResponses, ReplyData, ReplyErrors, ReplyResponse, ReplyResponses, RepoVariantsResponse, ResetPromptData, ResetPromptErrors, ResetPromptResponse, ResetPromptResponses, ResourceContents, ResourceMetadata, Response, RestartAgentData, RestartAgentErrors, RestartAgentRequest, RestartAgentResponse, RestartAgentResponse2, RestartAgentResponses, ResumeAgentData, ResumeAgentErrors, ResumeAgentRequest, ResumeAgentResponse, ResumeAgentResponse2, ResumeAgentResponses, RetryConfig, Role, RunNowHandlerData, RunNowHandlerErrors, RunNowHandlerResponse, RunNowHandlerResponses, RunNowResponse, SamplingConfig, SavePromptData, SavePromptErrors, SavePromptRequest, SavePromptResponse, SavePromptResponses, SaveRecipeData, SaveRecipeError, SaveRecipeErrors, SaveRecipeRequest, SaveRecipeResponse, SaveRecipeResponse2, SaveRecipeResponses, ScanRecipeData, ScanRecipeRequest, ScanRecipeResponse, ScanRecipeResponse2, ScanRecipeResponses, ScheduledJob, ScheduleRecipeData, ScheduleRecipeErrors, ScheduleRecipeRequest, ScheduleRecipeResponses, SearchHfModelsData, SearchHfModelsErrors, SearchHfModelsResponse, SearchHfModelsResponses, SearchSessionsData, SearchSessionsErrors, SearchSessionsResponse, SearchSessionsResponses, SendTelemetryEventData, SendTelemetryEventResponses, Session, SessionDisplayInfo, SessionExtensionsResponse, SessionInsights, SessionListResponse, SessionsHandlerData, SessionsHandlerErrors, SessionsHandlerResponse, SessionsHandlerResponses, SessionsQuery, SessionType, SetConfigProviderData, SetProviderRequest, SetRecipeSlashCommandData, SetRecipeSlashCommandErrors, SetRecipeSlashCommandResponses, SetSlashCommandRequest, Settings, SetupResponse, SlashCommand, SlashCommandsResponse, StartAgentData, StartAgentError, StartAgentErrors, StartAgentRequest, StartAgentResponse, StartAgentResponses, StartOpenrouterSetupData, StartOpenrouterSetupResponse, StartOpenrouterSetupResponses, StartTetrateSetupData, StartTetrateSetupResponse, StartTetrateSetupResponses, StartTunnelData, StartTunnelError, StartTunnelErrors, StartTunnelResponse, StartTunnelResponses, StatusData, StatusResponse, StatusResponses, StopAgentData, StopAgentErrors, StopAgentRequest, StopAgentResponse, StopAgentResponses, StopTunnelData, StopTunnelError, StopTunnelErrors, StopTunnelResponses, SubRecipe, SuccessCheck, SystemInfo, SystemInfoData, SystemInfoResponse, SystemInfoResponses, SystemNotificationContent, SystemNotificationType, TaskSupport, TelemetryEventRequest, Template, TextContent, ThinkingContent, TokenState, Tool, ToolAnnotations, ToolConfirmationRequest, ToolExecution, ToolInfo, ToolPermission, ToolRequest, ToolResponse, TranscribeDictationData, TranscribeDictationErrors, TranscribeDictationResponse, TranscribeDictationResponses, TranscribeRequest, TranscribeResponse, TunnelInfo, TunnelState, UiMetadata, UnpauseScheduleData, UnpauseScheduleErrors, UnpauseScheduleResponse, UnpauseScheduleResponses, UpdateAgentProviderData, UpdateAgentProviderErrors, UpdateAgentProviderResponses, UpdateCustomProviderData, UpdateCustomProviderErrors, UpdateCustomProviderRequest, UpdateCustomProviderResponse, UpdateCustomProviderResponses, UpdateFromSessionData, UpdateFromSessionErrors, UpdateFromSessionRequest, UpdateFromSessionResponses, UpdateModelSettingsData