You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@maka.apache.org by as...@apache.org on 2026/09/01 14:19:32 UTC
(maka) 02/09: refactor(core): drop the unread ModelMetadata.docsUrl
This is an automated email from the ASF dual-hosted git repository.
Astro-Han pushed a commit to branch ci/4398-model-metadata-drift-check
in repository https://gitbox.apache.org/repos/asf/maka.git
commit 5488f7c4096b85471c37d87efd1109419ac16117
Author: AstroHan <le...@outlook.com>
AuthorDate: Tue Sep 1 18:16:37 2026 +0800
refactor(core): drop the unread ModelMetadata.docsUrl
Nothing in packages or apps ever read `docsUrl`. It was a per-model copy
of the provider's `doc` field, which the generated provider facts already
carry once per provider, so every model row paid for a duplicate no
renderer asked for.
The snapshot stores the projected shape rather than the upstream bytes,
so the field cannot leave the type without leaving the snapshot in the
same change: 1871 keys removed and the projection digest recomputed. That
is a shape migration of a generated artifact, the same kind its own
`origin.kind` already records. A refresh run against today's upstream
produces exactly this shape, and `check:model-metadata` re-derives the
digest, so the migrated file is not taken on trust.
The snapshot's content vintage is unchanged; only the field is gone.
Generated-by: Claude Code
---
packages/core/src/__tests__/model-metadata.test.ts | 1 -
packages/core/src/model-metadata.ts | 8 -
.../model-metadata/models-dev-api.snapshot.json | 1873 +-------------------
scripts/sync-model-metadata.mjs | 1 -
4 files changed, 1 insertion(+), 1882 deletions(-)
diff --git a/packages/core/src/__tests__/model-metadata.test.ts b/packages/core/src/__tests__/model-metadata.test.ts
index 8f9e01cfe0..2696510d85 100644
--- a/packages/core/src/__tests__/model-metadata.test.ts
+++ b/packages/core/src/__tests__/model-metadata.test.ts
@@ -138,7 +138,6 @@ describe('deepseek v4 flash vision exp metadata regression', () => {
metadata.description,
'Experimental DeepSeek V4 Flash model for image understanding and multimodal agent tasks',
);
- assert.equal(metadata.docsUrl, 'https://api-docs.deepseek.com/guides/vision/');
assert.equal(metadata.contextWindow, 1_000_000);
assert.equal(metadata.maxOutputTokens, 384_000);
assert.equal(metadata.structuredOutput, true);
diff --git a/packages/core/src/model-metadata.ts b/packages/core/src/model-metadata.ts
index 4c8268be63..81366ad80f 100644
--- a/packages/core/src/model-metadata.ts
+++ b/packages/core/src/model-metadata.ts
@@ -28,7 +28,6 @@ export interface ModelMetadata {
displayName?: string;
description?: string;
lifecycle?: 'active' | 'beta' | 'alpha' | 'deprecated' | 'retired';
- docsUrl?: string;
contextWindow?: number;
inputLimit?: number;
maxOutputTokens?: number;
@@ -242,8 +241,6 @@ const SILICONFLOW_MODEL_OVERRIDES: Record<string, ModelMetadata> = Object.fromEn
.map(([id]) => [id, { capabilities: { chat: true } }]),
);
-const VOLCENGINE_CODING_PLAN_DOCS = 'https://www.volcengine.com/docs/82379/1925114';
-const VOLCENGINE_AGENT_PLAN_DOCS = 'https://www.volcengine.com/docs/82379/2366394';
const VOLCENGINE_CODING_PLAN_MODEL_METADATA: Record<string, ModelMetadata> = {
'ark-code-latest': planModel('Ark Code Latest', false),
'doubao-seed-2.0-code': planModel('Doubao Seed 2.0 Code', true),
@@ -351,7 +348,6 @@ const STATIC_MODEL_METADATA: Partial<Record<ProviderType, Record<string, ModelMe
'doubao-seed-2-0-pro-260215': {
displayName: 'Doubao Seed 2.0 Pro',
lifecycle: 'active',
- docsUrl: 'https://www.volcengine.com/docs/82379',
capabilities: { reasoning: true, functionCalling: true },
thinkingOptions: {
efforts: ['minimal', 'low', 'medium', 'high'],
@@ -413,7 +409,6 @@ const STATIC_MODEL_METADATA: Partial<Record<ProviderType, Record<string, ModelMe
displayName: 'DeepSeek-V4-Flash-Vision-Exp',
description:
'Experimental DeepSeek V4 Flash model for image understanding and multimodal agent tasks',
- docsUrl: 'https://api-docs.deepseek.com/guides/vision/',
contextWindow: 1_000_000,
maxOutputTokens: 384_000,
structuredOutput: true,
@@ -443,7 +438,6 @@ function planModel(
return {
displayName,
lifecycle: 'active',
- docsUrl: VOLCENGINE_CODING_PLAN_DOCS,
...(contextWindow === undefined ? {} : { contextWindow }),
...(maxOutputTokens === undefined ? {} : { maxOutputTokens }),
capabilities: { ...REASONING_FUNCTION_CALLING, vision },
@@ -462,7 +456,6 @@ function agentPlanModel(
return {
displayName,
lifecycle: options.lifecycle ?? 'active',
- docsUrl: VOLCENGINE_AGENT_PLAN_DOCS,
contextWindow,
maxOutputTokens,
capabilities: {
@@ -483,7 +476,6 @@ function displayMetadataOnly(
displayName: metadata.displayName,
...(metadata.description !== undefined ? { description: metadata.description } : {}),
lifecycle: metadata.lifecycle,
- docsUrl: metadata.docsUrl,
...(metadata.knowledgeCutoff !== undefined
? { knowledgeCutoff: metadata.knowledgeCutoff }
: {}),
diff --git a/scripts/model-metadata/models-dev-api.snapshot.json b/scripts/model-metadata/models-dev-api.snapshot.json
index 34667f1fcc..9f81accaa3 100644
--- a/scripts/model-metadata/models-dev-api.snapshot.json
+++ b/scripts/model-metadata/models-dev-api.snapshot.json
@@ -5,7 +5,7 @@
"kind": "generated-output-migration",
"commit": "729839ed8ada3e5498b0ad27e64fb42dfd283ae7"
},
- "projectionSha256": "6957e4d11c649fa77dc33474bd67390a28d290c994f34dabac23f539b5f59149",
+ "projectionSha256": "ed57286d0b96112574c227b5a327bfa5bbd572233b0bf2a27fe41e00d511beee",
"projection": {
"metadata": {
"anthropic": {
@@ -13,7 +13,6 @@
"displayName": "Claude Fable 5",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -35,7 +34,6 @@
"displayName": "Claude Haiku 4.5 (latest)",
"description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 200000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-02-28",
@@ -55,7 +53,6 @@
"displayName": "Claude Haiku 4.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 200000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-02-28",
@@ -75,7 +72,6 @@
"displayName": "Claude Opus 4.5 (latest)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 200000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-05",
@@ -98,7 +94,6 @@
"displayName": "Claude Opus 4.5",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 200000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-05",
@@ -121,7 +116,6 @@
"displayName": "Claude Opus 4.6",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-05-31",
@@ -144,7 +138,6 @@
"displayName": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -167,7 +160,6 @@
"displayName": "Claude Opus 4.8",
"description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01",
@@ -190,7 +182,6 @@
"displayName": "Claude Opus 5",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-05",
@@ -213,7 +204,6 @@
"displayName": "Claude Sonnet 4.5 (latest)",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-07-31",
@@ -233,7 +223,6 @@
"displayName": "Claude Sonnet 4.5",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-07-31",
@@ -253,7 +242,6 @@
"displayName": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-08-31",
@@ -276,7 +264,6 @@
"displayName": "Claude Sonnet 5",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"lifecycle": "active",
- "docsUrl": "https://docs.anthropic.com/en/docs/about-claude/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -302,7 +289,6 @@
"displayName": "DeepSeek V4 Flash 0731",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -326,7 +312,6 @@
"displayName": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -348,7 +333,6 @@
"displayName": "QVQ Max",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -367,7 +351,6 @@
"displayName": "Qwen Flash",
"description": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -389,7 +372,6 @@
"displayName": "Qwen Max",
"description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -408,7 +390,6 @@
"displayName": "Qwen-MT Plus",
"description": "Translation model for multilingual conversion, localization, and cross-language workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 16384,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -427,7 +408,6 @@
"displayName": "Qwen-MT Turbo",
"description": "Translation model for multilingual conversion, localization, and cross-language workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 16384,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -446,7 +426,6 @@
"displayName": "Qwen-Omni Turbo",
"description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 2048,
"knowledgeCutoff": "2024-04",
@@ -465,7 +444,6 @@
"displayName": "Qwen-Omni Turbo Realtime",
"description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 2048,
"knowledgeCutoff": "2024-04",
@@ -484,7 +462,6 @@
"displayName": "Qwen Plus",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -506,7 +483,6 @@
"displayName": "Qwen Plus Character (Japanese)",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 8192,
"maxOutputTokens": 512,
"knowledgeCutoff": "2024-04",
@@ -525,7 +501,6 @@
"displayName": "Qwen Turbo",
"description": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-04",
@@ -547,7 +522,6 @@
"displayName": "Qwen-VL Max",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -566,7 +540,6 @@
"displayName": "Qwen-VL OCR",
"description": "OCR model for extracting structured text from documents and screenshots",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 34096,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-04",
@@ -585,7 +558,6 @@
"displayName": "Qwen-VL Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -604,7 +576,6 @@
"displayName": "Qwen2.5 14B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -623,7 +594,6 @@
"displayName": "Qwen2.5 32B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -642,7 +612,6 @@
"displayName": "Qwen2.5 72B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -661,7 +630,6 @@
"displayName": "Qwen2.5 7B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -680,7 +648,6 @@
"displayName": "Qwen2.5-Omni 7B",
"description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 2048,
"knowledgeCutoff": "2024-04",
@@ -699,7 +666,6 @@
"displayName": "Qwen2.5-VL 72B Instruct",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -718,7 +684,6 @@
"displayName": "Qwen2.5-VL 7B Instruct",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -737,7 +702,6 @@
"displayName": "Qwen3 14B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2025-04",
@@ -759,7 +723,6 @@
"displayName": "Qwen3 235B-A22B",
"description": "Large open Qwen MoE for multilingual reasoning, coding, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -781,7 +744,6 @@
"displayName": "Qwen3 32B",
"description": "Dense open Qwen model for self-hosted chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -803,7 +765,6 @@
"displayName": "Qwen3 8B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2025-04",
@@ -825,7 +786,6 @@
"displayName": "Qwen3-ASR Flash",
"description": "Speech transcription model for accurate audio-to-text and captioning workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 53248,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-04",
@@ -844,7 +804,6 @@
"displayName": "Qwen3-Coder 30B-A3B Instruct",
"description": "Smaller Qwen coder for efficient local agents and repo-level fixes",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -863,7 +822,6 @@
"displayName": "Qwen3-Coder 480B-A35B Instruct",
"description": "Open Qwen coding heavyweight for repository reasoning and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -882,7 +840,6 @@
"displayName": "Qwen3 Coder Flash",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -901,7 +858,6 @@
"displayName": "Qwen3 Coder Plus",
"description": "Hosted Qwen coder for software agents, repo edits, and long-context code",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -920,7 +876,6 @@
"displayName": "Qwen3-LiveTranslate Flash Realtime",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 53248,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-04",
@@ -939,7 +894,6 @@
"displayName": "Qwen3 Max",
"description": "Flagship Qwen3 model for coding agents, complex reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -958,7 +912,6 @@
"displayName": "Qwen3-Next 80B-A3B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -977,7 +930,6 @@
"displayName": "Qwen3-Next 80B-A3B (Thinking)",
"description": "Efficient Qwen thinking model for local reasoning, math, and coding agents",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -996,7 +948,6 @@
"displayName": "Qwen3-Omni Flash",
"description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 65536,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-04",
@@ -1018,7 +969,6 @@
"displayName": "Qwen3-Omni Flash Realtime",
"description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 65536,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-04",
@@ -1037,7 +987,6 @@
"displayName": "Qwen3-VL 235B-A22B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -1056,7 +1005,6 @@
"displayName": "Qwen3-VL 30B-A3B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -1075,7 +1023,6 @@
"displayName": "Qwen3-VL Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -1097,7 +1044,6 @@
"displayName": "Qwen3.5 122B-A10B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -1119,7 +1065,6 @@
