From 22f49fddc883cc65be947206ccfb57aa78c678a2 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Wed, 13 May 2026 11:48:28 -0400 Subject: [PATCH] chore(release): release version 1.34.1 (patch) (#9185) Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> --- Cargo.lock | 16 +- Cargo.toml | 2 +- .../canonical/data/canonical_models.json | 9166 ++++++++++------- .../canonical/data/provider_metadata.json | 80 +- ui/desktop/openapi.json | 2 +- ui/desktop/package.json | 2 +- 6 files changed, 5457 insertions(+), 3811 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 895705eb89..3824589312 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -4365,7 +4365,7 @@ dependencies = [ [[package]] name = "goose" -version = "1.34.0" +version = "1.34.1" dependencies = [ "agent-client-protocol", "agent-client-protocol-schema", @@ -4492,7 +4492,7 @@ dependencies = [ [[package]] name = "goose-acp-macros" -version = "1.34.0" +version = "1.34.1" dependencies = [ "quote", "syn 2.0.117", @@ -4500,7 +4500,7 @@ dependencies = [ [[package]] name = "goose-cli" -version = "1.34.0" +version = "1.34.1" dependencies = [ "anstream", "anyhow", @@ -4552,7 +4552,7 @@ dependencies = [ [[package]] name = "goose-mcp" -version = "1.34.0" +version = "1.34.1" dependencies = [ "anyhow", "base64 0.22.1", @@ -4582,7 +4582,7 @@ dependencies = [ [[package]] name = "goose-sdk" -version = "1.34.0" +version = "1.34.1" dependencies = [ "agent-client-protocol", "agent-client-protocol-schema", @@ -4595,7 +4595,7 @@ dependencies = [ [[package]] name = "goose-server" -version = "1.34.0" +version = "1.34.1" dependencies = [ "anyhow", "aws-lc-rs", @@ -4643,7 +4643,7 @@ dependencies = [ [[package]] name = "goose-test" -version = "1.34.0" +version = "1.34.1" dependencies = [ "clap", "serde_json", @@ -4651,7 +4651,7 @@ dependencies = [ [[package]] name = "goose-test-support" -version = "1.34.0" +version = "1.34.1" dependencies = [ "axum", "env-lock", diff --git a/Cargo.toml b/Cargo.toml index 25169372af..12bef63790 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -9,7 +9,7 @@ resolver = "2" [workspace.package] edition = "2021" -version = "1.34.0" +version = "1.34.1" rust-version = "1.91.1" authors = ["AAIF "] license = "Apache-2.0" diff --git a/crates/goose/src/providers/canonical/data/canonical_models.json b/crates/goose/src/providers/canonical/data/canonical_models.json index c614ee1a7b..66f4e1f54a 100644 --- a/crates/goose/src/providers/canonical/data/canonical_models.json +++ b/crates/goose/src/providers/canonical/data/canonical_models.json @@ -4729,6 +4729,38 @@ "output": 128000 } }, + { + "id": "aihubmix/claude-opus-4.7-think", + "name": "Claude Opus 4.7 Thinking", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "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-sonnet-4.6", "name": "Claude Sonnet 4.6", @@ -4795,34 +4827,6 @@ "output": 64000 } }, - { - "id": "aihubmix/coding-glm-5-free", - "name": "Coding-GLM-5-Free", - "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 - }, - "limit": { - "context": 204800, - "output": 131072 - } - }, { "id": "aihubmix/coding-glm-5.1", "name": "Coding-GLM-5.1", @@ -4851,6 +4855,63 @@ "output": 128000 } }, + { + "id": "aihubmix/coding-glm-5.1-free", + "name": "Coding GLM 5.1 (free)", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-11", + "last_updated": "2026-04-11", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 204800, + "output": 128000 + } + }, + { + "id": "aihubmix/coding-minimax-m2.7", + "name": "Coding MiniMax M2.7", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 204800, + "output": 13100 + } + }, { "id": "aihubmix/coding-minimax-m2.7-free", "name": "Coding-MiniMax-M2.7-Free", @@ -4879,6 +4940,34 @@ "output": 13100 } }, + { + "id": "aihubmix/coding-minimax-m2.7-highspeed", + "name": "Coding MiniMax M2.7 Highspeed", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.2, + "output": 0.2 + }, + "limit": { + "context": 204800, + "output": 13100 + } + }, { "id": "aihubmix/deepseek-v4-flash", "name": "DeepSeek V4 Flash", @@ -5072,8 +5161,8 @@ } }, { - "id": "aihubmix/gemini-3.1-flash-lite-preview", - "name": "Gemini 3.1 Flash Lite Preview", + "id": "aihubmix/gemini-3.1-flash-lite", + "name": "Gemini 3.1 Flash Lite", "family": "gemini-flash-lite", "attachment": true, "reasoning": true, @@ -5140,32 +5229,37 @@ } }, { - "id": "aihubmix/glm-5", - "name": "GLM-5", - "family": "glm", - "attachment": false, + "id": "aihubmix/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, - "release_date": "2026-02-11", - "last_updated": "2026-02-11", + "knowledge": "2025-01", + "release_date": "2026-02-19", + "last_updated": "2026-02-19", "modalities": { "input": [ - "text" + "text", + "image", + "audio", + "video", + "pdf" ], "output": [ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { - "input": 0.88, - "output": 2.816, - "cache_read": 0.176 + "input": 2.0, + "output": 12.0, + "cache_read": 0.2 }, "limit": { - "context": 202752, - "output": 0 + "context": 1048576, + "output": 65536 } }, { @@ -5197,6 +5291,37 @@ "output": 128000 } }, + { + "id": "aihubmix/glm-5v-turbo", + "name": "GLM 5 Vision Turbo", + "family": "glm", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-05-09", + "last_updated": "2026-05-09", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.7042, + "output": 3.09848, + "cache_read": 0.169008 + }, + "limit": { + "context": 200000, + "output": 128000 + } + }, { "id": "aihubmix/gpt-4.1", "name": "GPT-4.1", @@ -5537,6 +5662,36 @@ "output": 128000 } }, + { + "id": "aihubmix/grok-4.3", + "name": "Grok 4.3", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-05-01", + "last_updated": "2026-05-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 1000000, + "output": 1000000 + } + }, { "id": "aihubmix/kimi-k2.5", "name": "Kimi K2.5", @@ -5601,34 +5756,6 @@ "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": 0.288, - "output": 1.152 - }, - "limit": { - "context": 204800, - "output": 192000 - } - }, { "id": "aihubmix/minimax-m2.7", "name": "MiniMax-M2.7", @@ -5689,104 +5816,11 @@ "output": 100000 } }, - { - "id": "aihubmix/qwen3-coder-next", - "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": 0.137, - "output": 0.548, - "cache_read": 0.137 - }, - "limit": { - "context": 2000000, - "output": 64000 - } - }, - { - "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": 0.34246, - "output": 1.36984, - "cache_read": 0.34246 - }, - "limit": { - "context": 252000, - "output": 32000 - } - }, - { - "id": "aihubmix/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": 0.1096, - "output": 0.6576, - "cache_read": 0.01096, - "cache_write": 0.137 - }, - "limit": { - "context": 991000, - "output": 64000 - } - }, { "id": "aihubmix/qwen3.6-flash", - "name": "Qwen3.6 Plus", + "name": "Qwen3.6 Flash", "family": "qwen", - "attachment": false, + "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, @@ -5811,8 +5845,72 @@ "cache_write": 0.21125 }, "limit": { - "context": 1000000, - "output": 65536 + "context": 991000, + "output": 64000 + } + }, + { + "id": "aihubmix/qwen3.6-max-preview", + "name": "Qwen3.6 Max Preview", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-05-09", + "last_updated": "2026-05-09", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.268, + "output": 7.608, + "cache_read": 0.1268, + "cache_write": 1.585 + }, + "limit": { + "context": 240000, + "output": 64000 + } + }, + { + "id": "aihubmix/qwen3.6-plus", + "name": "Qwen3.6 Plus", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-05-09", + "last_updated": "2026-05-09", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.282, + "output": 1.692, + "cache_read": 0.0282, + "cache_write": 0.3525 + }, + "limit": { + "context": 991000, + "output": 64000 } }, { @@ -7926,10 +8024,10 @@ }, "open_weights": false, "cost": { - "input": 0.276, - "output": 1.651, - "cache_read": 0.028, - "cache_write": 0.344 + "input": 0.5, + "output": 3.0, + "cache_read": 0.05, + "cache_write": 0.625 }, "limit": { "context": 1000000, @@ -10102,10 +10200,10 @@ }, "open_weights": false, "cost": { - "input": 0.276, - "output": 1.651, - "cache_read": 0.028, - "cache_write": 0.344 + "input": 0.5, + "output": 3.0, + "cache_read": 0.05, + "cache_write": 0.625 }, "limit": { "context": 1000000, @@ -10233,37 +10331,6 @@ "output": 8192 } }, - { - "id": "amazon-bedrock/amazon.nova-premier-v1:0", - "name": "Nova Premier", - "family": "nova", - "attachment": true, - "reasoning": true, - "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": 2.5, - "output": 12.5 - }, - "limit": { - "context": 1000000, - "output": 16384 - } - }, { "id": "amazon-bedrock/amazon.nova-pro-v1:0", "name": "Nova Pro", @@ -10296,169 +10363,6 @@ "output": 8192 } }, - { - "id": "amazon-bedrock/anthropic.claude-3-haiku-20240307-v1:0", - "name": "Claude Haiku 3", - "family": "claude-haiku", - "attachment": true, - "reasoning": false, - "tool_call": true, - "temperature": true, - "knowledge": "2024-02", - "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 - }, - "limit": { - "context": 200000, - "output": 4096 - } - }, - { - "id": "amazon-bedrock/anthropic.claude-3.5-haiku-20241022-v1:0", - "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": "amazon-bedrock/anthropic.claude-3.5-sonnet-20240620-v1:0", - "name": "Claude Sonnet 3.5", - "family": "claude-sonnet", - "attachment": true, - "reasoning": false, - "tool_call": true, - "temperature": true, - "knowledge": "2024-04-30", - "release_date": "2024-06-20", - "last_updated": "2024-06-20", - "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": "amazon-bedrock/anthropic.claude-3.5-sonnet-20241022-v2:0", - "name": "Claude Sonnet 3.5 v2", - "family": "claude-sonnet", - "attachment": true, - "reasoning": false, - "tool_call": true, - "temperature": true, - "knowledge": "2024-04", - "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": "amazon-bedrock/anthropic.claude-3.7-sonnet-20250219-v1:0", - "name": "Claude Sonnet 3.7", - "family": "claude-sonnet", - "attachment": true, - "reasoning": false, - "tool_call": true, - "temperature": true, - "knowledge": "2024-04", - "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": 8192 - } - }, { "id": "amazon-bedrock/anthropic.claude-haiku-4.5-20251001-v1:0", "name": "Claude Haiku 4.5", @@ -10492,39 +10396,6 @@ "output": 64000 } }, - { - "id": "amazon-bedrock/anthropic.claude-opus-4-20250514-v1:0", - "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": "amazon-bedrock/anthropic.claude-opus-4.1-20250805-v1:0", "name": "Claude Opus 4.1", @@ -10657,39 +10528,6 @@ "output": 128000 } }, - { - "id": "amazon-bedrock/anthropic.claude-sonnet-4-20250514-v1:0", - "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": "amazon-bedrock/anthropic.claude-sonnet-4.5-20250929-v1:0", "name": "Claude Sonnet 4.5", @@ -10756,6 +10594,39 @@ "output": 64000 } }, + { + "id": "amazon-bedrock/au.anthropic.claude-haiku-4.5-20251001-v1:0", + "name": "Claude Haiku 4.5 (AU)", + "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": "amazon-bedrock/au.anthropic.claude-opus-4.6-v1", "name": "AU Anthropic Claude Opus 4.6", @@ -10789,6 +10660,39 @@ "output": 128000 } }, + { + "id": "amazon-bedrock/au.anthropic.claude-sonnet-4.5-20250929-v1:0", + "name": "Claude Sonnet 4.5 (AU)", + "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": "amazon-bedrock/au.anthropic.claude-sonnet-4.6", "name": "AU Anthropic Claude Sonnet 4.6", @@ -11041,39 +10945,6 @@ "output": 128000 } }, - { - "id": "amazon-bedrock/eu.anthropic.claude-sonnet-4-20250514-v1:0", - "name": "Claude Sonnet 4 (EU)", - "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": "amazon-bedrock/eu.anthropic.claude-sonnet-4.5-20250929-v1:0", "name": "Claude Sonnet 4.5 (EU)", @@ -11272,39 +11143,6 @@ "output": 128000 } }, - { - "id": "amazon-bedrock/global.anthropic.claude-sonnet-4-20250514-v1:0", - "name": "Claude Sonnet 4 (Global)", - "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": "amazon-bedrock/global.anthropic.claude-sonnet-4.5-20250929-v1:0", "name": "Claude Sonnet 4.5 (Global)", @@ -11461,32 +11299,102 @@ } }, { - "id": "amazon-bedrock/meta.llama3-1-405b-instruct-v1:0", - "name": "Llama 3.1 405B Instruct", - "family": "llama", - "attachment": false, - "reasoning": false, + "id": "amazon-bedrock/jp.anthropic.claude-opus-4.7", + "name": "Claude Opus 4.7 (JP)", + "family": "claude-opus", + "attachment": true, + "reasoning": true, "tool_call": true, - "temperature": true, - "knowledge": "2023-12", - "release_date": "2024-07-23", - "last_updated": "2024-07-23", + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", "modalities": { "input": [ - "text" + "text", + "image", + "pdf" ], "output": [ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { - "input": 2.4, - "output": 2.4 + "input": 5.0, + "output": 25.0, + "cache_read": 0.5, + "cache_write": 6.25 }, "limit": { - "context": 128000, - "output": 4096 + "context": 1000000, + "output": 128000 + } + }, + { + "id": "amazon-bedrock/jp.anthropic.claude-sonnet-4.5-20250929-v1:0", + "name": "Claude Sonnet 4.5 (JP)", + "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": "amazon-bedrock/jp.anthropic.claude-sonnet-4.6", + "name": "Claude Sonnet 4.6 (JP)", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2026-02-17", + "last_updated": "2026-03-13", + "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 } }, { @@ -11547,124 +11455,6 @@ "output": 4096 } }, - { - "id": "amazon-bedrock/meta.llama3-2-11b-instruct-v1:0", - "name": "Llama 3.2 11B 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": 0.16, - "output": 0.16 - }, - "limit": { - "context": 128000, - "output": 4096 - } - }, - { - "id": "amazon-bedrock/meta.llama3-2-1b-instruct-v1:0", - "name": "Llama 3.2 1B 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" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.1, - "output": 0.1 - }, - "limit": { - "context": 131000, - "output": 4096 - } - }, - { - "id": "amazon-bedrock/meta.llama3-2-3b-instruct-v1:0", - "name": "Llama 3.2 3B 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" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.15, - "output": 0.15 - }, - "limit": { - "context": 131000, - "output": 4096 - } - }, - { - "id": "amazon-bedrock/meta.llama3-2-90b-instruct-v1:0", - "name": "Llama 3.2 90B 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": 0.72, - "output": 0.72 - }, - "limit": { - "context": 128000, - "output": 4096 - } - }, { "id": "amazon-bedrock/meta.llama3-3-70b-instruct-v1:0", "name": "Llama 3.3 70B Instruct", @@ -12612,39 +12402,6 @@ "output": 64000 } }, - { - "id": "amazon-bedrock/us.anthropic.claude-opus-4-20250514-v1:0", - "name": "Claude Opus 4 (US)", - "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": "amazon-bedrock/us.anthropic.claude-opus-4.1-20250805-v1:0", "name": "Claude Opus 4.1 (US)", @@ -12777,39 +12534,6 @@ "output": 128000 } }, - { - "id": "amazon-bedrock/us.anthropic.claude-sonnet-4-20250514-v1:0", - "name": "Claude Sonnet 4 (US)", - "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": "amazon-bedrock/us.anthropic.claude-sonnet-4.5-20250929-v1:0", "name": "Claude Sonnet 4.5 (US)", @@ -12876,6 +12600,95 @@ "output": 64000 } }, + { + "id": "amazon-bedrock/us.deepseek.r1-v1:0", + "name": "DeepSeek-R1 (US)", + "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": "amazon-bedrock/us.meta.llama4-maverick-17b-instruct-v1:0", + "name": "Llama 4 Maverick 17B Instruct (US)", + "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": 0.24, + "output": 0.97 + }, + "limit": { + "context": 1000000, + "output": 16384 + } + }, + { + "id": "amazon-bedrock/us.meta.llama4-scout-17b-instruct-v1:0", + "name": "Llama 4 Scout 17B Instruct (US)", + "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": 0.17, + "output": 0.66 + }, + "limit": { + "context": 3500000, + "output": 16384 + } + }, { "id": "amazon-bedrock/writer.palmyra-x4-v1:0", "name": "Palmyra X4", @@ -13579,6 +13392,479 @@ "output": 64000 } }, + { + "id": "auriko/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": "2026-03-13", + "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": "auriko/claude-opus-4.7", + "name": "Claude Opus 4.7", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "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": "auriko/claude-sonnet-4.6", + "name": "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": "2026-03-13", + "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": "auriko/deepseek-v4-flash", + "name": "DeepSeek V4 Flash", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.0028 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, + { + "id": "auriko/deepseek-v4-pro", + "name": "DeepSeek V4 Pro", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.435, + "output": 0.87, + "cache_read": 0.003625 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, + { + "id": "auriko/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": 0.03 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "auriko/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": 0.125 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "auriko/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": "auriko/glm-5.1", + "name": "GLM-5.1", + "family": "glm", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-27", + "last_updated": "2026-03-27", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.4, + "output": 4.4, + "cache_read": 0.26 + }, + "limit": { + "context": 200000, + "output": 131072 + } + }, + { + "id": "auriko/grok-4.3", + "name": "Grok 4.3", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-05-01", + "last_updated": "2026-05-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 1000000, + "output": 30000 + } + }, + { + "id": "auriko/kimi-k2.5", + "name": "Kimi K2.5", + "family": "kimi-k2.5", + "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": 0.5, + "output": 2.8 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "auriko/kimi-k2.6", + "name": "Kimi K2.6", + "family": "kimi-k2.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.95, + "output": 4.0, + "cache_read": 0.16 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, + { + "id": "auriko/minimax-m2-7", + "name": "MiniMax-M2.7", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.3, + "output": 1.2, + "cache_write": 0.375 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "auriko/minimax-m2-7-highspeed", + "name": "MiniMax-M2.7-highspeed", + "family": "minimax", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 2.4, + "cache_write": 0.375 + }, + "limit": { + "context": 204800, + "output": 131072 + } + }, + { + "id": "auriko/qwen-3.6-plus", + "name": "Qwen3.6 Plus", + "family": "qwen", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-04-02", + "last_updated": "2026-04-02", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 3.0, + "cache_read": 0.1 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, { "id": "azure-cognitive-services/claude-haiku-4.5", "name": "Claude Haiku 4.5", @@ -20264,34 +20550,6 @@ "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", @@ -20301,7 +20559,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-02-15", - "last_updated": "2026-02-15", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20312,9 +20570,9 @@ }, "open_weights": true, "cost": { - "input": 0.3, - "output": 1.1, - "cache_read": 0.15 + "input": 0.15, + "output": 1.2, + "cache_read": 0.075 }, "limit": { "context": 196608, @@ -20330,7 +20588,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20341,8 +20599,9 @@ }, "open_weights": true, "cost": { - "input": 0.02, - "output": 0.1 + "input": 0.0245, + "output": 0.0978, + "cache_read": 0.01225 }, "limit": { "context": 32768, @@ -20358,7 +20617,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20369,127 +20628,15 @@ }, "open_weights": true, "cost": { - "input": 0.01, - "output": 0.05 + "input": 0.0136, + "output": 0.0543, + "cache_read": 0.0068 }, "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", @@ -20499,7 +20646,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20510,8 +20657,9 @@ }, "open_weights": true, "cost": { - "input": 0.13, - "output": 0.52 + "input": 0.2989, + "output": 1.1957, + "cache_read": 0.14945 }, "limit": { "context": 32768, @@ -20527,7 +20675,7 @@ "tool_call": false, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20538,8 +20686,9 @@ }, "open_weights": true, "cost": { - "input": 0.03, - "output": 0.11 + "input": 0.0272, + "output": 0.1087, + "cache_read": 0.0136 }, "limit": { "context": 32768, @@ -20550,12 +20699,12 @@ "id": "chutes/Qwen/Qwen2.5-VL-32B-Instruct", "name": "Qwen2.5 VL 32B Instruct", "family": "qwen", - "attachment": false, + "attachment": true, "reasoning": false, "tool_call": false, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text", @@ -20567,99 +20716,15 @@ }, "open_weights": true, "cost": { - "input": 0.05, - "output": 0.22 + "input": 0.0543, + "output": 0.2174, + "cache_read": 0.02715 }, "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", @@ -20669,7 +20734,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20680,9 +20745,9 @@ }, "open_weights": true, "cost": { - "input": 0.08, - "output": 0.55, - "cache_read": 0.04 + "input": 0.1, + "output": 0.6, + "cache_read": 0.05 }, "limit": { "context": 262144, @@ -20698,7 +20763,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20710,7 +20775,8 @@ "open_weights": true, "cost": { "input": 0.11, - "output": 0.6 + "output": 0.6, + "cache_read": 0.055 }, "limit": { "context": 262144, @@ -20726,7 +20792,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20738,7 +20804,8 @@ "open_weights": true, "cost": { "input": 0.06, - "output": 0.22 + "output": 0.22, + "cache_read": 0.03 }, "limit": { "context": 40960, @@ -20746,43 +20813,15 @@ } }, { - "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", + "id": "chutes/Qwen/Qwen3-32B-TEE", + "name": "Qwen3 32B TEE", "family": "qwen", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "release_date": "2026-04-25", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20803,15 +20842,15 @@ } }, { - "id": "chutes/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8-TEE", - "name": "Qwen3 Coder 480B A35B Instruct FP8 TEE", + "id": "chutes/Qwen/Qwen3-Coder-Next-TEE", + "name": "Qwen3 Coder Next TEE", "family": "qwen", "attachment": false, "reasoning": false, "tool_call": true, "temperature": true, - "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "release_date": "2026-04-25", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20822,37 +20861,9 @@ }, "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 + "input": 0.12, + "output": 0.75, + "cache_read": 0.06 }, "limit": { "context": 262144, @@ -20868,7 +20879,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20880,36 +20891,8 @@ "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 + "output": 0.8, + "cache_read": 0.05 }, "limit": { "context": 262144, @@ -20925,7 +20908,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-02-18", - "last_updated": "2026-02-18", + "last_updated": "2026-04-25", "modalities": { "input": [ "text", @@ -20946,6 +20929,36 @@ "output": 65536 } }, + { + "id": "chutes/Qwen/Qwen3.6-27B-TEE", + "name": "Qwen3.6 27B TEE", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-25", + "last_updated": "2026-04-25", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.195, + "output": 1.56, + "cache_read": 0.0975 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, { "id": "chutes/Qwen/Qwen3Guard-Gen-0.6B", "name": "Qwen3Guard Gen 0.6B", @@ -20955,7 +20968,7 @@ "tool_call": false, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20967,7 +20980,7 @@ "open_weights": true, "cost": { "input": 0.01, - "output": 0.01, + "output": 0.0109, "cache_read": 0.005 }, "limit": { @@ -20976,15 +20989,15 @@ } }, { - "id": "chutes/XiaomiMiMo/MiMo-V2-Flash", - "name": "MiMo V2 Flash", + "id": "chutes/XiaomiMiMo/MiMo-V2-Flash-TEE", + "name": "MiMo V2 Flash TEE", "family": "mimo", "attachment": false, - "reasoning": true, + "reasoning": false, "tool_call": true, "temperature": true, - "release_date": "2025-12-29", - "last_updated": "2026-01-27", + "release_date": "2026-04-25", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -20996,70 +21009,12 @@ "open_weights": true, "cost": { "input": 0.09, - "output": 0.29 + "output": 0.29, + "cache_read": 0.045 }, "limit": { "context": 262144, - "output": 32000 - } - }, - { - "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 + "output": 65536 } }, { @@ -21071,7 +21026,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -21082,8 +21037,9 @@ }, "open_weights": true, "cost": { - "input": 0.4, - "output": 1.75 + "input": 0.45, + "output": 2.15, + "cache_read": 0.225 }, "limit": { "context": 163840, @@ -21099,7 +21055,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -21110,70 +21066,15 @@ }, "open_weights": true, "cost": { - "input": 0.03, - "output": 0.11 + "input": 0.0272, + "output": 0.1087, + "cache_read": 0.0136 }, "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", @@ -21183,7 +21084,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -21194,9 +21095,9 @@ }, "open_weights": true, "cost": { - "input": 0.19, - "output": 0.87, - "cache_read": 0.095 + "input": 0.25, + "output": 1.0, + "cache_read": 0.125 }, "limit": { "context": 163840, @@ -21212,63 +21113,7 @@ "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", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -21280,7 +21125,8 @@ "open_weights": true, "cost": { "input": 0.27, - "output": 0.41 + "output": 1.0, + "cache_read": 0.135 }, "limit": { "context": 163840, @@ -21296,7 +21142,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -21317,102 +21163,19 @@ } }, { - "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, + "id": "chutes/google/gemma-4-31B-turbo-TEE", + "name": "gemma 4 31B turbo TEE", + "family": "gemma", + "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "release_date": "2026-04-25", + "last_updated": "2026-04-25", "modalities": { "input": [ - "text" + "text", + "image" ], "output": [ "text" @@ -21420,25 +21183,26 @@ }, "open_weights": true, "cost": { - "input": 0.4, - "output": 1.75 + "input": 0.13, + "output": 0.38, + "cache_read": 0.065 }, "limit": { - "context": 262144, - "output": 65535 + "context": 131072, + "output": 65536 } }, { "id": "chutes/moonshotai/Kimi-K2.5-TEE", "name": "Kimi K2.5 TEE", "family": "kimi", - "attachment": false, + "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, "knowledge": "2024-10", "release_date": "2026-01-27", - "last_updated": "2026-01-27", + "last_updated": "2026-04-25", "modalities": { "input": [ "text", @@ -21451,8 +21215,9 @@ }, "open_weights": true, "cost": { - "input": 0.6, - "output": 3.0 + "input": 0.44, + "output": 2.0, + "cache_read": 0.22 }, "limit": { "context": 262144, @@ -21469,7 +21234,7 @@ "temperature": true, "knowledge": "2025-12", "release_date": "2026-04-20", - "last_updated": "2026-04-23", + "last_updated": "2026-04-25", "modalities": { "input": [ "text", @@ -21482,40 +21247,13 @@ }, "open_weights": true, "cost": { - "input": 0.44, - "output": 2.0 + "input": 0.95, + "output": 4.0, + "cache_read": 0.475 }, "limit": { "context": 262144, - "output": 262144 - } - }, - { - "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 + "output": 65535 } }, { @@ -21527,7 +21265,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -21538,52 +21276,25 @@ }, "open_weights": true, "cost": { - "input": 0.04, - "output": 0.18 + "input": 0.09, + "output": 0.36, + "cache_read": 0.045 }, "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, + "attachment": true, "reasoning": false, "tool_call": false, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text", @@ -21596,7 +21307,7 @@ "open_weights": true, "cost": { "input": 0.01, - "output": 0.01, + "output": 0.0109, "cache_read": 0.005 }, "limit": { @@ -21605,15 +21316,15 @@ } }, { - "id": "chutes/tngtech/DeepSeek-R1T-Chimera", - "name": "DeepSeek R1T Chimera", - "family": "tngtech", + "id": "chutes/tngtech/DeepSeek-TNG-R1T2-Chimera-TEE", + "name": "DeepSeek TNG R1T2 Chimera TEE", + "family": "deepseek", "attachment": false, "reasoning": true, - "tool_call": false, + "tool_call": true, "temperature": true, - "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "release_date": "2026-04-25", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -21625,105 +21336,24 @@ "open_weights": true, "cost": { "input": 0.3, - "output": 1.2 + "output": 1.1, + "cache_read": 0.15 }, "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", + "family": "unsloth", "attachment": false, "reasoning": false, "tool_call": false, "temperature": true, "release_date": "2026-01-27", - "last_updated": "2026-01-27", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -21735,11 +21365,11 @@ "open_weights": true, "cost": { "input": 0.01, - "output": 0.01, + "output": 0.0109, "cache_read": 0.005 }, "limit": { - "context": 32768, + "context": 16384, "output": 8192 } }, @@ -21752,7 +21382,7 @@ "tool_call": false, "temperature": true, "release_date": "2025-02-12", - "last_updated": "2025-02-12", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -21764,7 +21394,7 @@ "open_weights": true, "cost": { "input": 0.01, - "output": 0.01, + "output": 0.0136, "cache_read": 0.005 }, "limit": { @@ -21781,7 +21411,7 @@ "tool_call": false, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -21801,45 +21431,16 @@ "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, + "attachment": true, "reasoning": false, "tool_call": false, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text", @@ -21852,7 +21453,8 @@ "open_weights": true, "cost": { "input": 0.03, - "output": 0.1 + "output": 0.1, + "cache_read": 0.015 }, "limit": { "context": 131072, @@ -21863,12 +21465,12 @@ "id": "chutes/unsloth/gemma-3-27b-it", "name": "gemma 3 27b it", "family": "unsloth", - "attachment": false, + "attachment": true, "reasoning": false, "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text", @@ -21880,9 +21482,9 @@ }, "open_weights": true, "cost": { - "input": 0.04, - "output": 0.15, - "cache_read": 0.02 + "input": 0.0272, + "output": 0.1087, + "cache_read": 0.0136 }, "limit": { "context": 128000, @@ -21893,12 +21495,12 @@ "id": "chutes/unsloth/gemma-3-4b-it", "name": "gemma 3 4b it", "family": "unsloth", - "attachment": false, + "attachment": true, "reasoning": false, "tool_call": false, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text", @@ -21911,162 +21513,24 @@ "open_weights": true, "cost": { "input": 0.01, - "output": 0.03 + "output": 0.0272, + "cache_read": 0.005 }, "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": 0.4, - "output": 1.7, - "cache_read": 0.2 - }, - "limit": { - "context": 202752, - "output": 65536 - } - }, { "id": "chutes/zai-org/GLM-4.6V", "name": "GLM 4.6V", "family": "glm", - "attachment": false, + "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text", @@ -22090,12 +21554,13 @@ { "id": "chutes/zai-org/GLM-4.7-FP8", "name": "GLM 4.7 FP8", + "family": "glm", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, "release_date": "2026-01-27", - "last_updated": "2026-01-27", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -22106,35 +21571,9 @@ }, "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 + "input": 0.2989, + "output": 1.1957, + "cache_read": 0.14945 }, "limit": { "context": 202752, @@ -22150,7 +21589,7 @@ "tool_call": true, "temperature": true, "release_date": "2025-12-29", - "last_updated": "2026-01-10", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -22161,8 +21600,9 @@ }, "open_weights": true, "cost": { - "input": 0.4, - "output": 1.5 + "input": 0.39, + "output": 1.75, + "cache_read": 0.195 }, "limit": { "context": 202752, @@ -22178,7 +21618,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-02-14", - "last_updated": "2026-02-14", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -22190,7 +21630,7 @@ "open_weights": true, "cost": { "input": 0.95, - "output": 3.15, + "output": 2.55, "cache_read": 0.475 }, "limit": { @@ -22207,7 +21647,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-03-11", - "last_updated": "2026-03-11", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -22218,9 +21658,9 @@ }, "open_weights": true, "cost": { - "input": 0.49, - "output": 1.96, - "cache_read": 0.245 + "input": 0.4891, + "output": 1.9565, + "cache_read": 0.24455 }, "limit": { "context": 202752, @@ -22236,7 +21676,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-04-08", - "last_updated": "2026-04-08", + "last_updated": "2026-04-25", "modalities": { "input": [ "text" @@ -22247,9 +21687,9 @@ }, "open_weights": true, "cost": { - "input": 0.95, - "output": 3.15, - "cache_read": 0.475 + "input": 1.05, + "output": 3.5, + "cache_read": 0.525 }, "limit": { "context": 202752, @@ -22602,6 +22042,35 @@ "output": 131072 } }, + { + "id": "claudinio/claudinio", + "name": "Claudinio", + "attachment": true, + "reasoning": true, + "tool_call": true, + "knowledge": "2026-05", + "release_date": "2026-05-12", + "last_updated": "2026-05-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.5, + "output": 2.0, + "cache_read": 0.05 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, { "id": "cloudferro-sherlock/MiniMaxAI/MiniMax-M2.5", "name": "MiniMax-M2.5", @@ -22628,7 +22097,7 @@ }, "limit": { "context": 196000, - "output": 196000 + "output": 16000 } }, { @@ -26939,6 +26408,811 @@ "output": 250000 } }, + { + "id": "databricks/databricks-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": "databricks/databricks-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": "databricks/databricks-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": "databricks/databricks-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": "2026-03-13", + "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": "databricks/databricks-claude-opus-4.7", + "name": "Claude Opus 4.7", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "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": "databricks/databricks-claude-sonnet-4", + "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": "databricks/databricks-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": "databricks/databricks-claude-sonnet-4.6", + "name": "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": "2026-03-13", + "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": "databricks/databricks-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": 0.03 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "databricks/databricks-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": 0.125 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "databricks/databricks-gemini-3-flash", + "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": "databricks/databricks-gemini-3-pro", + "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": "databricks/databricks-gemini-3.1-flash-lite", + "name": "Gemini 3.1 Flash Lite Preview", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-03-03", + "last_updated": "2026-03-03", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.5, + "cache_read": 0.025 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, + { + "id": "databricks/databricks-gemini-3.1-pro", + "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": "databricks/databricks-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": "databricks/databricks-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": "databricks/databricks-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": "databricks/databricks-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": "databricks/databricks-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": "databricks/databricks-gpt-5.4", + "name": "GPT-5.4", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-05", + "last_updated": "2026-03-05", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 2.5, + "output": 15.0, + "cache_read": 0.25 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "databricks/databricks-gpt-5.4-mini", + "name": "GPT-5.4 mini", + "family": "gpt-mini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.75, + "output": 4.5, + "cache_read": 0.075 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "databricks/databricks-gpt-5.4-nano", + "name": "GPT-5.4 nano", + "family": "gpt-nano", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-08-31", + "release_date": "2026-03-17", + "last_updated": "2026-03-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.2, + "output": 1.25, + "cache_read": 0.02 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, + { + "id": "databricks/databricks-gpt-5.5", + "name": "GPT-5.5", + "family": "gpt", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-12-01", + "release_date": "2026-04-23", + "last_updated": "2026-04-23", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 30.0, + "cache_read": 0.5 + }, + "limit": { + "context": 1050000, + "output": 128000 + } + }, + { + "id": "databricks/databricks-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": 0.072, + "output": 0.28 + }, + "limit": { + "context": 131072, + "output": 32768 + } + }, + { + "id": "databricks/databricks-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": "deepinfra/MiniMaxAI/MiniMax-M2", "name": "MiniMax M2", @@ -27296,6 +27570,36 @@ "output": 64000 } }, + { + "id": "deepinfra/deepseek-ai/DeepSeek-V4-Flash", + "name": "DeepSeek V4 Flash", + "family": "deepseek-flash", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.028 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, { "id": "deepinfra/deepseek-ai/DeepSeek-V4-Pro", "name": "DeepSeek V4 Pro", @@ -27753,6 +28057,69 @@ "output": 16384 } }, + { + "id": "deepinfra/xiaomi/mimo-v2.5", + "name": "MiMo-V2.5", + "family": "mimo", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.0, + "cache_read": 0.08 + }, + "limit": { + "context": 262144, + "output": 16384 + } + }, + { + "id": "deepinfra/xiaomi/mimo-v2.5-pro", + "name": "MiMo-V2.5-Pro", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 16384 + } + }, { "id": "deepinfra/zai-org/GLM-4.5", "name": "GLM-4.5", @@ -28137,6 +28504,133 @@ "output": 384 } }, + { + "id": "digitalocean/anthropic-claude-3-opus", + "name": "Claude 3 Opus", + "family": "claude-opus", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2023-08", + "release_date": "2024-02-29", + "last_updated": "2024-02-29", + "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": 4096 + } + }, + { + "id": "digitalocean/anthropic-claude-3.5-haiku", + "name": "Claude 3.5 Haiku", + "family": "claude-haiku", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-11-05", + "last_updated": "2024-11-05", + "modalities": { + "input": [ + "text" + ], + "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": "digitalocean/anthropic-claude-3.5-sonnet", + "name": "Claude 3.5 Sonnet", + "family": "claude-sonnet", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-04", + "release_date": "2024-06-20", + "last_updated": "2024-10-22", + "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": 8192 + } + }, + { + "id": "digitalocean/anthropic-claude-3.7-sonnet", + "name": "Claude 3.7 Sonnet", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-11", + "release_date": "2025-02-24", + "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": "digitalocean/anthropic-claude-4.1-opus", "name": "Claude Opus 4.1", @@ -28170,6 +28664,38 @@ "output": 32000 } }, + { + "id": "digitalocean/anthropic-claude-4.5-haiku", + "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": 1.0, + "output": 5.0, + "cache_read": 1.0, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, { "id": "digitalocean/anthropic-claude-4.5-sonnet", "name": "Claude Sonnet 4.5", @@ -28576,6 +29102,32 @@ "output": 32768 } }, + { + "id": "digitalocean/deepseek-v3", + "name": "DeepSeek V3", + "family": "deepseek", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-07", + "release_date": "2024-12-26", + "last_updated": "2025-03-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 163840, + "output": 131072 + } + }, { "id": "digitalocean/deepseek-v4-pro", "name": "DeepSeek V4 Pro", @@ -28845,6 +29397,36 @@ "output": 32768 } }, + { + "id": "digitalocean/kimi-k2.6", + "name": "Kimi K2.6", + "family": "kimi", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2025-01", + "release_date": "2026-04-21", + "last_updated": "2026-04-21", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.95, + "output": 4.0 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "digitalocean/llama-4-maverick", "name": "Llama 4 Maverick 17B 128E Instruct", @@ -28876,29 +29458,32 @@ } }, { - "id": "digitalocean/llama-guard-4-12b", - "name": "Llama Guard 4 12B", + "id": "digitalocean/llama3-8b-instruct", + "name": "Llama 3.1 Instruct (8B)", "family": "llama", - "attachment": true, + "attachment": false, "reasoning": false, - "tool_call": false, + "tool_call": true, "temperature": true, - "release_date": "2025-04-05", - "last_updated": "2026-04-30", + "knowledge": "2023-12", + "release_date": "2024-07-23", + "last_updated": "2024-07-23", "modalities": { "input": [ - "text", - "image" + "text" ], "output": [ "text" ] }, "open_weights": true, - "cost": {}, + "cost": { + "input": 0.198, + "output": 0.198 + }, "limit": { - "context": 128000, - "output": 16384 + "context": 131072, + "output": 131072 } }, { @@ -28959,6 +29544,32 @@ "output": 128000 } }, + { + "id": "digitalocean/ministral-3-8b-instruct", + "name": "Ministral 3 8B", + "family": "ministral", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2025-12-15", + "last_updated": "2025-12-15", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "digitalocean/mistral-3-14B", "name": "Ministral 3 14B Instruct", @@ -28987,6 +29598,59 @@ "output": 128000 } }, + { + "id": "digitalocean/mistral-7b-instruct-v0.3", + "name": "Mistral 7B Instruct v0.3", + "family": "mistral", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-05-22", + "last_updated": "2024-05-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 32768, + "output": 32768 + } + }, + { + "id": "digitalocean/mistral-nemo-instruct", + "name": "Mistral Nemo Instruct", + "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": 0.3, + "output": 0.3 + }, + "limit": { + "context": 128000, + "output": 16384 + } + }, { "id": "digitalocean/multi-qa-mpnet-base-dot-v1", "name": "Multi-QA-mpnet-base-dot-v1", @@ -29015,6 +29679,31 @@ "output": 768 } }, + { + "id": "digitalocean/nemotron-3-nano-30b", + "name": "Nemotron 3 Nano 30B A3B", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2025-04-14", + "last_updated": "2025-04-14", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "digitalocean/nemotron-3-nano-omni", "name": "Nemotron Nano 3 Omni", @@ -29634,6 +30323,32 @@ "output": 0 } }, + { + "id": "digitalocean/openai-gpt-image-2", + "name": "GPT Image 2", + "family": "gpt-image", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-04-24", + "last_updated": "2025-04-24", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": {}, + "limit": { + "context": 0, + "output": 0 + } + }, { "id": "digitalocean/openai-gpt-oss-120b", "name": "gpt-oss-120b", @@ -29786,6 +30501,32 @@ "output": 100000 } }, + { + "id": "digitalocean/qwen-2.5-14b-instruct", + "name": "Qwen 2.5 14B Instruct", + "family": "qwen", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2024-09", + "release_date": "2024-09-19", + "last_updated": "2024-09-19", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 131072, + "output": 131072 + } + }, { "id": "digitalocean/qwen3-coder-flash", "name": "Qwen3 Coder Flash", @@ -30990,6 +31731,36 @@ "output": 131072 } }, + { + "id": "firepass/accounts/fireworks/routers/kimi-k2p6-turbo", + "name": "Kimi K2.6 Turbo", + "family": "kimi-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-17", + "last_updated": "2026-04-17", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 262000, + "output": 262000 + } + }, { "id": "fireworks-ai/accounts/fireworks/models/deepseek-v3p1", "name": "DeepSeek V3.1", @@ -35749,7 +36520,403 @@ "temperature": true, "knowledge": "2025-08-31", "release_date": "2026-02-17", - "last_updated": "2026-02-17", + "last_updated": "2026-03-13", + "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/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/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/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/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/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/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/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, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + } + }, + { + "id": "google-vertex/claude-opus-4.6@default", + "name": "Claude Opus 4.6", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05-31", + "release_date": "2026-02-05", + "last_updated": "2026-03-13", + "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/claude-opus-4.7@default", + "name": "Claude Opus 4.7", + "family": "claude-opus", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "knowledge": "2026-01-31", + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "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/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/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/claude-sonnet-4.6@default", + "name": "Claude Sonnet 4.6", + "family": "claude-sonnet", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-08-31", + "release_date": "2026-02-17", + "last_updated": "2026-03-13", "modalities": { "input": [ "text", @@ -35960,7 +37127,7 @@ "cost": { "input": 0.1, "output": 0.4, - "cache_read": 0.025 + "cache_read": 0.01 }, "limit": { "context": 1048576, @@ -36308,6 +37475,40 @@ "output": 65536 } }, + { + "id": "google-vertex/gemini-3.1-flash-lite", + "name": "Gemini 3.1 Flash Lite", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-07", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.5, + "cache_read": 0.025 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, { "id": "google-vertex/gemini-3.1-flash-lite-preview", "name": "Gemini 3.1 Flash Lite Preview", @@ -36335,8 +37536,7 @@ "cost": { "input": 0.25, "output": 1.5, - "cache_read": 0.025, - "cache_write": 1.0 + "cache_read": 0.025 }, "limit": { "context": 1048576, @@ -37031,7 +38231,7 @@ "cost": { "input": 0.1, "output": 0.4, - "cache_read": 0.025 + "cache_read": 0.01 }, "limit": { "context": 1048576, @@ -37460,7 +38660,7 @@ }, "open_weights": false, "cost": { - "input": 0.25, + "input": 0.5, "output": 60.0 }, "limit": { @@ -37468,6 +38668,40 @@ "output": 32768 } }, + { + "id": "google/gemini-3.1-flash-lite", + "name": "Gemini 3.1 Flash Lite", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-07", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.5, + "cache_read": 0.025 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, { "id": "google/gemini-3.1-flash-lite-preview", "name": "Gemini 3.1 Flash Lite Preview", @@ -37495,8 +38729,7 @@ "cost": { "input": 0.25, "output": 1.5, - "cache_read": 0.025, - "cache_write": 1.0 + "cache_read": 0.025 }, "limit": { "context": 1048576, @@ -45286,33 +46519,6 @@ "output": 65536 } }, - { - "id": "kilo/allenai/olmo-3.1-32b-instruct", - "name": "AllenAI: Olmo 3.1 32B Instruct", - "attachment": false, - "reasoning": false, - "tool_call": true, - "temperature": true, - "release_date": "2026-01-07", - "last_updated": "2026-03-15", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.2, - "output": 0.6 - }, - "limit": { - "context": 65536, - "output": 32768 - } - }, { "id": "kilo/alpindale/goliath-120b", "name": "Goliath 120B", @@ -46127,6 +47333,33 @@ "output": 64000 } }, + { + "id": "kilo/baidu/cobuddy:free", + "name": "Baidu: CoBuddy (free)", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-05-06", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 65536 + } + }, { "id": "kilo/baidu/ernie-4.5-21b-a3b", "name": "Baidu: ERNIE 4.5 21B A3B", @@ -48427,6 +49660,34 @@ "output": 16384 } }, + { + "id": "kilo/microsoft/phi-4-mini-instruct", + "name": "Microsoft: Phi 4 Mini Instruct", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-10-17", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.08, + "output": 0.35, + "cache_read": 0.08 + }, + "limit": { + "context": 128000, + "output": 128000 + } + }, { "id": "kilo/microsoft/wizardlm-2-8x22b", "name": "WizardLM-2 8x22B", @@ -48952,6 +50213,34 @@ "output": 26215 } }, + { + "id": "kilo/mistralai/mistral-medium-3.5", + "name": "Mistral: Mistral Medium 3.5", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-30", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.5, + "output": 7.5 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "kilo/mistralai/mistral-nemo", "name": "Mistral: Mistral Nemo", @@ -49321,7 +50610,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-04-20", - "last_updated": "2026-04-20", + "last_updated": "2026-05-12", "modalities": { "input": [ "text", @@ -49333,13 +50622,13 @@ }, "open_weights": true, "cost": { - "input": 0.95, - "output": 4.0, - "cache_read": 0.16 + "input": 0.75, + "output": 3.5, + "cache_read": 0.375 }, "limit": { "context": 262144, - "output": 262144 + "output": 65535 } }, { @@ -49725,35 +51014,6 @@ "output": 262144 } }, - { - "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-9b-v2", "name": "NVIDIA: Nemotron Nano 9B V2", @@ -51024,6 +52284,36 @@ "output": 16384 } }, + { + "id": "kilo/openai/gpt-chat", + "name": "OpenAI: GPT Chat Latest", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": false, + "release_date": "2026-05-05", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "image", + "pdf", + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 5.0, + "output": 30.0, + "cache_read": 0.5 + }, + "limit": { + "context": 400000, + "output": 128000 + } + }, { "id": "kilo/openai/gpt-oss-120b", "name": "OpenAI: gpt-oss-120b", @@ -54027,12 +55317,14 @@ { "id": "kilo/xiaomi/mimo-v2-flash", "name": "Xiaomi: MiMo-V2-Flash", + "family": "mimo", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2025-12-14", - "last_updated": "2026-03-15", + "knowledge": "2024-12-01", + "release_date": "2025-12-16", + "last_updated": "2026-02-04", "modalities": { "input": [ "text" @@ -54055,24 +55347,27 @@ { "id": "kilo/xiaomi/mimo-v2-omni", "name": "Xiaomi: MiMo-V2-Omni", + "family": "mimo", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, + "knowledge": "2024-12", "release_date": "2026-03-18", - "last_updated": "2026-04-11", + "last_updated": "2026-03-18", "modalities": { "input": [ - "audio", - "image", "text", - "video" + "image", + "audio", + "video", + "pdf" ], "output": [ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 0.4, "output": 2.0, @@ -54086,12 +55381,14 @@ { "id": "kilo/xiaomi/mimo-v2-pro", "name": "Xiaomi: MiMo-V2-Pro", + "family": "mimo", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, + "knowledge": "2024-12", "release_date": "2026-03-18", - "last_updated": "2026-04-11", + "last_updated": "2026-03-18", "modalities": { "input": [ "text" @@ -54100,7 +55397,7 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 1.0, "output": 3.0, @@ -54114,6 +55411,7 @@ { "id": "kilo/xiaomi/mimo-v2.5", "name": "Xiaomi: MiMo-V2.5", + "family": "mimo", "attachment": true, "reasoning": true, "tool_call": true, @@ -54123,13 +55421,16 @@ "last_updated": "2026-04-22", "modalities": { "input": [ - "text" + "text", + "image", + "audio", + "video" ], "output": [ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.4, "output": 2.0, @@ -54143,7 +55444,8 @@ { "id": "kilo/xiaomi/mimo-v2.5-pro", "name": "Xiaomi: MiMo V2.5 Pro", - "attachment": true, + "family": "mimo", + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -54166,7 +55468,7 @@ }, "limit": { "context": 1048576, - "output": 128000 + "output": 131072 } }, { @@ -55724,7 +57026,7 @@ "cost": { "input": 0.1, "output": 0.4, - "cache_read": 0.025 + "cache_read": 0.01 }, "limit": { "context": 1048576, @@ -55833,6 +57135,40 @@ "output": 65536 } }, + { + "id": "llmgateway/gemini-3.1-flash-lite", + "name": "Gemini 3.1 Flash Lite", + "family": "gemini-flash-lite", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2026-05-07", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.5, + "cache_read": 0.025 + }, + "limit": { + "context": 1048576, + "output": 65536 + } + }, { "id": "llmgateway/gemini-3.1-flash-lite-preview", "name": "Gemini 3.1 Flash Lite Preview", @@ -55860,8 +57196,7 @@ "cost": { "input": 0.25, "output": 1.5, - "cache_read": 0.025, - "cache_write": 1.0 + "cache_read": 0.025 }, "limit": { "context": 1048576, @@ -57845,6 +59180,36 @@ "output": 30000 } }, + { + "id": "llmgateway/grok-4.3", + "name": "Grok 4.3", + "family": "grok", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-05-01", + "last_updated": "2026-05-01", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2 + }, + "limit": { + "context": 1000000, + "output": 30000 + } + }, { "id": "llmgateway/grok-code-fast-1", "name": "Grok Code Fast 1", @@ -58393,8 +59758,135 @@ "cache_read": 0.01 }, "limit": { - "context": 256000, - "output": 64000 + "context": 262144, + "output": 65536 + } + }, + { + "id": "llmgateway/mimo-v2-omni", + "name": "MiMo-V2-Omni", + "family": "mimo", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.0, + "cache_read": 0.08 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "llmgateway/mimo-v2-pro", + "name": "MiMo-V2-Pro", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 3.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway/mimo-v2.5", + "name": "MiMo-V2.5", + "family": "mimo", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.0, + "cache_read": 0.08 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "llmgateway/mimo-v2.5-pro", + "name": "MiMo-V2.5-Pro", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.0, + "output": 3.