, UpdateModelSettingsErrors, UpdateModelSettingsResponse, UpdateModelSettingsResponses, UpdateProviderRequest, UpdateScheduleData, UpdateScheduleErrors, UpdateScheduleRequest, UpdateScheduleResponse, UpdateScheduleResponses, UpdateSessionNameData, UpdateSessionNameErrors, UpdateSessionNameRequest, UpdateSessionNameResponses, UpdateSessionUserRecipeValuesData, UpdateSessionUserRecipeValuesError, UpdateSessionUserRecipeValuesErrors, UpdateSessionUserRecipeValuesRequest, UpdateSessionUserRecipeValuesResponse, UpdateSessionUserRecipeValuesResponse2, UpdateSessionUserRecipeValuesResponses, UpdateWorkingDirData, UpdateWorkingDirErrors, UpdateWorkingDirRequest, UpdateWorkingDirResponses, UpsertConfigData, UpsertConfigErrors, UpsertConfigQuery, UpsertConfigResponse, UpsertConfigResponses, UpsertPermissionsData, UpsertPermissionsErrors, UpsertPermissionsQuery, UpsertPermissionsResponse, UpsertPermissionsResponses, ValidateConfigData, ValidateConfigErrors, ValidateConfigResponse, ValidateConfigResponses, WhisperModelResponse, WindowProps } from './types.gen'; diff --git a/ui/desktop/src/api/sdk.gen.ts b/ui/desktop/src/api/sdk.gen.ts index da2dc61d4b..bf342dee7e 100644 --- a/ui/desktop/src/api/sdk.gen.ts +++ b/ui/desktop/src/api/sdk.gen.ts @@ -2,7 +2,7 @@ import type { Client, Options as Options2, TDataShape } from './client'; import { client } from './client.gen'; -import type { AddExtensionData, AddExtensionErrors, AddExtensionResponses, AgentAddExtensionData, AgentAddExtensionErrors, AgentAddExtensionResponses, AgentRemoveExtensionData, AgentRemoveExtensionErrors, AgentRemoveExtensionResponses, BackupConfigData, BackupConfigErrors, BackupConfigResponses, CallToolData, CallToolErrors, CallToolResponses, CancelDownloadData, CancelDownloadErrors, CancelDownloadResponses, CancelLocalModelDownloadData, CancelLocalModelDownloadErrors, CancelLocalModelDownloadResponses, CheckProviderData, ConfigureProviderOauthData, ConfigureProviderOauthErrors, ConfigureProviderOauthResponses, ConfirmToolActionData, ConfirmToolActionErrors, ConfirmToolActionResponses, CreateCustomProviderData, CreateCustomProviderErrors, CreateCustomProviderResponses, CreateRecipeData, CreateRecipeErrors, CreateRecipeResponses, CreateScheduleData, CreateScheduleErrors, CreateScheduleResponses, DecodeRecipeData, DecodeRecipeErrors, DecodeRecipeResponses, DeleteLocalModelData, DeleteLocalModelErrors, DeleteLocalModelResponses, DeleteModelData, DeleteModelErrors, DeleteModelResponses, DeleteRecipeData, DeleteRecipeErrors, DeleteRecipeResponses, DeleteScheduleData, DeleteScheduleErrors, DeleteScheduleResponses, DeleteSessionData, DeleteSessionErrors, DeleteSessionResponses, DetectProviderData, DetectProviderErrors, DetectProviderResponses, DiagnosticsData, DiagnosticsErrors, DiagnosticsResponses, DownloadHfModelData, DownloadHfModelErrors, DownloadHfModelResponses, DownloadModelData, DownloadModelErrors, DownloadModelResponses, EncodeRecipeData, EncodeRecipeErrors, EncodeRecipeResponses, ExportAppData, ExportAppErrors, ExportAppResponses, ExportSessionData, ExportSessionErrors, ExportSessionResponses, ForkSessionData, ForkSessionErrors, ForkSessionResponses, GetCanonicalModelInfoData, GetCanonicalModelInfoResponses, GetCustomProviderData, GetCustomProviderErrors, GetCustomProviderResponses, GetDictationConfigData, GetDictationConfigResponses, GetDownloadProgressData, GetDownloadProgressErrors, GetDownloadProgressResponses, GetExtensionsData, GetExtensionsErrors, GetExtensionsResponses, GetLocalModelDownloadProgressData, GetLocalModelDownloadProgressErrors, GetLocalModelDownloadProgressResponses, GetModelSettingsData, GetModelSettingsErrors, GetModelSettingsResponses, GetPromptData, GetPromptErrors, GetPromptResponses, GetPromptsData, GetPromptsResponses, GetProviderModelsData, GetProviderModelsErrors, GetProviderModelsResponses, GetRepoFilesData, GetRepoFilesResponses, GetSessionData, GetSessionErrors, GetSessionExtensionsData, GetSessionExtensionsErrors, GetSessionExtensionsResponses, GetSessionInsightsData, GetSessionInsightsErrors, GetSessionInsightsResponses, GetSessionResponses, GetSlashCommandsData, GetSlashCommandsResponses, GetToolsData, GetToolsErrors, GetToolsResponses, GetTunnelStatusData, GetTunnelStatusResponses, ImportAppData, ImportAppErrors, ImportAppResponses, ImportSessionData, ImportSessionErrors, ImportSessionResponses, InitConfigData, InitConfigErrors, InitConfigResponses, InspectRunningJobData, InspectRunningJobErrors, InspectRunningJobResponses, KillRunningJobData, KillRunningJobResponses, ListAppsData, ListAppsErrors, ListAppsResponses, ListLocalModelsData, ListLocalModelsResponses, ListModelsData, ListModelsResponses, ListRecipesData, ListRecipesErrors, ListRecipesResponses, ListSchedulesData, ListSchedulesErrors, ListSchedulesResponses, ListSessionsData, ListSessionsErrors, ListSessionsResponses, McpUiProxyData, McpUiProxyErrors, McpUiProxyResponses, ParseRecipeData, ParseRecipeErrors, ParseRecipeResponses, PauseScheduleData, PauseScheduleErrors, PauseScheduleResponses, ProvidersData, ProvidersResponses, ReadAllConfigData, ReadAllConfigResponses, ReadConfigData, ReadConfigErrors, ReadConfigResponses, ReadResourceData, ReadResourceErrors, ReadResourceResponses, RecipeToYamlData, RecipeToYamlErrors, RecipeToYamlResponses, RecoverConfigData, RecoverConfigErrors, RecoverConfigResponses, RemoveConfigData, RemoveConfigErrors, RemoveConfigResponses, RemoveCustomProviderData, RemoveCustomProviderErrors, RemoveCustomProviderResponses, RemoveExtensionData, RemoveExtensionErrors, RemoveExtensionResponses, ReplyData, ReplyErrors, ReplyResponses, ResetPromptData, ResetPromptErrors, ResetPromptResponses, RestartAgentData, RestartAgentErrors, RestartAgentResponses, ResumeAgentData, ResumeAgentErrors, ResumeAgentResponses, RunNowHandlerData, RunNowHandlerErrors, RunNowHandlerResponses, SavePromptData, SavePromptErrors, SavePromptResponses, SaveRecipeData, SaveRecipeErrors, SaveRecipeResponses, ScanRecipeData, ScanRecipeResponses, ScheduleRecipeData, ScheduleRecipeErrors, ScheduleRecipeResponses, SearchHfModelsData, SearchHfModelsErrors, SearchHfModelsResponses, SearchSessionsData, SearchSessionsErrors, SearchSessionsResponses, SendTelemetryEventData, SendTelemetryEventResponses, SessionsHandlerData, SessionsHandlerErrors, SessionsHandlerResponses, SetConfigProviderData, SetRecipeSlashCommandData, SetRecipeSlashCommandErrors, SetRecipeSlashCommandResponses, StartAgentData, StartAgentErrors, StartAgentResponses, StartOpenrouterSetupData, StartOpenrouterSetupResponses, StartTetrateSetupData, StartTetrateSetupResponses, StartTunnelData, StartTunnelErrors, StartTunnelResponses, StatusData, StatusResponses, StopAgentData, StopAgentErrors, StopAgentResponses, StopTunnelData, StopTunnelErrors, StopTunnelResponses, SystemInfoData, SystemInfoResponses, TranscribeDictationData, TranscribeDictationErrors, TranscribeDictationResponses, UnpauseScheduleData, UnpauseScheduleErrors, UnpauseScheduleResponses, UpdateAgentProviderData, UpdateAgentProviderErrors, UpdateAgentProviderResponses, UpdateCustomProviderData, UpdateCustomProviderErrors, UpdateCustomProviderResponses, UpdateFromSessionData, UpdateFromSessionErrors, UpdateFromSessionResponses, UpdateModelSettingsData, UpdateModelSettingsErrors, UpdateModelSettingsResponses, UpdateScheduleData, UpdateScheduleErrors, UpdateScheduleResponses, UpdateSessionNameData, UpdateSessionNameErrors, UpdateSessionNameResponses, UpdateSessionUserRecipeValuesData, UpdateSessionUserRecipeValuesErrors, UpdateSessionUserRecipeValuesResponses, UpdateWorkingDirData, UpdateWorkingDirErrors, UpdateWorkingDirResponses, UpsertConfigData, UpsertConfigErrors, UpsertConfigResponses, UpsertPermissionsData, UpsertPermissionsErrors, UpsertPermissionsResponses, ValidateConfigData, ValidateConfigErrors, ValidateConfigResponses } from './types.gen'; +import type { AddExtensionData, AddExtensionErrors, AddExtensionResponses, AgentAddExtensionData, AgentAddExtensionErrors, AgentAddExtensionResponses, AgentRemoveExtensionData, AgentRemoveExtensionErrors, AgentRemoveExtensionResponses, BackupConfigData, BackupConfigErrors, BackupConfigResponses, CallToolData, CallToolErrors, CallToolResponses, CancelDownloadData, CancelDownloadErrors, CancelDownloadResponses, CancelLocalModelDownloadData, CancelLocalModelDownloadErrors, CancelLocalModelDownloadResponses, CheckProviderData, ConfigureProviderOauthData, ConfigureProviderOauthErrors, ConfigureProviderOauthResponses, ConfirmToolActionData, ConfirmToolActionErrors, ConfirmToolActionResponses, CreateCustomProviderData, CreateCustomProviderErrors, CreateCustomProviderResponses, CreateRecipeData, CreateRecipeErrors, CreateRecipeResponses, CreateScheduleData, CreateScheduleErrors, CreateScheduleResponses, DecodeRecipeData, DecodeRecipeErrors, DecodeRecipeResponses, DeleteLocalModelData, DeleteLocalModelErrors, DeleteLocalModelResponses, DeleteModelData, DeleteModelErrors, DeleteModelResponses, DeleteRecipeData, DeleteRecipeErrors, DeleteRecipeResponses, DeleteScheduleData, DeleteScheduleErrors, DeleteScheduleResponses, DeleteSessionData, DeleteSessionErrors, DeleteSessionResponses, DetectProviderData, DetectProviderErrors, DetectProviderResponses, DiagnosticsData, DiagnosticsErrors, DiagnosticsResponses, DownloadHfModelData, DownloadHfModelErrors, DownloadHfModelResponses, DownloadModelData, DownloadModelErrors, DownloadModelResponses, EncodeRecipeData, EncodeRecipeErrors, EncodeRecipeResponses, ExportAppData, ExportAppErrors, ExportAppResponses, ExportSessionData, ExportSessionErrors, ExportSessionResponses, ForkSessionData, ForkSessionErrors, ForkSessionResponses, GetCanonicalModelInfoData, GetCanonicalModelInfoResponses, GetCustomProviderData, GetCustomProviderErrors, GetCustomProviderResponses, GetDictationConfigData, GetDictationConfigResponses, GetDownloadProgressData, GetDownloadProgressErrors, GetDownloadProgressResponses, GetExtensionsData, GetExtensionsErrors, GetExtensionsResponses, GetLocalModelDownloadProgressData, GetLocalModelDownloadProgressErrors, GetLocalModelDownloadProgressResponses, GetModelSettingsData, GetModelSettingsErrors, GetModelSettingsResponses, GetPromptData, GetPromptErrors, GetPromptResponses, GetPromptsData, GetPromptsResponses, GetProviderCatalogData, GetProviderCatalogErrors, GetProviderCatalogResponses, GetProviderCatalogTemplateData, GetProviderCatalogTemplateErrors, GetProviderCatalogTemplateResponses, GetProviderModelsData, GetProviderModelsErrors, GetProviderModelsResponses, GetRepoFilesData, GetRepoFilesResponses, GetSessionData, GetSessionErrors, GetSessionExtensionsData, GetSessionExtensionsErrors, GetSessionExtensionsResponses, GetSessionInsightsData, GetSessionInsightsErrors, GetSessionInsightsResponses, GetSessionResponses, GetSlashCommandsData, GetSlashCommandsResponses, GetToolsData, GetToolsErrors, GetToolsResponses, GetTunnelStatusData, GetTunnelStatusResponses, ImportAppData, ImportAppErrors, ImportAppResponses, ImportSessionData, ImportSessionErrors, ImportSessionResponses, InitConfigData, InitConfigErrors, InitConfigResponses, InspectRunningJobData, InspectRunningJobErrors, InspectRunningJobResponses, KillRunningJobData, KillRunningJobResponses, ListAppsData, ListAppsErrors, ListAppsResponses, ListLocalModelsData, ListLocalModelsResponses, ListModelsData, ListModelsResponses, ListRecipesData, ListRecipesErrors, ListRecipesResponses, ListSchedulesData, ListSchedulesErrors, ListSchedulesResponses, ListSessionsData, ListSessionsErrors, ListSessionsResponses, McpUiProxyData, McpUiProxyErrors, McpUiProxyResponses, ParseRecipeData, ParseRecipeErrors, ParseRecipeResponses, PauseScheduleData, PauseScheduleErrors, PauseScheduleResponses, ProvidersData, ProvidersResponses, ReadAllConfigData, ReadAllConfigResponses, ReadConfigData, ReadConfigErrors, ReadConfigResponses, ReadResourceData, ReadResourceErrors, ReadResourceResponses, RecipeToYamlData, RecipeToYamlErrors, RecipeToYamlResponses, RecoverConfigData, RecoverConfigErrors, RecoverConfigResponses, RemoveConfigData, RemoveConfigErrors, RemoveConfigResponses, RemoveCustomProviderData, RemoveCustomProviderErrors, RemoveCustomProviderResponses, RemoveExtensionData, RemoveExtensionErrors, RemoveExtensionResponses, ReplyData, ReplyErrors, ReplyResponses, ResetPromptData, ResetPromptErrors, ResetPromptResponses, RestartAgentData, RestartAgentErrors, RestartAgentResponses, ResumeAgentData, ResumeAgentErrors, ResumeAgentResponses, RunNowHandlerData, RunNowHandlerErrors, RunNowHandlerResponses, SavePromptData, SavePromptErrors, SavePromptResponses, SaveRecipeData, SaveRecipeErrors, SaveRecipeResponses, ScanRecipeData, ScanRecipeResponses, ScheduleRecipeData, ScheduleRecipeErrors, ScheduleRecipeResponses, SearchHfModelsData, SearchHfModelsErrors, SearchHfModelsResponses, SearchSessionsData, SearchSessionsErrors, SearchSessionsResponses, SendTelemetryEventData, SendTelemetryEventResponses, SessionsHandlerData, SessionsHandlerErrors, SessionsHandlerResponses, SetConfigProviderData, SetRecipeSlashCommandData, SetRecipeSlashCommandErrors, SetRecipeSlashCommandResponses, StartAgentData, StartAgentErrors, StartAgentResponses, StartOpenrouterSetupData, StartOpenrouterSetupResponses, StartTetrateSetupData, StartTetrateSetupResponses, StartTunnelData, StartTunnelErrors, StartTunnelResponses, StatusData, StatusResponses, StopAgentData, StopAgentErrors, StopAgentResponses, StopTunnelData, StopTunnelErrors, StopTunnelResponses, SystemInfoData, SystemInfoResponses, TranscribeDictationData, TranscribeDictationErrors, TranscribeDictationResponses, UnpauseScheduleData, UnpauseScheduleErrors, UnpauseScheduleResponses, UpdateAgentProviderData, UpdateAgentProviderErrors, UpdateAgentProviderResponses, UpdateCustomProviderData, UpdateCustomProviderErrors, UpdateCustomProviderResponses, UpdateFromSessionData, UpdateFromSessionErrors, UpdateFromSessionResponses, UpdateModelSettingsData, UpdateModelSettingsErrors, UpdateModelSettingsResponses, UpdateScheduleData, UpdateScheduleErrors, UpdateScheduleResponses, UpdateSessionNameData, UpdateSessionNameErrors, UpdateSessionNameResponses, UpdateSessionUserRecipeValuesData, UpdateSessionUserRecipeValuesErrors, UpdateSessionUserRecipeValuesResponses, UpdateWorkingDirData, UpdateWorkingDirErrors, UpdateWorkingDirResponses, UpsertConfigData, UpsertConfigErrors, UpsertConfigResponses, UpsertPermissionsData, UpsertPermissionsErrors, UpsertPermissionsResponses, ValidateConfigData, ValidateConfigErrors, ValidateConfigResponses } from './types.gen'; export type Options = Options2 & { /** @@ -233,6 +233,10 @@ export const savePrompt = (options: Option } }); +export const getProviderCatalog = (options?: Options) => (options?.client ?? client).get({ url: '/config/provider-catalog', ...options }); + +export const getProviderCatalogTemplate = (options: Options) => (options.client ?? client).get({ url: '/config/provider-catalog/{id}', ...options }); + export const providers = (options?: Options) => (options?.client ?? client).get({ url: '/config/providers', ...options }); export const getProviderModels = (options: Options) => (options.client ?? client).get({ url: '/config/providers/{name}/models', ...options }); diff --git a/ui/desktop/src/api/types.gen.ts b/ui/desktop/src/api/types.gen.ts index ff0f550475..ea39254cdd 100644 --- a/ui/desktop/src/api/types.gen.ts +++ b/ui/desktop/src/api/types.gen.ts @@ -169,6 +169,7 @@ export type CspMetadata = { export type DeclarativeProviderConfig = { api_key_env?: string; base_url: string; + catalog_provider_id?: string | null; description?: string | null; display_name: string; engine: ProviderEngine; @@ -671,6 +672,13 @@ export type MessageMetadata = { userVisible: boolean; }; +export type ModelCapabilities = { + attachment: boolean; + reasoning: boolean; + temperature: boolean; + tool_call: boolean; +}; + export type ModelConfig = { context_limit?: number | null; max_tokens?: number | null; @@ -767,6 +775,14 @@ export type ModelSettings = { use_mlock?: boolean; }; +export type ModelTemplate = { + capabilities: ModelCapabilities; + context_limit: number; + deprecated: boolean; + id: string; + name: string; +}; + export type ParseRecipeRequest = { content: string; }; @@ -819,6 +835,16 @@ export type PromptsListResponse = { prompts: Array