"displayName": "Qwen3.5 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -1141,7 +1086,6 @@
"displayName": "Qwen3.5 35B-A3B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -1163,7 +1107,6 @@
"displayName": "Qwen3.5 397B-A17B",
"description": "Large open Qwen multimodal MoE for visual agents and long technical tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -1185,7 +1128,6 @@
"displayName": "Qwen3.5 Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -1207,7 +1149,6 @@
"displayName": "Qwen3.6 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -1229,7 +1170,6 @@
"displayName": "Qwen3.6 35B-A3B",
"description": "Open multimodal Qwen MoE for local agents that need vision, audio, and code",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -1251,7 +1191,6 @@
"displayName": "Qwen3.6 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -1273,7 +1212,6 @@
"displayName": "Qwen3.6 Max Preview",
"description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -1295,7 +1233,6 @@
"displayName": "Qwen3.6 Plus",
"description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -1317,7 +1254,6 @@
"displayName": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"lastUpdated": "2026-05-21",
@@ -1338,7 +1274,6 @@
"displayName": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -1360,7 +1295,6 @@
"displayName": "Qwen3.8 Max",
"description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -1383,7 +1317,6 @@
"displayName": "QwQ Plus",
"description": "Qwen reasoning model for deliberate problem solving, math, and coding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -1404,7 +1337,6 @@
"displayName": "DeepSeek R1",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"lastUpdated": "2025-01-01",
@@ -1422,7 +1354,6 @@
"displayName": "DeepSeek R1 0528",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"lastUpdated": "2025-05-28",
@@ -1440,7 +1371,6 @@
"displayName": "DeepSeek R1 Distill Llama 70B",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 16384,
"lastUpdated": "2025-01-01",
@@ -1458,7 +1388,6 @@
"displayName": "DeepSeek R1 Distill Llama 8B",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 16384,
"lastUpdated": "2025-01-01",
@@ -1476,7 +1405,6 @@
"displayName": "DeepSeek R1 Distill Qwen 1.5B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 16384,
"lastUpdated": "2025-01-01",
@@ -1494,7 +1422,6 @@
"displayName": "DeepSeek R1 Distill Qwen 14B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 16384,
"lastUpdated": "2025-01-01",
@@ -1512,7 +1439,6 @@
"displayName": "DeepSeek R1 Distill Qwen 32B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 16384,
"lastUpdated": "2025-01-01",
@@ -1530,7 +1456,6 @@
"displayName": "DeepSeek R1 Distill Qwen 7B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 16384,
"lastUpdated": "2025-01-01",
@@ -1548,7 +1473,6 @@
"displayName": "DeepSeek V3",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 65536,
"maxOutputTokens": 8192,
"lastUpdated": "2024-12-01",
@@ -1566,7 +1490,6 @@
"displayName": "DeepSeek V3.1",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"lastUpdated": "2025-01-01",
@@ -1584,7 +1507,6 @@
"displayName": "DeepSeek V3.2 Exp",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"lastUpdated": "2025-01-01",
@@ -1602,7 +1524,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -1626,7 +1547,6 @@
"displayName": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -1650,7 +1570,6 @@
"displayName": "GLM-5",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"lastUpdated": "2026-02-11",
@@ -1671,7 +1590,6 @@
"displayName": "GLM-5.1",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 202752,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -1693,7 +1611,6 @@
"displayName": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -1712,7 +1629,6 @@
"displayName": "Moonshot Kimi K2 Thinking",
"description": "Kimi reasoning model for long-horizon research, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -1731,7 +1647,6 @@
"displayName": "Moonshot Kimi K2.5",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -1754,7 +1669,6 @@
"displayName": "Moonshot Kimi K2.6",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-01",
@@ -1777,7 +1691,6 @@
"displayName": "kimi/kimi-k2.5",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -1800,7 +1713,6 @@
"displayName": "MiniMax-M2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-02-12",
@@ -1818,7 +1730,6 @@
"displayName": "MiniMax-M2.7",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-03-18",
@@ -1836,7 +1747,6 @@
"displayName": "Moonshot Kimi K2 Instruct",
"description": "Kimi model for long-context chat, coding, and agentic reasoning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"structuredOutput": false,
@@ -1855,7 +1765,6 @@
"displayName": "QVQ Max",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -1874,7 +1783,6 @@
"displayName": "Qwen Deep Research",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -1893,7 +1801,6 @@
"displayName": "Qwen Doc Turbo",
"description": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -1912,7 +1819,6 @@
"displayName": "Qwen Flash",
"description": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -1934,7 +1840,6 @@
"displayName": "Qwen Long",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 10000000,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -1953,7 +1858,6 @@
"displayName": "Qwen Math Plus",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 4096,
"maxOutputTokens": 3072,
"knowledgeCutoff": "2024-04",
@@ -1972,7 +1876,6 @@
"displayName": "Qwen Math Turbo",
"description": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 4096,
"maxOutputTokens": 3072,
"knowledgeCutoff": "2024-04",
@@ -1991,7 +1894,6 @@
"displayName": "Qwen Max",
"description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2010,7 +1912,6 @@
"displayName": "Qwen-MT Plus",
"description": "Translation model for multilingual conversion, localization, and cross-language workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 16384,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2029,7 +1930,6 @@
"displayName": "Qwen-MT Turbo",
"description": "Translation model for multilingual conversion, localization, and cross-language workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 16384,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2048,7 +1948,6 @@
"displayName": "Qwen-Omni Turbo",
"description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 2048,
"knowledgeCutoff": "2024-04",
@@ -2067,7 +1966,6 @@
"displayName": "Qwen-Omni Turbo Realtime",
"description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 2048,
"knowledgeCutoff": "2024-04",
@@ -2086,7 +1984,6 @@
"displayName": "Qwen Plus",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -2108,7 +2005,6 @@
"displayName": "Qwen Plus Character",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-04",
@@ -2127,7 +2023,6 @@
"displayName": "Qwen Turbo",
"description": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-04",
@@ -2149,7 +2044,6 @@
"displayName": "Qwen-VL Max",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2168,7 +2062,6 @@
"displayName": "Qwen-VL OCR",
"description": "OCR model for extracting structured text from documents and screenshots",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 34096,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-04",
@@ -2187,7 +2080,6 @@
"displayName": "Qwen-VL Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2206,7 +2098,6 @@
"displayName": "Qwen2.5 14B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2225,7 +2116,6 @@
"displayName": "Qwen2.5 32B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2244,7 +2134,6 @@
"displayName": "Qwen2.5 72B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2263,7 +2152,6 @@
"displayName": "Qwen2.5 7B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2282,7 +2170,6 @@
"displayName": "Qwen2.5-Coder 32B Instruct",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2301,7 +2188,6 @@
"displayName": "Qwen2.5-Coder 7B Instruct",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2320,7 +2206,6 @@
"displayName": "Qwen2.5-Math 72B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 4096,
"maxOutputTokens": 3072,
"knowledgeCutoff": "2024-04",
@@ -2339,7 +2224,6 @@
"displayName": "Qwen2.5-Math 7B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 4096,
"maxOutputTokens": 3072,
"knowledgeCutoff": "2024-04",
@@ -2358,7 +2242,6 @@
"displayName": "Qwen2.5-Omni 7B",
"description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 32768,
"maxOutputTokens": 2048,
"knowledgeCutoff": "2024-04",
@@ -2377,7 +2260,6 @@
"displayName": "Qwen2.5-VL 72B Instruct",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2396,7 +2278,6 @@
"displayName": "Qwen2.5-VL 7B Instruct",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2415,7 +2296,6 @@
"displayName": "Qwen3 14B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2025-04",
@@ -2437,7 +2317,6 @@
"displayName": "Qwen3 235B-A22B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -2459,7 +2338,6 @@
"displayName": "Qwen3 32B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -2481,7 +2359,6 @@
"displayName": "Qwen3 8B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2025-04",
@@ -2503,7 +2380,6 @@
"displayName": "Qwen3-ASR Flash",
"description": "Speech transcription model for accurate audio-to-text and captioning workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 53248,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-04",
@@ -2522,7 +2398,6 @@
"displayName": "Qwen3-Coder 30B-A3B Instruct",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -2541,7 +2416,6 @@
"displayName": "Qwen3-Coder 480B-A35B Instruct",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -2560,7 +2434,6 @@
"displayName": "Qwen3 Coder Flash",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -2579,7 +2452,6 @@
"displayName": "Qwen3 Coder Plus",
"description": "Hosted Qwen coder for software agents, repo edits, and long-context code",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -2598,7 +2470,6 @@
"displayName": "Qwen3 Max",
"description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -2617,7 +2488,6 @@
"displayName": "Qwen3-Next 80B-A3B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -2636,7 +2506,6 @@
"displayName": "Qwen3-Next 80B-A3B (Thinking)",
"description": "Qwen reasoning model for deliberate problem solving, math, and coding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -2655,7 +2524,6 @@
"displayName": "Qwen3-Omni Flash",
"description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 65536,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-04",
@@ -2677,7 +2545,6 @@
"displayName": "Qwen3-Omni Flash Realtime",
"description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 65536,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-04",
@@ -2696,7 +2563,6 @@
"displayName": "Qwen3-VL 235B-A22B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -2715,7 +2581,6 @@
"displayName": "Qwen3-VL 30B-A3B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -2734,7 +2599,6 @@
"displayName": "Qwen3-VL Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -2756,7 +2620,6 @@
"displayName": "Qwen3.5 397B-A17B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -2778,7 +2641,6 @@
"displayName": "Qwen3.5 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -2801,7 +2663,6 @@
"displayName": "Qwen3.5 Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -2823,7 +2684,6 @@
"displayName": "Qwen3.6 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -2845,7 +2705,6 @@
"displayName": "Qwen3.6 Max Preview",
"description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 245800,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -2867,7 +2726,6 @@
"displayName": "Qwen3.6 Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -2889,7 +2747,6 @@
"displayName": "Qwen3.7 Flash",
"description": "Lightweight multimodal Qwen model for high-throughput text, image, and video tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"inputLimit": 991000,
"maxOutputTokens": 65536,
@@ -2912,7 +2769,6 @@
"displayName": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"lastUpdated": "2026-05-21",
@@ -2933,7 +2789,6 @@
"displayName": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-04",
@@ -2955,7 +2810,6 @@
"displayName": "Qwen3.8 Max",
"description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -2978,7 +2832,6 @@
"displayName": "QwQ 32B",
"description": "Qwen reasoning model for deliberate problem solving, math, and coding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -2997,7 +2850,6 @@
"displayName": "QwQ Plus",
"description": "Qwen reasoning model for deliberate problem solving, math, and coding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04",
@@ -3016,7 +2868,6 @@
"displayName": "siliconflow/deepseek-r1-0528",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 163840,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -3035,7 +2886,6 @@
"displayName": "siliconflow/deepseek-v3-0324",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 163840,
"maxOutputTokens": 163840,
"structuredOutput": true,
@@ -3054,7 +2904,6 @@
"displayName": "siliconflow/deepseek-v3.1-terminus",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 163840,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -3076,7 +2925,6 @@