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 131072 } }, { @@ -59998,7 +61490,8 @@ "cost": { "input": 1.3, "output": 7.8, - "cache_read": 0.13 + "cache_read": 0.13, + "cache_write": 1.625 }, "limit": { "context": 262144, @@ -60028,10 +61521,10 @@ }, "open_weights": false, "cost": { - "input": 0.276, - "output": 1.651, - "cache_read": 0.028, - "cache_write": 0.344 + "input": 0.5, + "output": 3.0, + "cache_read": 0.05, + "cache_write": 0.625 }, "limit": { "context": 1000000, @@ -77272,73 +78765,15 @@ } }, { - "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", + "id": "nebius/MiniMaxAI/MiniMax-M2.5", + "name": "MiniMax-M2.5", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-10", - "release_date": "2026-02-01", - "last_updated": "2026-02-04", + "knowledge": "2025-01", + "release_date": "2025-01-20", + "last_updated": "2026-05-07", "modalities": { "input": [ "text" @@ -77355,7 +78790,37 @@ "cache_write": 0.375 }, "limit": { - "context": 128000, + "context": 196608, + "output": 8192 + } + }, + { + "id": "nebius/MiniMaxAI/MiniMax-M2.5-fast", + "name": "MiniMax-M2.5-fast", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-20", + "last_updated": "2026-05-07", + "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": 8000, "output": 8192 } }, @@ -77449,36 +78914,6 @@ "output": 8192 } }, - { - "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", @@ -77540,16 +78975,15 @@ } }, { - "id": "nebius/Qwen/Qwen3-235B-A22B-Thinking", - "name": "Qwen3 235B A22B Thinking 2507", - "family": "qwen", + "id": "nebius/Qwen/Qwen3-235B-A22B-Thinking-2507-fast", + "name": "Qwen3-235B-A22B-Thinking-2507-fast", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, "knowledge": "2025-07", "release_date": "2025-07-25", - "last_updated": "2025-10-04", + "last_updated": "2026-05-07", "modalities": { "input": [ "text" @@ -77558,13 +78992,15 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { - "input": 0.2, - "output": 0.8 + "input": 0.5, + "output": 2.0, + "cache_read": 0.05, + "cache_write": 0.625 }, "limit": { - "context": 262144, + "context": 8000, "output": 8192 } }, @@ -77598,36 +79034,6 @@ "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", @@ -77658,95 +79064,6 @@ "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", @@ -77807,71 +79124,15 @@ } }, { - "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", + "id": "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking-fast", + "name": "Qwen3-Next-80B-A3B-Thinking-fast", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-11", - "release_date": "2026-01-15", - "last_updated": "2026-02-04", + "knowledge": "2025-07", + "release_date": "2025-07-25", + "last_updated": "2026-05-07", "modalities": { "input": [ "text" @@ -77882,85 +79143,26 @@ }, "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, + "input": 0.15, + "output": 1.2, + "cache_read": 0.015, "cache_write": 0.1875 }, "limit": { - "context": 128000, + "context": 8000, "output": 8192 } }, { - "id": "nebius/deepseek-ai/DeepSeek-V3-0324-fast", - "name": "DeepSeek-V3-0324 (Fast)", + "id": "nebius/Qwen/Qwen3.5-397B-A17B", + "name": "Qwen3.5-397B-A17B", "attachment": false, - "reasoning": false, + "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-12", - "release_date": "2025-03-24", - "last_updated": "2026-02-04", + "knowledge": "2025-07", + "release_date": "2025-07-15", + "last_updated": "2026-05-07", "modalities": { "input": [ "text" @@ -77971,13 +79173,43 @@ }, "open_weights": true, "cost": { - "input": 0.75, - "output": 2.25, - "cache_read": 0.075, - "cache_write": 0.28125 + "input": 0.6, + "output": 3.6, + "cache_read": 0.06, + "cache_write": 0.75 }, "limit": { - "context": 128000, + "context": 262144, + "output": 8192 + } + }, + { + "id": "nebius/Qwen/Qwen3.5-397B-A17B-fast", + "name": "Qwen3.5-397B-A17B-fast", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-07", + "release_date": "2025-07-15", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.6, + "output": 3.6, + "cache_read": 0.06, + "cache_write": 0.75 + }, + "limit": { + "context": 8000, "output": 8192 } }, @@ -78011,6 +79243,66 @@ "output": 16384 } }, + { + "id": "nebius/deepseek-ai/DeepSeek-V3.2-fast", + "name": "DeepSeek-V3.2-fast", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-01", + "release_date": "2025-01-27", + "last_updated": "2026-05-07", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.0, + "cache_read": 0.04, + "cache_write": 0.5 + }, + "limit": { + "context": 8000, + "output": 8192 + } + }, + { + "id": "nebius/deepseek-ai/DeepSeek-V4-Pro", + "name": "DeepSeek V4 Pro", + "family": "deepseek-thinking", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.75, + "output": 3.5, + "cache_read": 0.15 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, { "id": "nebius/google/gemma-2-2b-it", "name": "Gemma-2-2b-it", @@ -78041,36 +79333,6 @@ "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", @@ -78102,66 +79364,6 @@ "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": 110000, - "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", @@ -78192,66 +79394,6 @@ "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", @@ -78282,97 +79424,6 @@ "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-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/moonshotai/Kimi-K2.5", "name": "Kimi-K2.5", @@ -78498,15 +79549,15 @@ } }, { - "id": "nebius/nvidia/Nemotron-Nano-V2-12b", - "name": "Nemotron-Nano-V2-12b", + "id": "nebius/nvidia/Nemotron-3-Nano-Omni", + "name": "Nemotron-3-Nano-Omni", "attachment": false, - "reasoning": false, + "reasoning": true, "tool_call": true, "temperature": true, "knowledge": "2025-01", - "release_date": "2025-03-15", - "last_updated": "2026-02-04", + "release_date": "2025-01-20", + "last_updated": "2026-05-07", "modalities": { "input": [ "text" @@ -78517,14 +79568,14 @@ }, "open_weights": true, "cost": { - "input": 0.07, - "output": 0.2, - "cache_read": 0.007, - "cache_write": 0.08 + "input": 0.06, + "output": 0.24, + "cache_read": 0.006, + "cache_write": 0.075 }, "limit": { - "context": 32000, - "output": 4096 + "context": 65536, + "output": 8192 } }, { @@ -78586,15 +79637,15 @@ } }, { - "id": "nebius/openai/gpt-oss-20b", - "name": "gpt-oss-20b", + "id": "nebius/openai/gpt-oss-120b-fast", + "name": "gpt-oss-120b-fast", "attachment": false, - "reasoning": false, + "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-09", - "release_date": "2026-01-10", - "last_updated": "2026-02-04", + "knowledge": "2025-06", + "release_date": "2025-06-10", + "last_updated": "2026-05-07", "modalities": { "input": [ "text" @@ -78605,104 +79656,14 @@ }, "open_weights": true, "cost": { - "input": 0.05, - "output": 0.2, - "cache_read": 0.005, - "cache_write": 0.06 + "input": 0.1, + "output": 0.5, + "cache_read": 0.01, + "cache_write": 0.125 }, "limit": { - "context": 128000, - "output": 4096 - } - }, - { - "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 + "context": 8000, + "output": 8192 } }, { @@ -79196,6 +80157,34 @@ "output": 64000 } }, + { + "id": "novita-ai/Sao10K/L3-8B-Stheno-v3.2", + "name": "L3 8B Stheno V3.2", + "family": "llama", + "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/baichuan/baichuan-m2-32b", "name": "baichuan-m2-32b", @@ -79567,7 +80556,7 @@ "name": "DeepSeek R1 Distill Qwen 14B", "family": "deepseek-thinking", "attachment": false, - "reasoning": true, + "reasoning": false, "tool_call": false, "temperature": true, "release_date": "2025-01-20", @@ -79595,7 +80584,7 @@ "name": "DeepSeek R1 Distill Qwen 32B", "family": "deepseek-thinking", "attachment": false, - "reasoning": true, + "reasoning": false, "tool_call": false, "temperature": true, "release_date": "2025-01-20", @@ -79867,9 +80856,9 @@ }, "open_weights": true, "cost": { - "input": 1.74, - "output": 3.48, - "cache_read": 0.145 + "input": 1.69, + "output": 3.38, + "cache_read": 0.13 }, "limit": { "context": 1048576, @@ -79884,7 +80873,6 @@ "reasoning": false, "tool_call": false, "temperature": true, - "knowledge": "2024-10", "release_date": "2025-03-13", "last_updated": "2025-03-13", "modalities": { @@ -80048,6 +81036,35 @@ "output": 32768 } }, + { + "id": "novita-ai/inclusionai/ling-2.6-flash", + "name": "Ling-2.6-flash", + "family": "ling", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3, + "cache_read": 0.02 + }, + "limit": { + "context": 262144, + "output": 32768 + } + }, { "id": "novita-ai/kwaipilot/kat-coder-pro", "name": "Kat Coder Pro", @@ -80620,7 +81637,7 @@ { "id": "novita-ai/moonshotai/kimi-k2.6", "name": "Kimi K2.6", - "family": "kimi", + "family": "kimi-k2.6", "attachment": true, "reasoning": true, "tool_call": true, @@ -81561,64 +82578,6 @@ "output": 64000 } }, - { - "id": "novita-ai/qwen/qwen3.6-27b", - "name": "Qwen3.6-27B", - "family": "qwen3.6", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2025-04", - "release_date": "2026-04-02", - "last_updated": "2026-04-02", - "modalities": { - "input": [ - "text", - "image", - "video" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.6, - "output": 3.6 - }, - "limit": { - "context": 262144, - "output": 65536 - } - }, - { - "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", @@ -82026,6 +82985,61 @@ "output": 131072 } }, + { + "id": "nvidia/abacusai/dracarys-llama-3_1-70b-instruct", + "name": "dracarys-llama-3.1-70b-instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-09-11", + "last_updated": "2025-05-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/baai/bge-m3", + "name": "BGE M3", + "family": "bge", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-01-30", + "last_updated": "2026-04-30", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 8192, + "output": 1024 + } + }, { "id": "nvidia/black-forest-labs/flux.1-dev", "name": "FLUX.1-dev", @@ -82056,70 +83070,101 @@ } }, { - "id": "nvidia/deepseek-ai/deepseek-coder-6.7b-instruct", - "name": "Deepseek Coder 6.7b Instruct", + "id": "nvidia/black-forest-labs/flux_1-kontext-dev", + "name": "FLUX.1-Kontext-dev", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-08-12", + "last_updated": "2025-08-12", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "nvidia/black-forest-labs/flux_1-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": "nvidia/black-forest-labs/flux_2-klein-4b", + "name": "FLUX.2 Klein 4B", + "family": "flux", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2026-01-14", + "last_updated": "2026-01-31", + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "image" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 40960, + "output": 40960 + } + }, + { + "id": "nvidia/bytedance/seed-oss-36b-instruct", + "name": "ByteDance-Seed/Seed-OSS-36B-Instruct", + "family": "seed", "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 0528", - "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": 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", + "release_date": "2025-09-04", + "last_updated": "2025-11-25", "modalities": { "input": [ "text" @@ -82134,8 +83179,8 @@ "output": 0.0 }, "limit": { - "context": 128000, - "output": 8192 + "context": 262000, + "output": 262000 } }, { @@ -82256,87 +83301,6 @@ "output": 393216 } }, - { - "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", @@ -82364,61 +83328,6 @@ "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", @@ -82539,14 +83448,42 @@ } }, { - "id": "nvidia/meta/codellama-70b", - "name": "Codellama 70b", + "id": "nvidia/google/google-paligemma", + "name": "paligemma", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-05-14", + "last_updated": "2024-08-26", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/meta/esm2-650m", + "name": "esm2-650m", "attachment": false, "reasoning": false, "tool_call": false, "temperature": true, - "release_date": "2024-01-29", - "last_updated": "2024-01-29", + "release_date": "2024-08-29", + "last_updated": "2025-03-10", "modalities": { "input": [ "text" @@ -82562,18 +83499,18 @@ }, "limit": { "context": 128000, - "output": 4096 + "output": 8192 } }, { - "id": "nvidia/meta/llama-3.1-405b-instruct", - "name": "Llama 3.1 405b Instruct", + "id": "nvidia/meta/esmfold", + "name": "esmfold", "attachment": false, "reasoning": false, - "tool_call": true, + "tool_call": false, "temperature": true, - "release_date": "2024-07-16", - "last_updated": "2024-07-16", + "release_date": "2024-03-15", + "last_updated": "2025-06-12", "modalities": { "input": [ "text" @@ -82589,7 +83526,7 @@ }, "limit": { "context": 128000, - "output": 4096 + "output": 8192 } }, { @@ -82619,6 +83556,35 @@ "output": 4096 } }, + { + "id": "nvidia/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": 0.0, + "output": 0.0 + }, + "limit": { + "context": 16000, + "output": 4096 + } + }, { "id": "nvidia/meta/llama-3.2-11b-vision-instruct", "name": "Llama 3.2 11b Vision Instruct", @@ -82676,6 +83642,64 @@ "output": 4096 } }, + { + "id": "nvidia/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": "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": 32768, + "output": 32000 + } + }, + { + "id": "nvidia/meta/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": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, { "id": "nvidia/meta/llama-3.3-70b-instruct", "name": "Llama 3.3 70b Instruct", @@ -82733,15 +83757,15 @@ } }, { - "id": "nvidia/meta/llama-4-scout-17b-16e-instruct", - "name": "Llama 4 Scout 17b 16e Instruct", + "id": "nvidia/meta/llama-guard-4-12b", + "name": "Llama Guard 4 12B", + "family": "llama", "attachment": true, "reasoning": false, - "tool_call": true, + "tool_call": false, "temperature": true, - "knowledge": "2024-02", - "release_date": "2025-04-02", - "last_updated": "2025-04-02", + "release_date": "2025-04-05", + "last_updated": "2026-04-30", "modalities": { "input": [ "text", @@ -82758,260 +83782,7 @@ }, "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 + "output": 16384 } }, { @@ -83046,15 +83817,13 @@ } }, { - "id": "nvidia/minimaxai/minimax-m2.1", - "name": "MiniMax-M2.1", - "family": "minimax", + "id": "nvidia/microsoft/phi-4-multimodal-instruct", + "name": "Phi 4 Multimodal", "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2025-12-23", - "last_updated": "2025-12-23", + "reasoning": false, + "tool_call": false, + "release_date": "2025-07-26", + "last_updated": "2025-07-26", "modalities": { "input": [ "text" @@ -83063,14 +83832,14 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 0.0, "output": 0.0 }, "limit": { - "context": 204800, - "output": 131072 + "context": 128000, + "output": 16384 } }, { @@ -83130,33 +83899,6 @@ "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", @@ -83187,14 +83929,13 @@ } }, { - "id": "nvidia/mistralai/mamba-codestral-7b-v0.1", - "name": "Mamba Codestral 7b V0.1", + "id": "nvidia/mistralai/magistral-small", + "name": "Magistral Small 2506", "attachment": false, "reasoning": false, "tool_call": false, - "temperature": true, - "release_date": "2024-07-16", - "last_updated": "2024-07-16", + "release_date": "2025-09-25", + "last_updated": "2025-09-25", "modalities": { "input": [ "text" @@ -83203,55 +83944,25 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 0.0, "output": 0.0 }, "limit": { - "context": 128000, - "output": 4096 + "context": 32768, + "output": 32768 } }, { - "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", + "id": "nvidia/mistralai/mistral-7b-instruct-v03", + "name": "Mistral-7B-Instruct-v0.3", "attachment": false, "reasoning": false, "tool_call": true, "temperature": true, - "release_date": "2024-07-24", - "last_updated": "2024-07-24", + "release_date": "2025-04-01", + "last_updated": "2025-04-01", "modalities": { "input": [ "text" @@ -83266,8 +83977,8 @@ "output": 0.0 }, "limit": { - "context": 128000, - "output": 4096 + "context": 65536, + "output": 65536 } }, { @@ -83301,15 +84012,14 @@ } }, { - "id": "nvidia/mistralai/mistral-medium-3.5-128b", - "name": "Mistral