"displayName": "siliconflow/deepseek-v3.2",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 163840,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -3098,7 +2946,6 @@
"displayName": "Tongyi Intent Detect V3",
"description": "General-purpose chat model for instruction following, writing, and analysis",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/models",
"contextWindow": 8192,
"maxOutputTokens": 1024,
"knowledgeCutoff": "2024-04",
@@ -3119,7 +2966,6 @@
"displayName": "GLM-4.7",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -3142,7 +2988,6 @@
"displayName": "GLM-5",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"lastUpdated": "2026-02-11",
@@ -3164,7 +3009,6 @@
"displayName": "Kimi K2.5",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -3187,7 +3031,6 @@
"displayName": "MiniMax-M2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 196608,
"maxOutputTokens": 24576,
"lastUpdated": "2026-02-12",
@@ -3206,7 +3049,6 @@
"displayName": "Qwen3 Coder Next",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -3226,7 +3068,6 @@
"displayName": "Qwen3 Coder Plus",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -3246,7 +3087,6 @@
"displayName": "Qwen3 Max",
"description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -3266,7 +3106,6 @@
"displayName": "Qwen3.5 Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -3289,7 +3128,6 @@
"displayName": "Qwen3.6 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -3311,7 +3149,6 @@
"displayName": "Qwen3.6 Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -3334,7 +3171,6 @@
"displayName": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"lastUpdated": "2026-05-21",
@@ -3355,7 +3191,6 @@
"displayName": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"lifecycle": "active",
- "docsUrl": "https://help.aliyun.com/zh/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-04",
@@ -3380,7 +3215,6 @@
"displayName": "GLM-4.7",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -3403,7 +3237,6 @@
"displayName": "GLM-5",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"lastUpdated": "2026-02-11",
@@ -3425,7 +3258,6 @@
"displayName": "Kimi K2.5",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -3448,7 +3280,6 @@
"displayName": "MiniMax-M2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 196608,
"inputLimit": 196601,
"maxOutputTokens": 24576,
@@ -3468,7 +3299,6 @@
"displayName": "Qwen3 Coder Next",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -3488,7 +3318,6 @@
"displayName": "Qwen3 Coder Plus",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -3508,7 +3337,6 @@
"displayName": "Qwen3 Max",
"description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -3528,7 +3356,6 @@
"displayName": "Qwen3.5 Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -3551,7 +3378,6 @@
"displayName": "Qwen3.6 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -3573,7 +3399,6 @@
"displayName": "Qwen3.6 Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -3596,7 +3421,6 @@
"displayName": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"lastUpdated": "2026-05-21",
@@ -3617,7 +3441,6 @@
"displayName": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-04",
@@ -3642,7 +3465,6 @@
"displayName": "DeepSeek V3.2",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -3666,7 +3488,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -3691,7 +3512,6 @@
"displayName": "DeepSeek V4 Flash 0731",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -3716,7 +3536,6 @@
"displayName": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -3741,7 +3560,6 @@
"displayName": "DeepSeek V4 Pro 0813",
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"structuredOutput": true,
@@ -3765,7 +3583,6 @@
"displayName": "GLM-5",
"description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -3788,7 +3605,6 @@
"displayName": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 202752,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -3811,7 +3627,6 @@
"displayName": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -3834,7 +3649,6 @@
"displayName": "HappyHorse 1.1 Image-to-Video",
"description": "Video model for image-to-video generation",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 0,
"maxOutputTokens": 0,
"lastUpdated": "2026-07-17",
@@ -3853,7 +3667,6 @@
"displayName": "HappyHorse 1.1 Reference-to-Video",
"description": "Video model for reference-guided video generation",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 0,
"maxOutputTokens": 0,
"lastUpdated": "2026-07-17",
@@ -3872,7 +3685,6 @@
"displayName": "HappyHorse 1.1 Text-to-Video",
"description": "Video model for prompt-driven text-to-video generation",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 0,
"maxOutputTokens": 0,
"lastUpdated": "2026-07-17",
@@ -3891,7 +3703,6 @@
"displayName": "Kimi K2.5",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 262144,
"maxOutputTokens": 98304,
"knowledgeCutoff": "2025-01",
@@ -3915,7 +3726,6 @@
"displayName": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -3939,7 +3749,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -3963,7 +3772,6 @@
"displayName": "MiniMax-M2.5",
"description": "Prior MiniMax coding model for agent workflows, office edits, and automation",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 196608,
"inputLimit": 196601,
"maxOutputTokens": 32768,
@@ -3983,7 +3791,6 @@
"displayName": "Qwen Image 2.0",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 8192,
"maxOutputTokens": 0,
"lastUpdated": "2026-03-03",
@@ -4002,7 +3809,6 @@
"displayName": "Qwen Image 2.0 Pro",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 8192,
"maxOutputTokens": 0,
"lastUpdated": "2026-03-03",
@@ -4021,7 +3827,6 @@
"displayName": "Qwen3.6 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -4044,7 +3849,6 @@
"displayName": "Qwen3.6 Plus",
"description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -4068,7 +3872,6 @@
"displayName": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -4091,7 +3894,6 @@
"displayName": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -4115,7 +3917,6 @@
"displayName": "Qwen3.8 Max",
"description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -4139,7 +3940,6 @@
"displayName": "Qwen3.8 Max Preview",
"description": "Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows",
"lifecycle": "beta",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -4162,7 +3962,6 @@
"displayName": "Wan2.7 Image",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 8192,
"maxOutputTokens": 0,
"lastUpdated": "2026-05-29",
@@ -4181,7 +3980,6 @@
"displayName": "Wan2.7 Image Pro",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"contextWindow": 8192,
"maxOutputTokens": 0,
"lastUpdated": "2026-05-29",
@@ -4202,7 +4000,6 @@
"displayName": "DeepSeek V3.2",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -4226,7 +4023,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -4251,7 +4047,6 @@
"displayName": "DeepSeek V4 Flash 0731",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -4276,7 +4071,6 @@
"displayName": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -4301,7 +4095,6 @@
"displayName": "DeepSeek V4 Pro 0813",
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"structuredOutput": true,
@@ -4325,7 +4118,6 @@
"displayName": "GLM-5",
"description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -4348,7 +4140,6 @@
"displayName": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 202752,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -4371,7 +4162,6 @@
"displayName": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -4394,7 +4184,6 @@
"displayName": "HappyHorse 1.1 Image-to-Video",
"description": "Video model for image-to-video generation",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 0,
"maxOutputTokens": 0,
"lastUpdated": "2026-07-17",
@@ -4413,7 +4202,6 @@
"displayName": "HappyHorse 1.1 Reference-to-Video",
"description": "Video model for reference-guided video generation",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 0,
"maxOutputTokens": 0,
"lastUpdated": "2026-07-17",
@@ -4432,7 +4220,6 @@
"displayName": "HappyHorse 1.1 Text-to-Video",
"description": "Video model for prompt-driven text-to-video generation",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 0,
"maxOutputTokens": 0,
"lastUpdated": "2026-07-17",
@@ -4451,7 +4238,6 @@
"displayName": "Kimi K2.5",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 262144,
"maxOutputTokens": 98304,
"knowledgeCutoff": "2025-01",
@@ -4475,7 +4261,6 @@
"displayName": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -4499,7 +4284,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -4523,7 +4307,6 @@
"displayName": "MiniMax-M2.5",
"description": "Prior MiniMax coding model for agent workflows, office edits, and automation",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 196608,
"inputLimit": 196601,
"maxOutputTokens": 32768,
@@ -4543,7 +4326,6 @@
"displayName": "Qwen Image 2.0",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 8192,
"maxOutputTokens": 0,
"lastUpdated": "2026-03-03",
@@ -4562,7 +4344,6 @@
"displayName": "Qwen Image 2.0 Pro",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 8192,
"maxOutputTokens": 0,
"lastUpdated": "2026-03-03",
@@ -4581,7 +4362,6 @@
"displayName": "Qwen3.6 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -4604,7 +4384,6 @@
"displayName": "Qwen3.6 Plus",
"description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -4628,7 +4407,6 @@
"displayName": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -4651,7 +4429,6 @@
"displayName": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -4675,7 +4452,6 @@
"displayName": "Qwen3.8 Max",
"description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -4699,7 +4475,6 @@
"displayName": "Qwen3.8 Max Preview",
"description": "Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows",
"lifecycle": "beta",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -4722,7 +4497,6 @@
"displayName": "Wan2.7 Image",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 8192,
"maxOutputTokens": 0,
"lastUpdated": "2026-05-29",
@@ -4741,7 +4515,6 @@
"displayName": "Wan2.7 Image Pro",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
"contextWindow": 8192,
"maxOutputTokens": 0,
"lastUpdated": "2026-05-29",
@@ -4762,7 +4535,6 @@
"displayName": "Gemma 4 31B IT",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"lifecycle": "beta",
- "docsUrl": "https://inference-docs.cerebras.ai/models/overview",
"contextWindow": 131072,
"maxOutputTokens": 40960,
"structuredOutput": true,
@@ -4784,7 +4556,6 @@
"displayName": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"lifecycle": "active",
- "docsUrl": "https://inference-docs.cerebras.ai/models/overview",
"contextWindow": 131072,
"maxOutputTokens": 40960,
"structuredOutput": true,
@@ -4808,7 +4579,6 @@
"displayName": "Aya Expanse 32B",
"description": "Open multilingual model optimized for generation across 23 languages",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 4000,
"lastUpdated": "2024-10-24",
@@ -4826,7 +4596,6 @@
"displayName": "Aya Expanse 8B",
"description": "Compact open multilingual model optimized for generation across 23 languages",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 8000,
"maxOutputTokens": 4000,
"lastUpdated": "2024-10-24",
@@ -4844,7 +4613,6 @@
"displayName": "Aya Vision 32B",
"description": "Open multilingual vision model for OCR, visual reasoning, and image question answering",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 16000,
"maxOutputTokens": 4000,
"lastUpdated": "2025-05-14",
@@ -4862,7 +4630,6 @@
"displayName": "Aya Vision 8B",
"description": "Compact open multilingual vision model for OCR and visual question answering",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 16000,
"maxOutputTokens": 4000,
"lastUpdated": "2025-05-14",
@@ -4880,7 +4647,6 @@
"displayName": "Command A",
"description": "Cohere command model for multilingual enterprise agents, tools, and chat",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 256000,
"maxOutputTokens": 8000,
"knowledgeCutoff": "2024-06-01",
@@ -4899,7 +4665,6 @@
"displayName": "Command A Plus",
"description": "Cohere's stronger command model for multilingual agents and enterprise workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-04-01",
@@ -4922,7 +4687,6 @@
"displayName": "Command A Reasoning",
"description": "Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 256000,
"maxOutputTokens": 32000,
"knowledgeCutoff": "2024-06-01",
@@ -4944,7 +4708,6 @@
"displayName": "Command A Translate",
"description": "Translation model for multilingual conversion, localization, and cross-language workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 8000,
"maxOutputTokens": 8000,
"knowledgeCutoff": "2024-06-01",
@@ -4963,7 +4726,6 @@
"displayName": "Command A Vision",
"description": "Cohere vision model for multilingual document analysis, OCR, and image understanding",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 8000,
"knowledgeCutoff": "2024-06-01",
@@ -4982,7 +4744,6 @@
"displayName": "Command R",
"description": "Cohere retrieval model for long-context chat and enterprise RAG workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 4000,
"knowledgeCutoff": "2024-06-01",
@@ -5001,7 +4762,6 @@
"displayName": "Command R+",
"description": "Cohere's RAG workhorse for long-context enterprise search and tool use",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 4000,
"knowledgeCutoff": "2024-06-01",
@@ -5020,7 +4780,6 @@
"displayName": "Command R7B",
"description": "Cohere retrieval model for long-context chat and enterprise RAG workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 4000,
"knowledgeCutoff": "2024-06-01",
@@ -5039,7 +4798,6 @@
"displayName": "Command R7B Arabic",
"description": "Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 4000,
"knowledgeCutoff": "2024-06-01",
@@ -5058,7 +4816,6 @@
"displayName": "North Mini Code",
"description": "Cohere coding model for practical software engineering and agentic edits",
"lifecycle": "active",
- "docsUrl": "https://docs.cohere.com/docs/models",
"contextWindow": 256000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-09-23",
@@ -5084,7 +4841,6 @@
"displayName": "Gemma Sea Lion V4 27B It",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"structuredOutput": false,
@@ -5103,7 +4859,6 @@
"displayName": "Deepseek R1 Distill Qwen 32B",
"description": "Classic open reasoning model for transparent math, coding, and deliberate problem solving",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 80000,
"maxOutputTokens": 80000,
"knowledgeCutoff": "2024-07",
@@ -5123,7 +4878,6 @@
"displayName": "DeepSeek V4 Flash 0731",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 1310720,
"maxOutputTokens": 1048576,
"knowledgeCutoff": "2025-05",
@@ -5147,7 +4901,6 @@
"displayName": "DeepSeek V4 Pro 0813",
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 1048576,
"maxOutputTokens": 1048576,
"structuredOutput": true,
@@ -5170,7 +4923,6 @@
"displayName": "Gemma 4 26B A4B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 256000,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -5193,7 +4945,6 @@
"displayName": "Granite 4.0 H Micro",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 131000,
"maxOutputTokens": 131000,
"structuredOutput": false,
@@ -5212,7 +4963,6 @@
"displayName": "Llama 3.1 8B Instruct fp8",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 32000,
"maxOutputTokens": 32000,
"knowledgeCutoff": "2023-12",
@@ -5232,7 +4982,6 @@
"displayName": "Llama 3.2 11B Vision Instruct",
"description": "Open Llama multimodal model for image understanding and text reasoning",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2023-12",
@@ -5252,7 +5001,6 @@
"displayName": "Llama 3.2 1B Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 60000,
"maxOutputTokens": 60000,
"knowledgeCutoff": "2023-12",
@@ -5272,7 +5020,6 @@
"displayName": "Llama 3.2 3B Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 80000,
"maxOutputTokens": 80000,
"knowledgeCutoff": "2023-12",
@@ -5292,7 +5039,6 @@
"displayName": "Llama 3.3 70B Instruct fp8 Fast",
"description": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 24000,
"maxOutputTokens": 24000,
"knowledgeCutoff": "2023-12",
@@ -5312,7 +5058,6 @@
"displayName": "Llama 4 Scout 17B 16E Instruct",
"description": "Open Llama with long-context vision for efficient multimodal agents",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 131000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-08",
@@ -5332,7 +5077,6 @@
"displayName": "Llama Guard 3 8B",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2023-12",
@@ -5352,7 +5096,6 @@
"displayName": "Mistral Small 3.1 24B Instruct",
"description": "Efficient Mistral model for fast chat, extraction, and production assistants",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"structuredOutput": false,
@@ -5371,7 +5114,6 @@
"displayName": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 262144,
"maxOutputTokens": 256000,
"knowledgeCutoff": "2025-01",
@@ -5395,7 +5137,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -5419,7 +5160,6 @@
"displayName": "Nemotron 3 Super 120B",
"description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 256000,
"maxOutputTokens": 256000,
"structuredOutput": true,
@@ -5442,7 +5182,6 @@
"displayName": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -5464,7 +5203,6 @@
"displayName": "GPT OSS 20B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -5483,7 +5221,6 @@
"displayName": "Qwen2.5 Coder 32B Instruct",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 32768,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -5502,7 +5239,6 @@
"displayName": "Qwen3 30B A3b fp8",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 32768,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -5521,7 +5257,6 @@
"displayName": "Qwen3.8 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -5544,7 +5279,6 @@
"displayName": "Qwq 32B",
"description": "Qwen reasoning model for deliberate problem solving, math, and coding",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 24000,
"maxOutputTokens": 24000,
"knowledgeCutoff": "2024-04",
@@ -5564,7 +5298,6 @@
"displayName": "GLM-4.7-Flash",
"description": "Efficient GLM model for fast reasoning, coding, and agent workflows",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -5588,7 +5321,6 @@
"displayName": "Glm 5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://developers.cloudflare.com/workers-ai/models/",
"contextWindow": 262144,
"maxOutputTokens": 256000,
"structuredOutput": true,
@@ -5613,7 +5345,6 @@
"displayName": "Seed 2.0 Code",
"description": "ByteDance Seed coding model for multimodal software engineering and long-running agents",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 256000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -5635,7 +5366,6 @@
"displayName": "Seed 2.0 Mini",
"description": "Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 256000,
"maxOutputTokens": 32000,
"structuredOutput": true,
@@ -5654,7 +5384,6 @@
"displayName": "Seed 2.0 Pro",
"description": "Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 256000,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -5673,7 +5402,6 @@
"displayName": "DeepSeek-R1-0528",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 163840,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2024-07",
@@ -5693,7 +5421,6 @@
"displayName": "DeepSeek-V3",
"description": "Open DeepSeek MoE chat model for coding, math, and general reasoning",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 163840,
"maxOutputTokens": 8192,
"structuredOutput": true,
@@ -5712,7 +5439,6 @@
"displayName": "DeepSeek V3 0324",
"description": "March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 163840,
"maxOutputTokens": 163840,
"structuredOutput": true,
@@ -5731,7 +5457,6 @@
"displayName": "DeepSeek-V3.1",
"description": "Hybrid-reasoning DeepSeek model with thinking and non-thinking modes",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 163840,
"maxOutputTokens": 8192,
"structuredOutput": true,
@@ -5753,7 +5478,6 @@
"displayName": "DeepSeek-V3.2",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 163840,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2024-12",
@@ -5776,7 +5500,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 1048576,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-05",
@@ -5800,7 +5523,6 @@
"displayName": "DeepSeek V4 Flash 0731",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 1048576,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -5823,7 +5545,6 @@
"displayName": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 1048576,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-05",
@@ -5847,7 +5568,6 @@
"displayName": "DeepSeek V4 Pro 0813",
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 1048576,
"maxOutputTokens": 384000,
"structuredOutput": true,
@@ -5870,7 +5590,6 @@
"displayName": "Gemma 4 26B A4B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -5892,7 +5611,6 @@
"displayName": "Gemma 4 31B IT",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -5914,7 +5632,6 @@
"displayName": "Gemma 4 E4B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"structuredOutput": true,
@@ -5936,7 +5653,6 @@
"displayName": "Llama 3.3 70B Turbo",
"description": "Compact Llama instruction model for fast chat and local deployment",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -5955,7 +5671,6 @@
"displayName": "Llama 4 Maverick 17B FP8",
"description": "Open multimodal Llama model for strong reasoning and fast responses",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 1048576,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -5974,7 +5689,6 @@
"displayName": "Llama 4 Scout 17B",
"description": "Open multimodal Llama model for long-context analysis and efficient agents",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 327680,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -5993,7 +5707,6 @@
"displayName": "MiniMax M2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "deprecated",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 196608,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-06",
@@ -6012,7 +5725,6 @@
"displayName": "MiniMax-M2.7",
"description": "Open MiniMax flagship for coding agents, office automation, and complex environments",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 196608,
"maxOutputTokens": 131072,
"lastUpdated": "2026-03-18",
@@ -6030,7 +5742,6 @@
"displayName": "MiniMax-M3",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 524288,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -6049,7 +5760,6 @@
"displayName": "Kimi K2.5",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -6072,7 +5782,6 @@
"displayName": "Kimi K2.6",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-04",
@@ -6095,7 +5804,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -6118,7 +5826,6 @@
"displayName": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -6140,7 +5847,6 @@
"displayName": "Llama 3.3 Nemotron Super 49B v1.5",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "deprecated",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -6159,7 +5865,6 @@
"displayName": "Nemotron 3 Nano 30B A3B",
"description": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"lastUpdated": "2025-12-15",
@@ -6180,7 +5885,6 @@
"displayName": "Nemotron 3 Nano Omni 30B A3B Reasoning",
"description": "Open Nemotron omni model combining reasoning with text, vision, and audio",
"lifecycle": "deprecated",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -6199,7 +5903,6 @@
"displayName": "GPT OSS 120B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -6221,7 +5924,6 @@
"displayName": "GPT OSS 20B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -6243,7 +5945,6 @@
"displayName": "Qwen3 235B-A22B Instruct 2507",
"description": "Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -6262,7 +5963,6 @@
"displayName": "Qwen3 30B A3B",
"description": "Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 40960,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -6281,7 +5981,6 @@
"displayName": "Qwen3 32B",
"description": "Dense open Qwen model for self-hosted chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 40960,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -6301,7 +6000,6 @@
"displayName": "Qwen3 Coder 480B A35B Instruct Turbo",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 66536,
"knowledgeCutoff": "2025-04",
@@ -6321,7 +6019,6 @@
"displayName": "Qwen3 Max",
"description": "Flagship Qwen3 model for coding agents, complex reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 256000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -6341,7 +6038,6 @@
"displayName": "Qwen3-Next 80B-A3B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -6361,7 +6057,6 @@
"displayName": "Qwen3 VL 235B A22B Instruct",
"description": "Qwen vision-language instruct model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -6381,7 +6076,6 @@
"displayName": "Qwen3.5 122B-A10B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -6400,7 +6094,6 @@
"displayName": "Qwen3.5 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -6419,7 +6112,6 @@
"displayName": "Qwen 3.5 35B A3B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 81920,
"knowledgeCutoff": "2025-01",
@@ -6439,7 +6131,6 @@
"displayName": "Qwen 3.5 397B A17B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 81920,
"knowledgeCutoff": "2025-01",
@@ -6459,7 +6150,6 @@
"displayName": "Qwen3.5 9B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -6478,7 +6168,6 @@
"displayName": "Qwen3.6 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -6497,7 +6186,6 @@
"displayName": "Qwen3.6 35B A3B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 81920,
"structuredOutput": true,
@@ -6516,7 +6204,6 @@
"displayName": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 256000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -6535,7 +6222,6 @@
"displayName": "Qwen3.8 2.4T A95B",
"description": "Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -6557,7 +6243,6 @@
"displayName": "Qwen3.8 27B",
"description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -6580,7 +6265,6 @@
"displayName": "Qwen3.8 Max",
"description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 256000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -6599,7 +6283,6 @@
"displayName": "Step 3.7 Flash",
"description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 256000,
"knowledgeCutoff": "2026-03-01",
@@ -6618,7 +6301,6 @@
"displayName": "Hy3",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 64000,
"structuredOutput": true,