Medium 3.5 128B", + "id": "nvidia/mistralai/mistral-medium-3-instruct", + "name": "Mistral Medium 3", "family": "mistral-medium", "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-04-29", - "last_updated": "2026-04-29", + "reasoning": false, + "tool_call": false, + "release_date": "2025-09-25", + "last_updated": "2025-09-25", "modalities": { "input": [ "text", @@ -83319,25 +84029,25 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 0.0, "output": 0.0 }, "limit": { - "context": 262144, - "output": 262144 + "context": 131072, + "output": 32768 } }, { - "id": "nvidia/mistralai/mistral-small-3.1-24b-instruct", - "name": "Mistral Small 3.1 24b Instruct 2503", + "id": "nvidia/mistralai/mistral-nemotron", + "name": "mistral-nemotron", "attachment": false, "reasoning": false, "tool_call": true, "temperature": true, - "release_date": "2025-03-11", - "last_updated": "2025-03-11", + "release_date": "2025-06-11", + "last_updated": "2025-06-12", "modalities": { "input": [ "text" @@ -83353,7 +84063,88 @@ }, "limit": { "context": 128000, - "output": 4096 + "output": 8192 + } + }, + { + "id": "nvidia/mistralai/mistral-small-4-119b", + "name": "mistral-small-4-119b-2603", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-16", + "last_updated": "2026-03-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/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": 0.0, + "output": 0.0 + }, + "limit": { + "context": 65536, + "output": 13108 + } + }, + { + "id": "nvidia/mistralai/mixtral-8x7b-instruct", + "name": "Mistral: Mixtral 8x7B Instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2023-12-10", + "last_updated": "2026-03-15", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 16384 } }, { @@ -83416,37 +84207,6 @@ "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/moonshotai/kimi-k2.6", "name": "Kimi K2.6", @@ -83479,16 +84239,68 @@ } }, { - "id": "nvidia/nvidia/cosmos-nemotron-34b", - "name": "Cosmos Nemotron 34B", - "family": "nemotron", - "attachment": false, - "reasoning": true, + "id": "nvidia/nvidia/active-speaker-detection", + "name": "Active Speaker Detection", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 0, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/bevformer", + "name": "bevformer", + "attachment": true, + "reasoning": false, "tool_call": false, "temperature": true, - "knowledge": "2024-01", - "release_date": "2024-01-01", - "last_updated": "2025-09-05", + "release_date": "2025-03-18", + "last_updated": "2025-07-20", + "modalities": { + "input": [ + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/nvidia/cosmos-predict1-5b", + "name": "cosmos-predict1-5b", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-03-18", + "last_updated": "2025-03-18", "modalities": { "input": [ "text", @@ -83496,111 +84308,86 @@ "video" ], "output": [ - "text" + "video" ] }, - "open_weights": false, + "open_weights": true, "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, + "context": 0, "output": 4096 } }, { - "id": "nvidia/nvidia/llama-3.1-nemotron-70b-instruct", - "name": "Llama 3.1 Nemotron 70b Instruct", - "attachment": false, + "id": "nvidia/nvidia/cosmos-transfer1-7b", + "name": "cosmos-transfer1-7b", + "attachment": true, "reasoning": false, - "tool_call": true, - "temperature": true, - "release_date": "2024-10-12", - "last_updated": "2024-10-12", + "tool_call": false, + "temperature": false, + "release_date": "2025-06-13", + "last_updated": "2025-06-30", "modalities": { "input": [ - "text" + "text", + "image", + "video" ], "output": [ - "text" + "video" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.0, "output": 0.0 }, "limit": { - "context": 128000, + "context": 0, "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", + "id": "nvidia/nvidia/cosmos-transfer2_5-2b", + "name": "cosmos-transfer2.5-2b", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2026-02-26", + "last_updated": "2026-02-26", "modalities": { "input": [ - "text" + "text", + "image", + "video" ], "output": [ - "text" + "video" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.0, "output": 0.0 }, "limit": { - "context": 131072, - "output": 8192 + "context": 0, + "output": 4096 } }, { - "id": "nvidia/nvidia/llama-3.3-nemotron-super-49b-v1", - "name": "Llama 3.3 Nemotron Super 49b V1", + "id": "nvidia/nvidia/gliner-pii", + "name": "gliner-pii", "attachment": false, "reasoning": false, "tool_call": false, "temperature": true, - "release_date": "2025-03-16", - "last_updated": "2025-03-16", + "release_date": "2026-03-03", + "last_updated": "2026-03-03", "modalities": { "input": [ "text" @@ -83609,7 +84396,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.0, "output": 0.0 @@ -83620,43 +84407,14 @@ } }, { - "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", + "id": "nvidia/nvidia/llama-3_1-nemotron-safety-guard-8b-v3", + "name": "llama-3.1-nemotron-safety-guard-8b-v3", "attachment": false, "reasoning": false, "tool_call": false, "temperature": false, - "knowledge": "2025-03", - "release_date": "2025-03-18", - "last_updated": "2025-03-18", + "release_date": "2025-10-28", + "last_updated": "2025-10-28", "modalities": { "input": [ "text" @@ -83665,7 +84423,34 @@ "text" ] }, - "open_weights": false, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/llama-3_2-nemoretriever-300m-embed-v1", + "name": "llama-3_2-nemoretriever-300m-embed-v1", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-07-24", + "last_updated": "2025-07-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, "cost": { "input": 0.0, "output": 0.0 @@ -83676,14 +84461,16 @@ } }, { - "id": "nvidia/nvidia/llama3-chatqa-1.5-70b", - "name": "Llama3 Chatqa 1.5 70b", + "id": "nvidia/nvidia/llama-3_3-nemotron-super-49b-v1", + "name": "Llama 3.3 Nemotron Super 49B v1", + "family": "nemotron", "attachment": false, - "reasoning": false, + "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2024-04-28", - "last_updated": "2024-04-28", + "knowledge": "2023-12", + "release_date": "2025-04-07", + "last_updated": "2025-04-07", "modalities": { "input": [ "text" @@ -83692,7 +84479,92 @@ "text" ] }, - "open_weights": false, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "nvidia/nvidia/llama-3_3-nemotron-super-49b-v1_5", + "name": "Llama 3.3 Nemotron Super 49B v1.5", + "family": "nemotron", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2023-12", + "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": 131072 + } + }, + { + "id": "nvidia/nvidia/llama-nemotron-embed-vl-1b-v2", + "name": "llama-nemotron-embed-vl-1b-v2", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2026-02-10", + "last_updated": "2026-02-10", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 2048 + } + }, + { + "id": "nvidia/nvidia/llama-nemotron-rerank-vl-1b-v2", + "name": "llama-nemotron-rerank-vl-1b-v2", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2026-03-31", + "last_updated": "2026-03-31", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "open_weights": true, "cost": { "input": 0.0, "output": 0.0 @@ -83703,25 +84575,24 @@ } }, { - "id": "nvidia/nvidia/nemoretriever-ocr-v1", - "name": "NeMo Retriever OCR v1", - "family": "nemoretriever", - "attachment": false, + "id": "nvidia/nvidia/magpie-tts-zeroshot", + "name": "magpie-tts-zeroshot", + "attachment": true, "reasoning": false, "tool_call": false, "temperature": false, - "knowledge": "2024-01", - "release_date": "2024-01-01", - "last_updated": "2025-09-05", + "release_date": "2025-05-22", + "last_updated": "2025-06-12", "modalities": { "input": [ - "image" + "text", + "audio" ], "output": [ - "text" + "audio" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.0, "output": 0.0 @@ -83731,6 +84602,33 @@ "output": 4096 } }, + { + "id": "nvidia/nvidia/nemotron-3-content-safety", + "name": "nemotron-3-content-safety", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, { "id": "nvidia/nvidia/nemotron-3-nano-30b-a3b", "name": "nemotron-3-nano-30b-a3b", @@ -83821,14 +84719,14 @@ } }, { - "id": "nvidia/nvidia/nemotron-4-340b-instruct", - "name": "Nemotron 4 340b Instruct", + "id": "nvidia/nvidia/nemotron-content-safety-reasoning-4b", + "name": "nemotron-content-safety-reasoning-4b", "attachment": false, - "reasoning": false, - "tool_call": true, - "temperature": true, - "release_date": "2024-06-13", - "last_updated": "2024-06-13", + "reasoning": true, + "tool_call": false, + "temperature": false, + "release_date": "2026-01-22", + "last_updated": "2026-01-22", "modalities": { "input": [ "text" @@ -83837,7 +84735,7 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.0, "output": 0.0 @@ -83847,6 +84745,115 @@ "output": 4096 } }, + { + "id": "nvidia/nvidia/nemotron-mini-4b-instruct", + "name": "nemotron-mini-4b-instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-08-21", + "last_updated": "2024-08-26", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/nvidia/nemotron-voicechat", + "name": "nemotron-voicechat", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2026-03-16", + "last_updated": "2026-03-16", + "modalities": { + "input": [ + "text", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/nvidia/nv-embed-v1", + "name": "nv-embed-v1", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-06-07", + "last_updated": "2025-07-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 2048 + } + }, + { + "id": "nvidia/nvidia/nv-embedcode-7b-v1", + "name": "nv-embedcode-7b-v1", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-03-17", + "last_updated": "2025-05-29", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 32768, + "output": 2048 + } + }, { "id": "nvidia/nvidia/nvidia-nemotron-nano-9b-v2", "name": "nvidia-nemotron-nano-9b-v2", @@ -83877,19 +84884,179 @@ } }, { - "id": "nvidia/nvidia/parakeet-tdt-0.6b-v2", - "name": "Parakeet TDT 0.6B v2", - "family": "parakeet", + "id": "nvidia/nvidia/rerank-qa-mistral-4b", + "name": "rerank-qa-mistral-4b", "attachment": false, "reasoning": false, "tool_call": false, "temperature": false, - "knowledge": "2024-01", - "release_date": "2024-01-01", - "last_updated": "2025-09-05", + "release_date": "2024-03-17", + "last_updated": "2025-01-17", "modalities": { "input": [ - "audio" + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/riva-translate-4b-instruct-v1_1", + "name": "riva-translate-4b-instruct-v1_1", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2025-12-12", + "last_updated": "2025-12-12", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/sparsedrive", + "name": "sparsedrive", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-03-18", + "last_updated": "2025-07-20", + "modalities": { + "input": [ + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/nvidia/streampetr", + "name": "streampetr", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-11-13", + "last_updated": "2025-11-13", + "modalities": { + "input": [ + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/nvidia/studiovoice", + "name": "studiovoice", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2024-10-03", + "last_updated": "2025-06-13", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, + { + "id": "nvidia/nvidia/synthetic-video-detector", + "name": "synthetic-video-detector", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-04-16", + "last_updated": "2026-04-16", + "modalities": { + "input": [ + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 0, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/usdcode", + "name": "usdcode", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2026-01-01", + "last_updated": "2026-01-01", + "modalities": { + "input": [ + "text" ], "output": [ "text" @@ -83900,6 +85067,33 @@ "input": 0.0, "output": 0.0 }, + "limit": { + "context": 128000, + "output": 4096 + } + }, + { + "id": "nvidia/nvidia/usdvalidate", + "name": "usdvalidate", + "attachment": false, + "reasoning": false, + "tool_call": false, + "temperature": false, + "release_date": "2024-07-24", + "last_updated": "2025-01-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, "limit": { "context": 0, "output": 4096 @@ -83934,6 +85128,34 @@ "output": 8192 } }, + { + "id": "nvidia/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": "nvidia/openai/whisper-large-v3", "name": "Whisper Large v3", @@ -83963,6 +85185,64 @@ "output": 4096 } }, + { + "id": "nvidia/qwen/qwen-image", + "name": "Qwen Image", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-08-07", + "last_updated": "2025-08-07", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 0, + "output": 0 + } + }, + { + "id": "nvidia/qwen/qwen-image-edit", + "name": "Qwen Image Edit", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": false, + "temperature": true, + "release_date": "2025-08-19", + "last_updated": "2025-08-19", + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "open_weights": false, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 0, + "output": 0 + } + }, { "id": "nvidia/qwen/qwen2.5-coder-32b-instruct", "name": "Qwen2.5 Coder 32b Instruct", @@ -83990,62 +85270,6 @@ "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", @@ -84133,6 +85357,37 @@ "output": 16384 } }, + { + "id": "nvidia/qwen/qwen3.5-122b-a10b", + "name": "Qwen3.5 122B-A10B", + "family": "qwen", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-23", + "last_updated": "2026-02-23", + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, { "id": "nvidia/qwen/qwen3.5-397b-a17b", "name": "Qwen3.5-397B-A17B", @@ -84164,14 +85419,14 @@ } }, { - "id": "nvidia/qwen/qwq-32b", - "name": "Qwq 32b", + "id": "nvidia/sarvamai/sarvam-m", + "name": "sarvam-m", "attachment": false, - "reasoning": true, - "tool_call": false, + "reasoning": false, + "tool_call": true, "temperature": true, - "release_date": "2025-03-05", - "last_updated": "2025-03-05", + "release_date": "2025-07-25", + "last_updated": "2025-07-25", "modalities": { "input": [ "text" @@ -84187,7 +85442,7 @@ }, "limit": { "context": 128000, - "output": 