@@ -6637,7 +6319,6 @@
"displayName": "Inkling",
"description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 524288,
"maxOutputTokens": 1048576,
"lastUpdated": "2026-07-15",
@@ -6655,7 +6336,6 @@
"displayName": "Inkling Small",
"description": "Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 524288,
"maxOutputTokens": 1048576,
"structuredOutput": true,
@@ -6674,7 +6354,6 @@
"displayName": "MiMo-V2.5",
"description": "Open MiMo model for multimodal coding agents and long-context automation",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-12",
@@ -6697,7 +6376,6 @@
"displayName": "MiMo-V2.5-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 1048576,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-12",
@@ -6720,7 +6398,6 @@
"displayName": "GLM-4.6",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 202752,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -6743,7 +6420,6 @@
"displayName": "GLM-4.7",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -6766,7 +6442,6 @@
"displayName": "GLM-4.7-Flash",
"description": "Efficient GLM model for fast reasoning, coding, and agent workflows",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -6786,7 +6461,6 @@
"displayName": "GLM-5",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-12",
@@ -6809,7 +6483,6 @@
"displayName": "GLM-5.1",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -6832,7 +6505,6 @@
"displayName": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://deepinfra.com/models",
"contextWindow": 1048576,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -6857,7 +6529,6 @@
"displayName": "DeepSeek Chat",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://api-docs.deepseek.com/quick_start/pricing",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-09",
@@ -6876,7 +6547,6 @@
"displayName": "DeepSeek Reasoner",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"lifecycle": "active",
- "docsUrl": "https://api-docs.deepseek.com/quick_start/pricing",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-09",
@@ -6895,7 +6565,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://api-docs.deepseek.com/quick_start/pricing",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -6919,7 +6588,6 @@
"displayName": "DeepSeek V4 Pro",
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
"lifecycle": "active",
- "docsUrl": "https://api-docs.deepseek.com/quick_start/pricing",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"structuredOutput": true,
@@ -6944,7 +6612,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -6968,7 +6635,6 @@
"displayName": "DeepSeek V4 Flash 0731",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -6992,7 +6658,6 @@
"displayName": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -7016,7 +6681,6 @@
"displayName": "DeepSeek V4 Pro 0813",
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"structuredOutput": true,
@@ -7039,7 +6703,6 @@
"displayName": "GLM 5.2",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 1048575,
"maxOutputTokens": 131072,
"lastUpdated": "2026-06-16",
@@ -7061,7 +6724,6 @@
"displayName": "GPT OSS 120B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"lastUpdated": "2026-06-16",
@@ -7082,7 +6744,6 @@
"displayName": "GPT OSS 20B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"lastUpdated": "2025-08-05",
@@ -7103,7 +6764,6 @@
"displayName": "Inkling",
"description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 1048576,
"maxOutputTokens": 1048576,
"lastUpdated": "2026-07-15",
@@ -7121,7 +6781,6 @@
"displayName": "Kimi K2.6",
"description": "Kimi reasoning model for long-horizon research, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 262000,
"maxOutputTokens": 262000,
"lastUpdated": "2026-04-17",
@@ -7142,7 +6801,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Kimi coding model for software agents, refactors, and repository reasoning",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 262000,
"maxOutputTokens": 262000,
"lastUpdated": "2026-06-16",
@@ -7163,7 +6821,6 @@
"displayName": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -7186,7 +6843,6 @@
"displayName": "MiniMax-M2.7",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 196608,
"maxOutputTokens": 196608,
"lastUpdated": "2026-04-12",
@@ -7207,7 +6863,6 @@
"displayName": "MiniMax-M3",
"description": "MiniMax multimodal coding model for long-context reasoning and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 512000,
"maxOutputTokens": 512000,
"lastUpdated": "2026-06-12",
@@ -7228,7 +6883,6 @@
"displayName": "Muse Glimmer 30B",
"description": "Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2026-01-04",
@@ -7251,7 +6905,6 @@
"displayName": "Nemotron 3 Ultra 550B A55B",
"description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 262144,
"maxOutputTokens": 128000,
"lastUpdated": "2026-06-04",
@@ -7272,7 +6925,6 @@
"displayName": "Nemotron 3.5 Lightning 30B A3B",
"description": "Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -7294,7 +6946,6 @@
"displayName": "Qwen 3.7 Plus",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"lastUpdated": "2026-06-12",
@@ -7316,7 +6967,6 @@
"displayName": "Qwen3.8 Max",
"description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"lastUpdated": "2026-08-03",
@@ -7337,7 +6987,6 @@
"displayName": "GLM 5.2 Fast",
"description": "Efficient GLM model for fast reasoning, coding, and agent workflows",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 1048575,
"maxOutputTokens": 131072,
"lastUpdated": "2026-06-26",
@@ -7359,7 +7008,6 @@
"displayName": "Kimi K2.6 Fast",
"description": "Kimi reasoning model for long-horizon research, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 262000,
"maxOutputTokens": 262000,
"lastUpdated": "2026-06-05",
@@ -7380,7 +7028,6 @@
"displayName": "Kimi K2.6 Turbo",
"description": "Kimi reasoning model for long-horizon research, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 262000,
"maxOutputTokens": 262000,
"lastUpdated": "2026-04-17",
@@ -7401,7 +7048,6 @@
"displayName": "Kimi K2.7 Code Fast",
"description": "Kimi coding model for software agents, refactors, and repository reasoning",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 262000,
"maxOutputTokens": 262000,
"lastUpdated": "2026-06-16",
@@ -7422,7 +7068,6 @@
"displayName": "Kimi K3 Fast",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"lifecycle": "active",
- "docsUrl": "https://fireworks.ai/docs/",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -7447,7 +7092,6 @@
"displayName": "Claude Fable 5",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -7469,7 +7113,6 @@
"displayName": "Claude Haiku 4.5 (latest)",
"description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 200000,
"inputLimit": 136000,
"maxOutputTokens": 64000,
@@ -7489,7 +7132,6 @@
"displayName": "Claude Opus 4.5 (latest)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 200000,
"inputLimit": 168000,
"maxOutputTokens": 32000,
@@ -7509,7 +7151,6 @@
"displayName": "Claude Opus 4.6",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 200000,
"inputLimit": 168000,
"maxOutputTokens": 32000,
@@ -7532,7 +7173,6 @@
"displayName": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 200000,
"inputLimit": 168000,
"maxOutputTokens": 32000,
@@ -7555,7 +7195,6 @@
"displayName": "Claude Opus 4.8",
"description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 200000,
"inputLimit": 168000,
"maxOutputTokens": 64000,
@@ -7578,7 +7217,6 @@
"displayName": "Claude Opus 5",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1000000,
"inputLimit": 936000,
"maxOutputTokens": 64000,
@@ -7602,7 +7240,6 @@
"displayName": "Claude Sonnet 4 (latest)",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 216000,
"inputLimit": 128000,
"maxOutputTokens": 16000,
@@ -7622,7 +7259,6 @@
"displayName": "Claude Sonnet 4.5 (latest)",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 200000,
"inputLimit": 168000,
"maxOutputTokens": 32000,
@@ -7642,7 +7278,6 @@
"displayName": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 200000,
"inputLimit": 168000,
"maxOutputTokens": 32000,
@@ -7665,7 +7300,6 @@
"displayName": "Claude Sonnet 5",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -7687,7 +7321,6 @@
"displayName": "Gemini 3.1 Pro Preview",
"description": "Reasoning-first Gemini preview for agentic coding and complex problem solving",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1000000,
"inputLimit": 936000,
"maxOutputTokens": 64000,
@@ -7711,7 +7344,6 @@
"displayName": "Gemini 3.5 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 200000,
"inputLimit": 128000,
"maxOutputTokens": 64000,
@@ -7735,7 +7367,6 @@
"displayName": "Gemini 3.6 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1000000,
"inputLimit": 936000,
"maxOutputTokens": 64000,
@@ -7759,7 +7390,6 @@
"displayName": "Gemini 3.7 Flash",
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1000000,
"inputLimit": 936000,
"maxOutputTokens": 64000,
@@ -7783,7 +7413,6 @@
"displayName": "GPT-4.1",
"description": "Long-lived GPT workhorse for coding, instruction following, and production apps",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 128000,
"inputLimit": 128000,
"maxOutputTokens": 16384,
@@ -7804,7 +7433,6 @@
"displayName": "GPT-5 Mini",
"description": "Small GPT-5 for responsive agents, coding help, and everyday automation",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 264000,
"inputLimit": 128000,
"maxOutputTokens": 64000,
@@ -7828,7 +7456,6 @@
"displayName": "GPT-5.2",
"description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -7849,7 +7476,6 @@
"displayName": "GPT-5.2 Codex",
"description": "Code-specialist GPT for repository edits, reviews, and long-running software agents",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -7870,7 +7496,6 @@
"displayName": "GPT-5.3 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -7894,7 +7519,6 @@
"displayName": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -7918,7 +7542,6 @@
"displayName": "GPT-5.4 mini",
"description": "Strong small GPT for coding subagents, quick tool use, and high-volume work",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -7942,7 +7565,6 @@
"displayName": "GPT-5.4 nano",
"description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -7963,7 +7585,6 @@
"displayName": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -7987,7 +7608,6 @@
"displayName": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -8011,7 +7631,6 @@
"displayName": "GPT-5.6 Sol",
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -8035,7 +7654,6 @@
"displayName": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -8059,7 +7677,6 @@
"displayName": "Grok 4.5",
"description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 500000,
"inputLimit": 372000,
"maxOutputTokens": 128000,
@@ -8082,7 +7699,6 @@
"displayName": "Grok 4.6",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 500000,
"inputLimit": 372000,
"maxOutputTokens": 128000,
@@ -8106,7 +7722,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 256000,
"inputLimit": 224000,
"maxOutputTokens": 32000,
@@ -8127,7 +7742,6 @@
"displayName": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -8149,7 +7763,6 @@
"displayName": "MAI-Code-1-Flash",
"description": "Microsoft coding model built for fast, efficient assistance in everyday developer workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 256000,
"inputLimit": 128000,
"maxOutputTokens": 128000,
@@ -8173,7 +7786,6 @@
"displayName": "MAI-Code-1.1-Flash",
"description": "Microsoft coding model with native vision support, optimized for fast and efficient software development",
"lifecycle": "active",
- "docsUrl": "https://docs.github.com/en/copilot",
"contextWindow": 256000,
"inputLimit": 128000,
"maxOutputTokens": 128000,
@@ -8198,7 +7810,6 @@
"displayName": "Deep Research Max Preview (Apr-21-2026)",
"description": "Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8217,7 +7828,6 @@
"displayName": "Deep Research Preview (Apr-21-2026)",
"description": "Agentic model for autonomous multi-step research, synthesis, and cited reports",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8236,7 +7846,6 @@
"displayName": "Gemini 2.5 Computer Use Preview 10-2025",
"description": "Specialized Gemini 2.5 model for browser-control agents that automate UI tasks",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8255,7 +7864,6 @@
"displayName": "Gemini 2.5 Flash",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8278,7 +7886,6 @@
"displayName": "Nano Banana",
"description": "Nano Banana image model for fast generation, edits, and character-consistent assets",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 32768,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-06",
@@ -8297,7 +7904,6 @@
"displayName": "Gemini 2.5 Flash-Lite",
"description": "Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8320,7 +7926,6 @@
"displayName": "Gemini 2.5 Flash Preview TTS",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 8192,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-01",
@@ -8339,7 +7944,6 @@
"displayName": "Gemini 2.5 Pro",
"description": "Google's proven reasoning model for coding, math, and multimodal analysis",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8359,7 +7963,6 @@
"displayName": "Gemini 2.5 Pro Preview TTS",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 8192,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-01",
@@ -8378,7 +7981,6 @@
"displayName": "Gemini 3 Flash Preview",
"description": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8401,7 +8003,6 @@
"displayName": "Nano Banana Pro",
"description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -8423,7 +8024,6 @@
"displayName": "Nano Banana Pro",
"description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -8442,7 +8042,6 @@
"displayName": "Nano Banana 2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 65536,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8464,7 +8063,6 @@
"displayName": "Nano Banana 2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 65536,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8486,7 +8084,6 @@
"displayName": "Gemini 3.1 Flash Lite",
"description": "Low-latency Gemini model for high-volume multimodal and agent workloads",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8509,7 +8106,6 @@
"displayName": "Nano Banana 2 Lite",
"description": "Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 65536,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8532,7 +8128,6 @@
"displayName": "Gemini 3.1 Flash Lite Preview",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8555,7 +8150,6 @@
"displayName": "Gemini 3.1 Flash Live Preview",
"description": "High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8578,7 +8172,6 @@
"displayName": "Gemini 3.1 Flash TTS Preview",
"description": "Low-latency speech generation with steerable prompts and expressive audio tags",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 8192,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-01",
@@ -8597,7 +8190,6 @@
"displayName": "Gemini 3.1 Pro Preview",
"description": "Reasoning-first Gemini preview for agentic coding and complex problem solving",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8620,7 +8212,6 @@
"displayName": "Gemini 3.1 Pro Preview Custom Tools",
"description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8643,7 +8234,6 @@
"displayName": "Gemini 3.5 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8666,7 +8256,6 @@
"displayName": "Gemini 3.5 Flash Lite",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2026-03",
@@ -8689,7 +8278,6 @@
"displayName": "Gemini 3.5 Live Translate Preview",
"description": "Low-latency audio-to-audio model for real-time speech translation across 70+ languages",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 16384,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -8708,7 +8296,6 @@
"displayName": "Gemini 3.6 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2026-03",
@@ -8731,7 +8318,6 @@
"displayName": "Gemini 3.7 Flash",
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2026-03",
@@ -8754,7 +8340,6 @@
"displayName": "Gemini Embedding 001",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 2048,
"maxOutputTokens": 1,
"knowledgeCutoff": "2025-05",
@@ -8773,7 +8358,6 @@
"displayName": "Gemini Embedding 2",
"description": "Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 8192,
"maxOutputTokens": 1,
"knowledgeCutoff": "2025-11",
@@ -8792,7 +8376,6 @@
"displayName": "Gemini Flash Latest",
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2026-03",
@@ -8815,7 +8398,6 @@
"displayName": "Gemini Flash-Lite Latest",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2026-03",
@@ -8838,7 +8420,6 @@
"displayName": "Gemini Omni Flash Preview",
"description": "Video generation and editing model for fast, conversational text- and image-to-video workflows",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"lastUpdated": "2026-06-30",
@@ -8856,7 +8437,6 @@
"displayName": "Gemini Robotics-ER 1.6 Preview",
"description": "Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -8879,7 +8459,6 @@
"displayName": "Gemma 4 26B A4B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -8901,7 +8480,6 @@
"displayName": "Gemma 4 31B IT",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -8923,7 +8501,6 @@
"displayName": "Lyria 3 Clip Preview",
"description": "Music generation model for short 30-second clips, loops, and previews from text or image prompts",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"structuredOutput": false,
@@ -8943,7 +8520,6 @@
"displayName": "Lyria 3 Pro Preview",
"description": "Music generation model for full-length songs from text or images with vocals and structure",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"structuredOutput": false,
@@ -8963,7 +8539,6 @@
"displayName": "Veo 3.1 fast",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 480,
"maxOutputTokens": 8192,
"lastUpdated": "2026-01-01",
@@ -8981,7 +8556,6 @@
"displayName": "Veo 3.1",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"lifecycle": "beta",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 480,
"maxOutputTokens": 8192,
"lastUpdated": "2026-01",
@@ -8999,7 +8573,6 @@
"displayName": "Veo 3.1 lite",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"lifecycle": "active",
- "docsUrl": "https://ai.google.dev/gemini-api/docs/models",
"contextWindow": 480,
"maxOutputTokens": 8192,
"lastUpdated": "2026-03-31",
@@ -9019,7 +8592,6 @@
"displayName": "ALLaM-2-7b",
"description": "ALLaM-2-7b instruction tuned model by SDAIA",
"lifecycle": "active",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 4096,
"maxOutputTokens": 4096,
"lastUpdated": "2025-01-23",
@@ -9038,7 +8610,6 @@
"displayName": "Canopy Labs Orpheus Arabic Saudi",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"lifecycle": "beta",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 4000,
"maxOutputTokens": 50000,
"lastUpdated": "2025-12-16",
@@ -9056,7 +8627,6 @@
"displayName": "Canopy Labs Orpheus V1 English",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"lifecycle": "beta",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 4000,
"maxOutputTokens": 50000,
"lastUpdated": "2025-12-19",
@@ -9074,7 +8644,6 @@
"displayName": "Compound",
"description": "General-purpose chat model for instruction following, writing, and analysis",
"lifecycle": "active",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"lastUpdated": "2025-09-04",
@@ -9092,7 +8661,6 @@
"displayName": "Compound Mini",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"lastUpdated": "2025-09-04",
@@ -9110,7 +8678,6 @@
"displayName": "Llama 3.1 8B",
"description": "Compact Llama instruction model for fast chat and local deployment",
"lifecycle": "active",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2023-12",
@@ -9129,7 +8696,6 @@
"displayName": "Llama 3.3 70B",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2023-12",
@@ -9148,7 +8714,6 @@
"displayName": "Llama Prompt Guard 2 22M",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"lifecycle": "beta",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 512,
"maxOutputTokens": 512,
"lastUpdated": "2025-05-29",
@@ -9166,7 +8731,6 @@
"displayName": "Prompt Guard 2 86M",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"lifecycle": "beta",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 512,
"maxOutputTokens": 512,
"lastUpdated": "2025-05-29",
@@ -9184,7 +8748,6 @@
"displayName": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"lifecycle": "active",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -9206,7 +8769,6 @@
"displayName": "GPT OSS 20B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -9228,7 +8790,6 @@
"displayName": "Safety GPT OSS 20B",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"lifecycle": "beta",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -9250,7 +8811,6 @@
"displayName": "Qwen3.6 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -9272,7 +8832,6 @@
"displayName": "Whisper",
"description": "Speech transcription model for accurate audio-to-text and captioning workflows",
"lifecycle": "active",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 0,
"maxOutputTokens": 0,
"lastUpdated": "2025-09-05",
@@ -9290,7 +8849,6 @@
"displayName": "Whisper Large V3 Turbo",
"description": "Speech transcription model for accurate audio-to-text and captioning workflows",
"lifecycle": "active",
- "docsUrl": "https://console.groq.com/docs/models",
"contextWindow": 0,
"maxOutputTokens": 0,
"lastUpdated": "2024-10-01",
@@ -9310,7 +8868,6 @@
"displayName": "DeepSeek-R1",
"description": "Classic open reasoning model for transparent math, coding, and deliberate problem solving",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 64000,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-07",
@@ -9330,7 +8887,6 @@
"displayName": "DeepSeek-R1-0528",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 163840,
"maxOutputTokens": 163840,
"knowledgeCutoff": "2025-05",
@@ -9349,7 +8905,6 @@
"displayName": "DeepSeek-V3",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 64000,
"maxOutputTokens": 8192,
"structuredOutput": true,
@@ -9368,7 +8923,6 @@
"displayName": "DeepSeek V3 0324",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 163840,
"maxOutputTokens": 163840,
"structuredOutput": true,
@@ -9387,7 +8941,6 @@
"displayName": "DeepSeek-V3.1",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"structuredOutput": true,
@@ -9406,7 +8959,6 @@
"displayName": "DeepSeek-V3.2",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 163840,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2024-07",
@@ -9425,7 +8977,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 1048576,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -9445,7 +8996,6 @@
"displayName": "DeepSeek V4 Flash 0731",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 1048576,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -9468,7 +9018,6 @@
"displayName": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 1048576,
"maxOutputTokens": 393216,
"knowledgeCutoff": "2025-05",
@@ -9491,7 +9040,6 @@
"displayName": "DeepSeek V4 Pro 0813",
"description": "Flagship DeepSeek model for coding, reasoning, and agentic work",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"structuredOutput": true,
@@ -9513,7 +9061,6 @@
"displayName": "Gemma 4 26B A4B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -9532,7 +9079,6 @@
"displayName": "Gemma 4 31B IT",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -9551,7 +9097,6 @@
"displayName": "Llama-3.1-8B-Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-12",
@@ -9571,7 +9116,6 @@
"displayName": "Llama-3.3-70B-Instruct",
"description": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-12",
@@ -9591,7 +9135,6 @@
"displayName": "MiniMax-M2",
"description": "Efficient open MiniMax model built for coding agents and tool-heavy workflows",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 204800,
"maxOutputTokens": 128000,
"lastUpdated": "2025-10-27",
@@ -9609,7 +9152,6 @@
"displayName": "MiniMax-M2.1",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-10",
@@ -9628,7 +9170,6 @@
"displayName": "MiniMax-M2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-02-12",
@@ -9646,7 +9187,6 @@
"displayName": "MiniMax-M2.7",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -9665,7 +9205,6 @@
"displayName": "MiniMax-M3",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 524288,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -9684,7 +9223,6 @@
"displayName": "Kimi-K2-Instruct",
"description": "Kimi model for long-context chat, coding, and agentic reasoning",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-10",
@@ -9703,7 +9241,6 @@
"displayName": "Kimi-K2-Instruct-0905",
"description": "Kimi model for long-context chat, coding, and agentic reasoning",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-10",
@@ -9722,7 +9259,6 @@
"displayName": "Kimi-K2-Thinking",
"description": "Kimi reasoning model for long-horizon research, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-08",
@@ -9741,7 +9277,6 @@
"displayName": "Kimi-K2.5",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -9760,7 +9295,6 @@
"displayName": "Kimi-K2.6",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -9779,7 +9313,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -9799,7 +9332,6 @@
"displayName": "Kimi K3",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -9821,7 +9353,6 @@
"displayName": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -9843,7 +9374,6 @@
"displayName": "GPT OSS 20B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -9865,7 +9395,6 @@
"displayName": "Qwen2.5-Coder-32B-Instruct",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"structuredOutput": true,
@@ -9884,7 +9413,6 @@
"displayName": "Qwen3 235B-A22B",
"description": "Large open Qwen MoE for multilingual reasoning, coding, and tool use",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 40960,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -9904,7 +9432,6 @@
"displayName": "Qwen3 235B-A22B Instruct 2507",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -9923,7 +9450,6 @@
"displayName": "Qwen3-235B-A22B-Thinking-2507",
"description": "Qwen reasoning model for deliberate problem solving, math, and coding",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -9942,7 +9468,6 @@
"displayName": "Qwen3 30B A3B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 40960,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -9961,7 +9486,6 @@
"displayName": "Qwen3 32B",