4096 + "output": 8192 } }, { @@ -84217,6 +85472,33 @@ "output": 16384 } }, + { + "id": "nvidia/upstage/solar-10_7b-instruct", + "name": "solar-10.7b-instruct", + "attachment": false, + "reasoning": false, + "tool_call": true, + "temperature": true, + "release_date": "2024-06-05", + "last_updated": "2025-04-10", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 128000, + "output": 8192 + } + }, { "id": "nvidia/z-ai/glm-5.1", "name": "GLM-5.1", @@ -84274,34 +85556,6 @@ "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", @@ -84691,7 +85945,7 @@ "cost": {}, "limit": { "context": 202752, - "output": 202752 + "output": 131072 } }, { @@ -84793,8 +86047,8 @@ } }, { - "id": "ollama-cloud/kimi-k2.6:cloud", - "name": "kimi-k2.6:cloud", + "id": "ollama-cloud/kimi-k2.6", + "name": "kimi-k2.6", "family": "kimi", "attachment": true, "reasoning": true, @@ -85231,7 +86485,7 @@ "cost": {}, "limit": { "context": 262144, - "output": 262144 + "output": 65536 } }, { @@ -86905,7 +88159,7 @@ }, { "id": "opencode-go/kimi-k2.6", - "name": "Kimi K2.6 (3x limits)", + "name": "Kimi K2.6", "family": "kimi-k2.6", "attachment": true, "reasoning": true, @@ -86926,9 +88180,9 @@ }, "open_weights": true, "cost": { - "input": 0.32, - "output": 1.34, - "cache_read": 0.054 + "input": 0.95, + "output": 4.0, + "cache_read": 0.16 }, "limit": { "context": 262144, @@ -87014,7 +88268,7 @@ "text", "image", "audio", - "pdf" + "video" ], "output": [ "text" @@ -87515,6 +88769,36 @@ "output": 64000 } }, + { + "id": "opencode/deepseek-v4-flash-free", + "name": "DeepSeek V4 Flash Free", + "family": "deepseek-flash-free", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-05", + "release_date": "2026-04-24", + "last_updated": "2026-04-24", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, { "id": "opencode/gemini-3-flash", "name": "Gemini 3 Flash", @@ -87881,9 +89165,9 @@ }, "open_weights": false, "cost": { - "input": 0.0, - "output": 0.0, - "cache_read": 0.0 + "input": 0.05, + "output": 0.4, + "cache_read": 0.005 }, "limit": { "context": 400000, @@ -88974,6 +90258,35 @@ "output": 64000 } }, + { + "id": "opencode/ring-2.6-1t-free", + "name": "Ring 2.6 1T Free", + "family": "ring-1t-free", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-06", + "release_date": "2026-05-08", + "last_updated": "2026-05-08", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0 + }, + "limit": { + "context": 262000, + "output": 66000 + } + }, { "id": "opencode/trinity-large-preview-free", "name": "Trinity Large Preview", @@ -93128,6 +94441,68 @@ "output": 8192 } }, + { + "id": "openrouter/qwen/qwen-3.6-27b", + "name": "Qwen3.6 27B", + "family": "qwen", + "attachment": true, + "reasoning": false, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.195, + "output": 1.56 + }, + "limit": { + "context": 262144, + "output": 81920 + } + }, + { + "id": "openrouter/qwen/qwen-plus", + "name": "Qwen: Qwen-Plus", + "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": 0.26, + "output": 0.78, + "cache_read": 0.052, + "cache_write": 0.325 + }, + "limit": { + "context": 1000000, + "output": 32768 + } + }, { "id": "openrouter/qwen/qwen2.5-vl-72b-instruct", "name": "Qwen2.5 VL 72B Instruct", @@ -93354,13 +94729,46 @@ "open_weights": false, "cost": { "input": 0.3, - "output": 1.5 + "output": 1.5, + "cache_read": 0.039, + "cache_write": 0.24375 }, "limit": { "context": 128000, "output": 66536 } }, + { + "id": "openrouter/qwen/qwen3-coder-plus", + "name": "Qwen3 Coder Plus", + "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": true, + "cost": { + "input": 0.65, + "output": 3.25, + "cache_read": 0.13, + "cache_write": 0.8125 + }, + "limit": { + "context": 1000000, + "output": 65536 + } + }, { "id": "openrouter/qwen/qwen3-coder:exacto", "name": "Qwen3 Coder (exacto)", @@ -93411,7 +94819,9 @@ "open_weights": false, "cost": { "input": 1.2, - "output": 6.0 + "output": 6.0, + "cache_read": 0.156, + "cache_write": 0.975 }, "limit": { "context": 262144, @@ -93592,7 +95002,9 @@ "open_weights": false, "cost": { "input": 0.325, - "output": 1.95 + "output": 1.95, + "cache_read": 0.0325, + "cache_write": 0.40625 }, "limit": { "context": 1000000, @@ -93719,6 +95131,36 @@ "output": 256000 } }, + { + "id": "openrouter/tencent/hy3-preview", + "name": "Hy3 preview", + "family": "Hy", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-04-20", + "last_updated": "2026-04-20", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.066, + "output": 0.26, + "cache_read": 0.029, + "cache_write": 0.029 + }, + "limit": { + "context": 256000, + "output": 64000 + } + }, { "id": "openrouter/x-ai/grok-3", "name": "Grok 3", @@ -94060,15 +95502,15 @@ }, { "id": "openrouter/xiaomi/mimo-v2-flash", - "name": "MiMo-V2-Flash", + "name": "Xiaomi: MiMo-V2-Flash", "family": "mimo", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2024-12", - "release_date": "2025-12-14", - "last_updated": "2025-12-14", + "knowledge": "2024-12-01", + "release_date": "2025-12-16", + "last_updated": "2026-02-04", "modalities": { "input": [ "text" @@ -94090,106 +95532,15 @@ }, { "id": "openrouter/xiaomi/mimo-v2-omni", - "name": "MiMo-V2-Omni", - "family": "mimo", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-03-18", - "last_updated": "2026-03-18", - "modalities": { - "input": [ - "text", - "image", - "video", - "audio" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.4, - "output": 2.0, - "cache_read": 0.08 - }, - "limit": { - "context": 262144, - "output": 65536 - } - }, - { - "id": "openrouter/xiaomi/mimo-v2-pro", - "name": "MiMo-V2-Pro", - "family": "mimo", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "release_date": "2026-03-18", - "last_updated": "2026-03-18", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 1.0, - "output": 3.0, - "cache_read": 0.2 - }, - "limit": { - "context": 1048576, - "output": 65536 - } - }, - { - "id": "openrouter/xiaomi/mimo-v2.5", - "name": "MiMo-V2.5", + "name": "Xiaomi: MiMo-V2-Omni", "family": "mimo", "attachment": true, "reasoning": true, "tool_call": true, "temperature": true, "knowledge": "2024-12", - "release_date": "2026-04-22", - "last_updated": "2026-04-22", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": false, - "cost": { - "input": 0.4, - "output": 2.0, - "cache_read": 0.08 - }, - "limit": { - "context": 1048576, - "output": 131072 - } - }, - { - "id": "openrouter/xiaomi/mimo-v2.5-pro", - "name": "MiMo-V2.5-Pro", - "family": "mimo", - "attachment": true, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2024-12", - "release_date": "2026-04-22", - "last_updated": "2026-04-22", + "release_date": "2026-03-18", + "last_updated": "2026-03-18", "modalities": { "input": [ "text", @@ -94203,6 +95554,99 @@ ] }, "open_weights": false, + "cost": { + "input": 0.4, + "output": 2.0, + "cache_read": 0.08 + }, + "limit": { + "context": 262144, + "output": 131072 + } + }, + { + "id": "openrouter/xiaomi/mimo-v2-pro", + "name": "Xiaomi: MiMo-V2-Pro", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-03-18", + "last_updated": "2026-03-18", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 1.0, + "output": 3.0, + "cache_read": 0.2 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "openrouter/xiaomi/mimo-v2.5", + "name": "Xiaomi: MiMo-V2.5", + "family": "mimo", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.4, + "output": 2.0, + "cache_read": 0.08 + }, + "limit": { + "context": 1048576, + "output": 131072 + } + }, + { + "id": "openrouter/xiaomi/mimo-v2.5-pro", + "name": "Xiaomi: MiMo-V2.5-Pro", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12", + "release_date": "2026-04-22", + "last_updated": "2026-04-22", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, "cost": { "input": 1.0, "output": 3.0, @@ -96172,6 +97616,58 @@ "output": 0 } }, + { + "id": "poe/empiriolabs/deepseek-v4-flash-el", + "name": "DeepSeek-V4-Flash-EL", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-04-24", + "last_updated": "2026-05-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.14, + "output": 0.28 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, + { + "id": "poe/empiriolabs/deepseek-v4-pro-el", + "name": "DeepSeek-V4-Pro-EL", + "attachment": true, + "reasoning": true, + "tool_call": true, + "release_date": "2026-04-24", + "last_updated": "2026-05-02", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 1.67, + "output": 3.33 + }, + "limit": { + "context": 1000000, + "output": 384000 + } + }, { "id": "poe/fireworks-ai/kimi-k2.5-fw", "name": "Kimi-K2.5-FW", @@ -97236,6 +98732,37 @@ "output": 262144 } }, + { + "id": "poe/novita/kimi-k2.6", + "name": "Kimi-K2.6", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2025-04", + "release_date": "2026-04-20", + "last_updated": "2026-05-02", + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.96, + "output": 4.04, + "cache_read": 0.16 + }, + "limit": { + "context": 262144, + "output": 262144 + } + }, { "id": "poe/novita/minimax-m2.1", "name": "minimax-m2.1", @@ -100813,12 +102340,14 @@ { "id": "qiniu-ai/mimo-v2-flash", "name": "Mimo-V2-Flash", + "family": "mimo", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, - "release_date": "2025-12-17", - "last_updated": "2025-12-17", + "knowledge": "2024-12-01", + "release_date": "2025-12-16", + "last_updated": "2026-02-04", "modalities": { "input": [ "text" @@ -100827,8 +102356,12 @@ "text" ] }, - "open_weights": false, - "cost": {}, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3, + "cache_read": 0.01 + }, "limit": { "context": 256000, "output": 256000 @@ -101706,12 +103239,14 @@ { "id": "qiniu-ai/xiaomi/mimo-v2-flash", "name": "Xiaomi/Mimo-V2-Flash", + "family": "mimo", "attachment": false, "reasoning": true, - "tool_call": false, + "tool_call": true, "temperature": true, - "release_date": "2025-12-26", - "last_updated": "2025-12-26", + "knowledge": "2024-12-01", + "release_date": "2025-12-16", + "last_updated": "2026-02-04", "modalities": { "input": [ "text" @@ -101720,8 +103255,12 @@ "text" ] }, - "open_weights": false, - "cost": {}, + "open_weights": true, + "cost": { + "input": 0.1, + "output": 0.3, + "cache_read": 0.01 + }, "limit": { "context": 256000, "output": 256000 @@ -104148,6 +105687,56 @@ "output": 8192 } }, + { + "id": "sarvam/sarvam-105b", + "name": "Sarvam-105B", + "family": "sarvam", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-18", + "last_updated": "2026-03-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 131072, + "output": 131072 + } + }, + { + "id": "sarvam/sarvam-30b", + "name": "Sarvam-30B", + "family": "sarvam", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-02-18", + "last_updated": "2026-03-06", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": {}, + "limit": { + "context": 65536, + "output": 65536 + } + }, { "id": "scaleway/bge-multilingual-gemma2", "name": "BGE Multilingual Gemma2", @@ -112030,7 +113619,7 @@ "tool_call": true, "temperature": true, "release_date": "2026-03-12", - "last_updated": "2026-04-19", + "last_updated": "2026-05-07", "modalities": { "input": [ "text", @@ -112042,8 +113631,8 @@ }, "open_weights": false, "cost": { - "input": 2.27, - "output": 6.8, + "input": 1.42, + "output": 2.83, "cache_read": 0.23 }, "limit": { @@ -112060,7 +113649,7 @@ "tool_call": false, "temperature": true, "release_date": "2026-03-12", - "last_updated": "2026-04-19", + "last_updated": "2026-05-07", "modalities": { "input": [ "text", @@ -112072,8 +113661,8 @@ }, "open_weights": false, "cost": { - "input": 2.27, - "output": 6.8, + "input": 1.42, + "output": 2.83, "cache_read": 0.23 }, "limit": { @@ -112232,36 +113821,6 @@ "output": 65536 } }, - { - "id": "venice/kimi-k2-thinking", - "name": "Kimi K2 Thinking", - "family": "kimi-thinking", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2024-04", - "release_date": "2025-12-10", - "last_updated": "2026-03-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.75, - "output": 3.2, - "cache_read": 0.375 - }, - "limit": { - "context": 256000, - "output": 65536 - } - }, { "id": "venice/llama-3.2-3b", "name": "Llama 3.2 3B", @@ -112851,12 +114410,12 @@ "name": "OpenAI GPT OSS 120B", "family": "gpt-oss", "attachment": false, - "reasoning": false, + "reasoning": true, "tool_call": true, "temperature": true, "knowledge": "2025-07", "release_date": "2025-11-06", - "last_updated": "2026-03-12", + "last_updated": "2026-05-06", "modalities": { "input": [ "text" @@ -113085,35 +114644,6 @@ "output": 65536 } }, - { - "id": "venice/qwen3-coder-480b-a35b-instruct", - "name": "Qwen 3 Coder 480b", - "family": "qwen", - "attachment": false, - "reasoning": false, - "tool_call": true, - "temperature": true, - "knowledge": "2025-07", - "release_date": "2025-04-29", - "last_updated": "2026-03-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.75, - "output": 3.0 - }, - "limit": { - "context": 256000, - "output": 65536 - } - }, { "id": "venice/qwen3-coder-480b-a35b-instruct-turbo", "name": "Qwen 3 Coder 480B Turbo", @@ -113201,35 +114731,6 @@ "output": 16384 } }, - { - "id": "venice/venice-uncensored", - "name": "Venice Uncensored 1.1", - "family": "venice", - "attachment": false, - "reasoning": false, - "tool_call": false, - "temperature": true, - "knowledge": "2023-10", - "release_date": "2025-03-18", - "last_updated": "2026-03-12", - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "open_weights": true, - "cost": { - "input": 0.2, - "output": 0.9 - }, - "limit": { - "context": 32000, - "output": 8192 - } - }, { "id": "venice/venice-uncensored-1.2", "name": "Venice Uncensored 1.2", @@ -115861,6 +117362,37 @@ "output": 32768 } }, + { + "id": "vercel/google/gemini-3.1-flash-lite", + "name": "Gemini 3.1 Flash Lite", + "family": "gemini", + "attachment": true, + "reasoning": true, + "tool_call": true, + "temperature": true, + "release_date": "2026-05-07", + "last_updated": "2026-05-08", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "open_weights": false, + "cost": { + "input": 