"description": "Dense open Qwen model for self-hosted chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -9981,7 +9505,6 @@
"displayName": "Qwen3-Coder 30B-A3B Instruct",
"description": "Smaller Qwen coder for efficient local agents and repo-level fixes",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -10001,7 +9524,6 @@
"displayName": "Qwen3-Coder-480B-A35B-Instruct",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 66536,
"knowledgeCutoff": "2025-04",
@@ -10020,7 +9542,6 @@
"displayName": "Qwen3-Coder-Next",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -10039,7 +9560,6 @@
"displayName": "Qwen 3 Embedding 4B",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 32000,
"maxOutputTokens": 2048,
"knowledgeCutoff": "2024-12",
@@ -10058,7 +9578,6 @@
"displayName": "Qwen 3 Embedding 8B",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 32000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-12",
@@ -10077,7 +9596,6 @@
"displayName": "Qwen3-Next-80B-A3B-Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 66536,
"knowledgeCutoff": "2025-04",
@@ -10096,7 +9614,6 @@
"displayName": "Qwen3-Next-80B-A3B-Thinking",
"description": "Qwen reasoning model for deliberate problem solving, math, and coding",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -10115,7 +9632,6 @@
"displayName": "Qwen3 VL 235B A22B Instruct",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -10135,7 +9651,6 @@
"displayName": "Qwen3 VL 235B A22B Thinking",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -10158,7 +9673,6 @@
"displayName": "Qwen3.5 122B-A10B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -10177,7 +9691,6 @@
"displayName": "Qwen3.5 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -10196,7 +9709,6 @@
"displayName": "Qwen3.5 35B-A3B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -10215,7 +9727,6 @@
"displayName": "Qwen3.5-397B-A17B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -10237,7 +9748,6 @@
"displayName": "Qwen3.5 9B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -10256,7 +9766,6 @@
"displayName": "Qwen3.6 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -10275,7 +9784,6 @@
"displayName": "Qwen3.6 35B-A3B",
"description": "Open multimodal Qwen MoE for local agents that need vision, audio, and code",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -10294,7 +9802,6 @@
"displayName": "Qwen3.8 2.4T A95B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -10316,7 +9823,6 @@
"displayName": "Step 3.5 Flash",
"description": "StepFun flash lane for quick multimodal reasoning and coding assistance",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 256000,
"knowledgeCutoff": "2025-01",
@@ -10335,7 +9841,6 @@
"displayName": "Step 3.7 Flash",
"description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 256000,
"knowledgeCutoff": "2026-03-01",
@@ -10357,7 +9862,6 @@
"displayName": "Hy3",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 64000,
"structuredOutput": true,
@@ -10379,7 +9883,6 @@
"displayName": "Inkling",
"description": "Multimodal model for analyzing text, images, documents, and rich media",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 1048576,
"maxOutputTokens": 1048576,
"structuredOutput": true,
@@ -10401,7 +9904,6 @@
"displayName": "Inkling Small",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 524288,
"maxOutputTokens": 1048576,
"lastUpdated": "2026-07-30",
@@ -10419,7 +9921,6 @@
"displayName": "MiMo-V2-Flash",
"description": "MiMo flash model for fast multimodal assistance and agent workflows",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-12",
@@ -10438,7 +9939,6 @@
"displayName": "MiMo-V2.5",
"description": "MiMo model for long-context reasoning, perception, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2024-12",
@@ -10462,7 +9962,6 @@
"displayName": "MiMo-V2.5-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2024-12",
@@ -10486,7 +9985,6 @@
"displayName": "GLM-4.5",
"description": "Hybrid-reasoning GLM release that made the 4.5 line broadly useful",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 98304,
"knowledgeCutoff": "2025-04",
@@ -10505,7 +10003,6 @@
"displayName": "GLM-4.5-Air",
"description": "Lighter GLM-4.5 variant for fast coding assistance and cheaper agents",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 98304,
"knowledgeCutoff": "2025-04",
@@ -10524,7 +10021,6 @@
"displayName": "GLM-4.5V",
"description": "GLM vision model for visual reasoning, documents, and multimodal agents",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 65536,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -10543,7 +10039,6 @@
"displayName": "GLM-4.6",
"description": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -10562,7 +10057,6 @@
"displayName": "GLM-4.6V-Flash",
"description": "GLM vision model for visual reasoning, documents, and multimodal agents",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"lastUpdated": "2025-12-08",
@@ -10583,7 +10077,6 @@
"displayName": "GLM-4.7",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -10602,7 +10095,6 @@
"displayName": "GLM-4.7-Flash",
"description": "Efficient GLM model for fast reasoning, coding, and agent workflows",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 200000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-04",
@@ -10622,7 +10114,6 @@
"displayName": "GLM-5",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 202752,
"maxOutputTokens": 131072,
"lastUpdated": "2026-02-11",
@@ -10640,7 +10131,6 @@
"displayName": "GLM-5.1",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 202752,
"maxOutputTokens": 131072,
"lastUpdated": "2026-04-03",
@@ -10658,7 +10148,6 @@
"displayName": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://huggingface.co/docs/inference-providers",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -10679,7 +10168,6 @@
"displayName": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"lifecycle": "active",
- "docsUrl": "https://www.kimi.com/code/docs/en/third-party-tools/other-coding-agents.html",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -10703,7 +10191,6 @@
"displayName": "Kimi K3-256K",
"description": "256K-context version of Kimi K3, reducing token consumption for shorter coding sessions",
"lifecycle": "active",
- "docsUrl": "https://www.kimi.com/code/docs/en/third-party-tools/other-coding-agents.html",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -10726,7 +10213,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://www.kimi.com/code/docs/en/third-party-tools/other-coding-agents.html",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -10747,7 +10233,6 @@
"displayName": "Kimi For Coding HighSpeed",
"description": "Lower-latency Kimi Code variant for interactive edits and coding-agent loops",
"lifecycle": "active",
- "docsUrl": "https://www.kimi.com/code/docs/en/third-party-tools/other-coding-agents.html",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -10770,7 +10255,6 @@
"displayName": "MiniMax-M2",
"description": "Efficient open MiniMax model built for coding agents and tool-heavy workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/guides/quickstart",
"contextWindow": 196608,
"maxOutputTokens": 128000,
"lastUpdated": "2025-10-27",
@@ -10788,7 +10272,6 @@
"displayName": "MiniMax-M2.1",
"description": "Earlier MiniMax agent model for practical coding and productivity tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/guides/quickstart",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2025-12-23",
@@ -10806,7 +10289,6 @@
"displayName": "MiniMax-M2.5",
"description": "Prior MiniMax coding model for agent workflows, office edits, and automation",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/guides/quickstart",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-02-12",
@@ -10824,7 +10306,6 @@
"displayName": "MiniMax-M2.5-highspeed",
"description": "High-speed MiniMax model for low-latency coding and agent workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/guides/quickstart",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-02-13",
@@ -10842,7 +10323,6 @@
"displayName": "MiniMax-M2.7",
"description": "Open MiniMax flagship for coding agents, office automation, and complex environments",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/guides/quickstart",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-03-18",
@@ -10860,7 +10340,6 @@
"displayName": "MiniMax-M2.7-highspeed",
"description": "Low-latency M2.7 variant for interactive coding plans and agent loops",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/guides/quickstart",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-03-18",
@@ -10878,7 +10357,6 @@
"displayName": "MiniMax-M3",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/guides/quickstart",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"lastUpdated": "2026-06-25",
@@ -10901,7 +10379,6 @@
"displayName": "MiniMax-M2",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.minimaxi.com/docs/guides/quickstart",
"contextWindow": 196608,
"maxOutputTokens": 128000,
"lastUpdated": "2025-10-27",
@@ -10919,7 +10396,6 @@
"displayName": "MiniMax-M2.1",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.minimaxi.com/docs/guides/quickstart",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2025-12-23",
@@ -10937,7 +10413,6 @@
"displayName": "MiniMax-M2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.minimaxi.com/docs/guides/quickstart",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-02-12",
@@ -10955,7 +10430,6 @@
"displayName": "MiniMax-M2.5-highspeed",
"description": "High-speed MiniMax model for low-latency coding and agent workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.minimaxi.com/docs/guides/quickstart",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-02-13",
@@ -10973,7 +10447,6 @@
"displayName": "MiniMax-M2.7",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.minimaxi.com/docs/guides/quickstart",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-03-18",
@@ -10991,7 +10464,6 @@
"displayName": "MiniMax-M2.7-highspeed",
"description": "High-speed MiniMax model for low-latency coding and agent workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.minimaxi.com/docs/guides/quickstart",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-03-18",
@@ -11009,7 +10481,6 @@
"displayName": "MiniMax-M3",
"description": "MiniMax multimodal coding model for long-context reasoning and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.minimaxi.com/docs/guides/quickstart",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"lastUpdated": "2026-06-25",
@@ -11032,7 +10503,6 @@
"displayName": "MiniMax-M2",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/token-plan/intro",
"contextWindow": 196608,
"maxOutputTokens": 128000,
"lastUpdated": "2025-10-27",
@@ -11051,7 +10521,6 @@
"displayName": "MiniMax-M2.1",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/token-plan/intro",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2025-12-23",
@@ -11070,7 +10539,6 @@
"displayName": "MiniMax-M2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/token-plan/intro",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-02-12",
@@ -11089,7 +10557,6 @@
"displayName": "MiniMax-M2.5-highspeed",
"description": "High-speed MiniMax model for low-latency coding and agent workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/token-plan/intro",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-02-13",
@@ -11108,7 +10575,6 @@
"displayName": "MiniMax-M2.7",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/token-plan/intro",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-03-18",
@@ -11127,7 +10593,6 @@
"displayName": "MiniMax-M2.7-highspeed",
"description": "High-speed MiniMax model for low-latency coding and agent workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/token-plan/intro",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-03-18",
@@ -11146,7 +10611,6 @@
"displayName": "MiniMax-M3",
"description": "MiniMax multimodal coding model for long-context reasoning and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.minimax.io/docs/token-plan/intro",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"lastUpdated": "2026-06-25",
@@ -11170,7 +10634,6 @@
"displayName": "Codestral (latest)",
"description": "Mistral code model for completions, refactors, and developer IDE workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 256000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-10",
@@ -11189,7 +10652,6 @@
"displayName": "Devstral 2",
"description": "Mistral's coding-agent model for repository work, terminal tasks, and software fixes",
"lifecycle": "deprecated",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-12",
@@ -11208,7 +10670,6 @@
"displayName": "Devstral 2",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-12",
@@ -11227,7 +10688,6 @@
"displayName": "Devstral Medium",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-05",
@@ -11246,7 +10706,6 @@
"displayName": "Devstral 2 (latest)",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-12",
@@ -11265,7 +10724,6 @@
"displayName": "Devstral Small 2505",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-05",
@@ -11284,7 +10742,6 @@
"displayName": "Devstral Small",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-05",
@@ -11303,7 +10760,6 @@
"displayName": "Devstral Small 2",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 256000,