0.25, + "output": 1.5, + "cache_read": 0.03 + }, + "limit": { + "context": 1000000, + "output": 65000 + } + }, { "id": "vercel/google/gemini-3.1-flash-lite-preview", "name": "Gemini 3.1 Flash Lite Preview", @@ -120297,7 +121829,8 @@ "input": [ "text", "image", - "pdf" + "audio", + "video" ], "output": [ "text" @@ -120326,9 +121859,7 @@ "last_updated": "2026-05-01", "modalities": { "input": [ - "text", - "image", - "pdf" + "text" ], "output": [ "text" @@ -121286,37 +122817,6 @@ "output": 4096 } }, - { - "id": "wafer.ai/DeepSeek-V4-Pro", - "name": "DeepSeek V4 Pro", - "family": "deepseek-thinking", - "attachment": false, - "reasoning": true, - "tool_call": true, - "temperature": true, - "knowledge": "2025-05", - "release_date": "2026-04-24", - "last_updated": "2026-04-24", - "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": 1000000, - "output": 384000 - } - }, { "id": "wafer.ai/GLM-5.1", "name": "GLM-5.1", @@ -122442,6 +123942,36 @@ "output": 4096 } }, + { + "id": "xiaomi-token-plan-ams/mimo-v2-flash", + "name": "MiMo-V2-Flash", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12-01", + "release_date": "2025-12-16", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 262144, + "output": 65536 + } + }, { "id": "xiaomi-token-plan-ams/mimo-v2-omni", "name": "MiMo-V2-Omni", @@ -122465,22 +123995,22 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 0.0, "output": 0.0, "cache_read": 0.0 }, "limit": { - "context": 256000, - "output": 128000 + "context": 262144, + "output": 131072 } }, { "id": "xiaomi-token-plan-ams/mimo-v2-pro", "name": "MiMo-V2-Pro", "family": "mimo", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -122495,15 +124025,15 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 0.0, "output": 0.0, "cache_read": 0.0 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { @@ -122529,14 +124059,14 @@ "output": 0.0 }, "limit": { - "context": 8000, - "output": 16000 + "context": 8192, + "output": 16384 } }, { "id": "xiaomi-token-plan-ams/mimo-v2.5", "name": "MiMo-V2.5", - "family": "mimo-v2.5", + "family": "mimo", "attachment": true, "reasoning": true, "tool_call": true, @@ -122549,8 +124079,7 @@ "text", "image", "audio", - "video", - "pdf" + "video" ], "output": [ "text" @@ -122563,15 +124092,15 @@ "cache_read": 0.0 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { "id": "xiaomi-token-plan-ams/mimo-v2.5-pro", "name": "MiMo-V2.5-Pro", - "family": "mimo-v2.5-pro", - "attachment": true, + "family": "mimo", + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -122593,8 +124122,38 @@ "cache_read": 0.0 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 + } + }, + { + "id": "xiaomi-token-plan-cn/mimo-v2-flash", + "name": "MiMo-V2-Flash", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12-01", + "release_date": "2025-12-16", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 262144, + "output": 65536 } }, { @@ -122620,22 +124179,22 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 0.0, "output": 0.0, "cache_read": 0.0 }, "limit": { - "context": 256000, - "output": 128000 + "context": 262144, + "output": 131072 } }, { "id": "xiaomi-token-plan-cn/mimo-v2-pro", "name": "MiMo-V2-Pro", "family": "mimo", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -122650,15 +124209,15 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 0.0, "output": 0.0, "cache_read": 0.0 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { @@ -122684,14 +124243,14 @@ "output": 0.0 }, "limit": { - "context": 8000, - "output": 16000 + "context": 8192, + "output": 16384 } }, { "id": "xiaomi-token-plan-cn/mimo-v2.5", "name": "MiMo-V2.5", - "family": "mimo-v2.5", + "family": "mimo", "attachment": true, "reasoning": true, "tool_call": true, @@ -122704,8 +124263,7 @@ "text", "image", "audio", - "video", - "pdf" + "video" ], "output": [ "text" @@ -122718,15 +124276,15 @@ "cache_read": 0.0 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { "id": "xiaomi-token-plan-cn/mimo-v2.5-pro", "name": "MiMo-V2.5-Pro", - "family": "mimo-v2.5-pro", - "attachment": true, + "family": "mimo", + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -122748,8 +124306,38 @@ "cache_read": 0.0 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 + } + }, + { + "id": "xiaomi-token-plan-sgp/mimo-v2-flash", + "name": "MiMo-V2-Flash", + "family": "mimo", + "attachment": false, + "reasoning": true, + "tool_call": true, + "temperature": true, + "knowledge": "2024-12-01", + "release_date": "2025-12-16", + "last_updated": "2026-02-04", + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "open_weights": true, + "cost": { + "input": 0.0, + "output": 0.0, + "cache_read": 0.0 + }, + "limit": { + "context": 262144, + "output": 65536 } }, { @@ -122775,22 +124363,22 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 0.0, "output": 0.0, "cache_read": 0.0 }, "limit": { - "context": 256000, - "output": 128000 + "context": 262144, + "output": 131072 } }, { "id": "xiaomi-token-plan-sgp/mimo-v2-pro", "name": "MiMo-V2-Pro", "family": "mimo", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -122805,15 +124393,15 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 0.0, "output": 0.0, "cache_read": 0.0 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { @@ -122839,14 +124427,14 @@ "output": 0.0 }, "limit": { - "context": 8000, - "output": 16000 + "context": 8192, + "output": 16384 } }, { "id": "xiaomi-token-plan-sgp/mimo-v2.5", "name": "MiMo-V2.5", - "family": "mimo-v2.5", + "family": "mimo", "attachment": true, "reasoning": true, "tool_call": true, @@ -122859,8 +124447,7 @@ "text", "image", "audio", - "video", - "pdf" + "video" ], "output": [ "text" @@ -122873,15 +124460,15 @@ "cache_read": 0.0 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { "id": "xiaomi-token-plan-sgp/mimo-v2.5-pro", "name": "MiMo-V2.5-Pro", - "family": "mimo-v2.5-pro", - "attachment": true, + "family": "mimo", + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -122903,8 +124490,8 @@ "cache_read": 0.0 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { @@ -122933,8 +124520,8 @@ "cache_read": 0.01 }, "limit": { - "context": 256000, - "output": 64000 + "context": 262144, + "output": 65536 } }, { @@ -122960,22 +124547,22 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 0.4, "output": 2.0, "cache_read": 0.08 }, "limit": { - "context": 256000, - "output": 128000 + "context": 262144, + "output": 131072 } }, { "id": "xiaomi/mimo-v2-pro", "name": "MiMo-V2-Pro", "family": "mimo", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -122990,15 +124577,15 @@ "text" ] }, - "open_weights": true, + "open_weights": false, "cost": { "input": 1.0, "output": 3.0, "cache_read": 0.2 }, "limit": { - "context": 1000000, - "output": 128000 + "context": 1048576, + "output": 131072 } }, { @@ -123014,13 +124601,16 @@ "last_updated": "2026-04-22", "modalities": { "input": [ - "text" + "text", + "image", + "audio", + "video" ], "output": [ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.4, "output": 2.0, @@ -123035,7 +124625,7 @@ "id": "xiaomi/mimo-v2.5-pro", "name": "MiMo-V2.5-Pro", "family": "mimo", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -123044,17 +124634,13 @@ "last_updated": "2026-04-22", "modalities": { "input": [ - "text", - "image", - "audio", - "video", - "pdf" + "text" ], "output": [ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 1.0, "output": 3.0, @@ -125974,13 +127560,14 @@ { "id": "zenmux/xiaomi/mimo-v2-flash", "name": "MiMo-V2-Flash", + "family": "mimo", "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01-01", - "release_date": "2025-12-17", - "last_updated": "2025-12-17", + "knowledge": "2024-12-01", + "release_date": "2025-12-16", + "last_updated": "2026-02-04", "modalities": { "input": [ "text" @@ -125989,32 +127576,35 @@ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.1, "output": 0.3, "cache_read": 0.01 }, "limit": { - "context": 262000, - "output": 64000 + "context": 262144, + "output": 65536 } }, { "id": "zenmux/xiaomi/mimo-v2-omni", "name": "MiMo V2 Omni", + "family": "mimo", "attachment": true, - "reasoning": false, + "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01-01", - "release_date": "2026-03-20", - "last_updated": "2026-03-20", + "knowledge": "2024-12", + "release_date": "2026-03-18", + "last_updated": "2026-03-18", "modalities": { "input": [ "text", "image", - "video" + "audio", + "video", + "pdf" ], "output": [ "text" @@ -126023,7 +127613,8 @@ "open_weights": false, "cost": { "input": 0.4, - "output": 2.0 + "output": 2.0, + "cache_read": 0.08 }, "limit": { "context": 265000, @@ -126033,18 +127624,17 @@ { "id": "zenmux/xiaomi/mimo-v2-pro", "name": "MiMo V2 Pro", - "attachment": true, + "family": "mimo", + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, - "knowledge": "2025-01-01", - "release_date": "2026-03-20", - "last_updated": "2026-03-20", + "knowledge": "2024-12", + "release_date": "2026-03-18", + "last_updated": "2026-03-18", "modalities": { "input": [ - "text", - "image", - "video" + "text" ], "output": [ "text" @@ -126052,8 +127642,9 @@ }, "open_weights": false, "cost": { - "input": 1.5, - "output": 4.5 + "input": 1.0, + "output": 3.0, + "cache_read": 0.2 }, "limit": { "context": 1000000, @@ -126073,13 +127664,16 @@ "last_updated": "2026-04-22", "modalities": { "input": [ - "text" + "text", + "image", + "audio", + "video" ], "output": [ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 0.4, "output": 2.0, @@ -126094,7 +127688,7 @@ "id": "zenmux/xiaomi/mimo-v2.5-pro", "name": "MiMo-V2.5-Pro", "family": "mimo", - "attachment": true, + "attachment": false, "reasoning": true, "tool_call": true, "temperature": true, @@ -126103,17 +127697,13 @@ "last_updated": "2026-04-22", "modalities": { "input": [ - "text", - "image", - "audio", - "video", - "pdf" + "text" ], "output": [ "text" ] }, - "open_weights": false, + "open_weights": true, "cost": { "input": 1.0, "output": 3.0, diff --git a/crates/goose/src/providers/canonical/data/provider_metadata.json b/crates/goose/src/providers/canonical/data/provider_metadata.json index e7560817c5..55d28e664c 100644 --- a/crates/goose/src/providers/canonical/data/provider_metadata.json +++ b/crates/goose/src/providers/canonical/data/provider_metadata.json @@ -98,6 +98,17 @@ ], "model_count": 6 }, + { + "id": "claudinio", + "display_name": "Claudinio", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.claudin.io/v1", + "doc": "https://claudin.io", + "env": [ + "CLAUDINIO_API_KEY" + ], + "model_count": 1 + }, { "id": "deepseek", "display_name": "DeepSeek", @@ -164,6 +175,18 @@ ], "model_count": 14 }, + { + "id": "databricks", + "display_name": "Databricks", + "npm": "@ai-sdk/openai-compatible", + "api": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", + "doc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", + "env": [ + "DATABRICKS_HOST", + "DATABRICKS_TOKEN" + ], + "model_count": 25 + }, { "id": "io-net", "display_name": "IO.NET", @@ -186,6 +209,17 @@ ], "model_count": 80 }, + { + "id": "firepass", + "display_name": "Fireworks (Firepass)", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.fireworks.ai/inference/v1/", + "doc": "https://docs.fireworks.ai/firepass", + "env": [ + "FIREPASS_API_KEY" + ], + "model_count": 1 + }, { "id": "minimax-cn-coding-plan", "display_name": "MiniMax Coding Plan (minimaxi.com)", @@ -283,7 +317,7 @@ "env": [ "XIAOMI_API_KEY" ], - "model_count": 5 + "model_count": 6 }, { "id": "wandb", @@ -305,7 +339,7 @@ "env": [ "CHUTES_API_KEY" ], - "model_count": 70 + "model_count": 39 }, { "id": "dinference", @@ -349,7 +383,18 @@ "env": [ "KILO_API_KEY" ], - "model_count": 355 + "model_count": 357 + }, + { + "id": "auriko", + "display_name": "Auriko", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.auriko.ai/v1", + "doc": "https://docs.auriko.ai", + "env": [ + "AURIKO_API_KEY" + ], + "model_count": 15 }, { "id": "morph", @@ -393,7 +438,7 @@ "env": [ "XIAOMI_API_KEY" ], - "model_count": 5 + "model_count": 6 }, { "id": "zai", @@ -415,7 +460,7 @@ "env": [ "OPENCODE_API_KEY" ], - "model_count": 58 + "model_count": 60 }, { "id": "stepfun", @@ -437,7 +482,7 @@ "env": [ "NEBIUS_API_KEY" ], - "model_count": 49 + "model_count": 31 }, { "id": "poe", @@ -448,7 +493,7 @@ "env": [ "POE_API_KEY" ], - "model_count": 132 + "model_count": 135 }, { "id": "helicone", @@ -591,7 +636,7 @@ "env": [ "WAFER_API_KEY" ], - "model_count": 3 + "model_count": 2 }, { "id": "cloudferro-sherlock", @@ -657,7 +702,7 @@ "env": [ "NVIDIA_API_KEY" ], - "model_count": 82 + "model_count": 92 }, { "id": "inference", @@ -701,7 +746,7 @@ "env": [ "DIGITALOCEAN_ACCESS_TOKEN" ], - "model_count": 63 + "model_count": 76 }, { "id": "vultr", @@ -789,7 +834,7 @@ "env": [ "LLMGATEWAY_API_KEY" ], - "model_count": 190 + "model_count": 196 }, { "id": "cloudflare-workers-ai", @@ -903,6 +948,17 @@ ], "model_count": 14 }, + { + "id": "sarvam", + "display_name": "Sarvam AI", + "npm": "@ai-sdk/openai-compatible", + "api": "https://api.sarvam.ai/v1", + "doc": "https://docs.sarvam.ai/api-reference-docs/getting-started/models", + "env": [ + "SARVAM_API_KEY" + ], + "model_count": 2 + }, { "id": "qihang-ai", "display_name": "QiHang", @@ -1000,7 +1056,7 @@ "env": [ "XIAOMI_API_KEY" ], - "model_count": 5 + "model_count": 6 }, { "id": "zhipuai", diff --git a/ui/desktop/openapi.json b/ui/desktop/openapi.json index fc15113a54..81cf91e2a5 100644 --- a/ui/desktop/openapi.json +++ b/ui/desktop/openapi.json @@ -10,7 +10,7 @@ "license": { "name": "Apache-2.0" }, - "version": "1.34.0" + "version": "1.34.1" }, "paths": { "/action-required/tool-confirmation": { diff --git a/ui/desktop/package.json b/ui/desktop/package.json index b4fc18afc7..646348914d 100644 --- a/ui/desktop/package.json +++ b/ui/desktop/package.json @@ -1,7 +1,7 @@ { "name": "goose-app", "productName": "Goose", - "version": "1.34.0", + "version": "1.34.1", "description": "Goose App", "engines": { "node": "^24.10.0",