"maxOutputTokens": 256000,
"knowledgeCutoff": "2025-12",
@@ -11323,7 +10779,6 @@
"displayName": "Magistral Medium (latest)",
"description": "Mistral reasoning model for transparent analysis, math, and complex decisions",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-06",
@@ -11342,7 +10797,6 @@
"displayName": "Magistral Small",
"description": "Mistral reasoning model for transparent analysis, math, and complex decisions",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-06",
@@ -11361,7 +10815,6 @@
"displayName": "Ministral 3B (latest)",
"description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-10",
@@ -11380,7 +10833,6 @@
"displayName": "Ministral 8B (latest)",
"description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-10",
@@ -11399,7 +10851,6 @@
"displayName": "Mistral Embed",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 8000,
"maxOutputTokens": 3072,
"lastUpdated": "2023-12-11",
@@ -11417,7 +10868,6 @@
"displayName": "Mistral Large 2.1",
"description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-11",
@@ -11436,7 +10886,6 @@
"displayName": "Mistral Large 3",
"description": "Mistral's largest general model for enterprise agents, coding, and multilingual reasoning",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-11",
@@ -11455,7 +10904,6 @@
"displayName": "Mistral Large (latest)",
"description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-11",
@@ -11474,7 +10922,6 @@
"displayName": "Mistral Medium 3",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-05",
@@ -11493,7 +10940,6 @@
"displayName": "Mistral Medium 3.1",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-05",
@@ -11512,7 +10958,6 @@
"displayName": "Mistral Medium 3.5",
"description": "Balanced Mistral model for enterprise assistants, multilingual work, and tools",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -11534,7 +10979,6 @@
"displayName": "Mistral Medium (latest)",
"description": "Balanced Mistral model for enterprise assistants, multilingual work, and tools",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -11556,7 +11000,6 @@
"displayName": "Mistral Nemo",
"description": "Efficient Mistral-NVIDIA open model for multilingual chat and local deployment",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-07",
@@ -11575,7 +11018,6 @@
"displayName": "Mistral Small 3.2",
"description": "Efficient Mistral model for fast chat, extraction, and production assistants",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-03",
@@ -11594,7 +11036,6 @@
"displayName": "Mistral Small 4",
"description": "Fast Mistral production model for chat, extraction, and cost-sensitive agents",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 256000,
"maxOutputTokens": 256000,
"knowledgeCutoff": "2025-06",
@@ -11616,7 +11057,6 @@
"displayName": "Mistral Small (latest)",
"description": "Efficient Mistral model for fast chat, extraction, and production assistants",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 256000,
"maxOutputTokens": 256000,
"knowledgeCutoff": "2025-06",
@@ -11638,7 +11078,6 @@
"displayName": "Mistral 7B",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 8000,
"maxOutputTokens": 8000,
"knowledgeCutoff": "2023-12",
@@ -11657,7 +11096,6 @@
"displayName": "Open Mistral Nemo",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-07",
@@ -11676,7 +11114,6 @@
"displayName": "Mixtral 8x22B",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 64000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2024-04",
@@ -11695,7 +11132,6 @@
"displayName": "Mixtral 8x7B",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 32000,
"maxOutputTokens": 32000,
"knowledgeCutoff": "2024-01",
@@ -11714,7 +11150,6 @@
"displayName": "Pixtral 12B",
"description": "Mistral vision-language model for image understanding and multimodal chat",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-09",
@@ -11733,7 +11168,6 @@
"displayName": "Pixtral Large (latest)",
"description": "Mistral's larger vision model for document-heavy image understanding and chat",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-11",
@@ -11752,7 +11186,6 @@
"displayName": "Voxtral Mini (latest)",
"description": "Speech transcription model for accurate audio-to-text and captioning workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 0,
"maxOutputTokens": 0,
"lastUpdated": "2026-02-01",
@@ -11770,7 +11203,6 @@
"displayName": "Voxtral Mini TTS (latest)",
"description": "Multilingual text-to-speech model with zero-shot voice cloning",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 0,
"maxOutputTokens": 0,
"lastUpdated": "2026-03-01",
@@ -11788,7 +11220,6 @@
"displayName": "Voxtral Small (latest)",
"description": "Instruct model with native audio input for speech understanding and tool use",
"lifecycle": "active",
- "docsUrl": "https://docs.mistral.ai/getting-started/models/",
"contextWindow": 32000,
"maxOutputTokens": 32000,
"lastUpdated": "2025-07-15",
@@ -11808,7 +11239,6 @@
"displayName": "Kimi K2 0711",
"description": "Kimi model for long-context chat, coding, and agentic reasoning",
"lifecycle": "active",
- "docsUrl": "https://platform.moonshot.cn/docs/api/chat",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-10",
@@ -11827,7 +11257,6 @@
"displayName": "Kimi K2 0905",
"description": "Kimi model for long-context chat, coding, and agentic reasoning",
"lifecycle": "active",
- "docsUrl": "https://platform.moonshot.cn/docs/api/chat",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-10",
@@ -11846,7 +11275,6 @@
"displayName": "Kimi K2 Thinking",
"description": "Thinking Kimi model for slower research passes, planning, and hard technical questions",
"lifecycle": "active",
- "docsUrl": "https://platform.moonshot.cn/docs/api/chat",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-08",
@@ -11865,7 +11293,6 @@
"displayName": "Kimi K2 Thinking Turbo",
"description": "Kimi reasoning model for long-horizon research, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://platform.moonshot.cn/docs/api/chat",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-08",
@@ -11884,7 +11311,6 @@
"displayName": "Kimi K2 Turbo",
"description": "Fast Kimi model for responsive chat, coding help, and agent loops",
"lifecycle": "active",
- "docsUrl": "https://platform.moonshot.cn/docs/api/chat",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-10",
@@ -11903,7 +11329,6 @@
"displayName": "Kimi K2.5",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"lifecycle": "active",
- "docsUrl": "https://platform.moonshot.cn/docs/api/chat",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -11926,7 +11351,6 @@
"displayName": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"lifecycle": "active",
- "docsUrl": "https://platform.moonshot.cn/docs/api/chat",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -11949,7 +11373,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://platform.moonshot.cn/docs/api/chat",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -11969,7 +11392,6 @@
"displayName": "Kimi K2.7 Code HighSpeed",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://platform.moonshot.cn/docs/api/chat",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -11989,7 +11411,6 @@
"displayName": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"lifecycle": "active",
- "docsUrl": "https://platform.moonshot.cn/docs/api/chat",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -12014,7 +11435,6 @@
"displayName": "dracarys-llama-3.1-70b-instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2025-05-22",
@@ -12033,7 +11453,6 @@
"displayName": "BGE M3",
"description": "Flagship model for demanding analysis, coding, and production agent workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 8192,
"maxOutputTokens": 1024,
"lastUpdated": "2026-04-30",
@@ -12052,7 +11471,6 @@
"displayName": "FLUX.1-Kontext-dev",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 40960,
"maxOutputTokens": 40960,
"lastUpdated": "2025-08-12",
@@ -12071,7 +11489,6 @@
"displayName": "FLUX.1-schnell",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 77,
"inputLimit": 77,
"maxOutputTokens": 0,
@@ -12093,7 +11510,6 @@
"displayName": "FLUX.2 Klein 4B",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 40960,
"maxOutputTokens": 40960,
"knowledgeCutoff": "2025-06",
@@ -12113,7 +11529,6 @@
"displayName": "FLUX.1-dev",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 4096,
"maxOutputTokens": 0,
"knowledgeCutoff": "2024-08",
@@ -12133,7 +11548,6 @@
"displayName": "ByteDance-Seed/Seed-OSS-36B-Instruct",
"description": "Tool-capable chat model for instruction following and agentic application workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262000,
"maxOutputTokens": 262000,
"structuredOutput": true,
@@ -12153,7 +11567,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 1048576,
"maxOutputTokens": 393216,
"knowledgeCutoff": "2025-05",
@@ -12176,7 +11589,6 @@
"displayName": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 1048576,
"maxOutputTokens": 393216,
"knowledgeCutoff": "2025-05",
@@ -12199,7 +11611,6 @@
"displayName": "Gemma 2 2b It",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"structuredOutput": true,
@@ -12219,7 +11630,6 @@
"displayName": "Gemma 3 12B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"lastUpdated": "2025-03-12",
@@ -12238,7 +11648,6 @@
"displayName": "Gemma 3 4B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"lastUpdated": "2025-03-12",
@@ -12257,7 +11666,6 @@
"displayName": "Gemma 3n E2b It",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-06",
@@ -12278,7 +11686,6 @@
"displayName": "Gemma 3n E4b It",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-06",
@@ -12299,7 +11706,6 @@
"displayName": "Gemma-4-31B-IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 256000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-01",
@@ -12322,7 +11728,6 @@
"displayName": "paligemma",
"description": "Gemini multimodal model for text, image, audio, video, and document tasks",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2024-08-26",
@@ -12341,7 +11746,6 @@
"displayName": "esm2-650m",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2025-03-10",
@@ -12360,7 +11764,6 @@
"displayName": "esmfold",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2025-06-12",
@@ -12379,7 +11782,6 @@
"displayName": "Llama 3.1 70b Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"structuredOutput": true,
@@ -12399,7 +11801,6 @@
"displayName": "Llama 3.1 8B Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 16000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-12",
@@ -12419,7 +11820,6 @@
"displayName": "Llama 3.2 11b Vision Instruct",
"description": "Open Llama multimodal model for image understanding and text reasoning",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-12",
@@ -12440,7 +11840,6 @@
"displayName": "Llama 3.2 1b Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-12",
@@ -12461,7 +11860,6 @@
"displayName": "Llama 3.2 3B Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 32768,
"maxOutputTokens": 32000,
"structuredOutput": true,
@@ -12481,7 +11879,6 @@
"displayName": "Llama-3.2-90B-Vision-Instruct",
"description": "Open Llama multimodal model for image understanding and text reasoning",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2023-12",
@@ -12501,7 +11898,6 @@
"displayName": "Llama 3.3 70b Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"structuredOutput": true,
@@ -12521,7 +11917,6 @@
"displayName": "Llama 4 Maverick 17b 128e Instruct",
"description": "Open multimodal Llama model for strong reasoning and fast responses",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-02",
@@ -12542,7 +11937,6 @@
"displayName": "Llama Guard 4 12B",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"lastUpdated": "2026-04-30",
@@ -12561,7 +11955,6 @@
"displayName": "Muse Glimmer 30B",
"description": "Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2026-01-04",
@@ -12585,7 +11978,6 @@
"displayName": "Phi-4-Mini",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-12",
@@ -12605,7 +11997,6 @@
"displayName": "Phi 4 Multimodal",
"description": "General-purpose chat model for instruction following, writing, and analysis",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"inputLimit": 128000,
"maxOutputTokens": 16384,
@@ -12626,7 +12017,6 @@
"displayName": "MiniMax-M2.7",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"lastUpdated": "2026-04-11",
@@ -12645,7 +12035,6 @@
"displayName": "MiniMax-M3",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 1000000,
"maxOutputTokens": 16384,
"lastUpdated": "2026-06-01",
@@ -12667,7 +12056,6 @@
"displayName": "Magistral Small 2506",
"description": "Mistral reasoning model for transparent analysis, math, and complex decisions",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 32768,
"inputLimit": 32768,
"maxOutputTokens": 32768,
@@ -12688,7 +12076,6 @@
"displayName": "Ministral 3 14B Instruct 2512",
"description": "Compact Mistral VLM for chat and instruction-based workloads",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"lastUpdated": "2025-12-02",
@@ -12707,7 +12094,6 @@
"displayName": "Mistral-7B-Instruct-v0.3",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 65536,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -12727,7 +12113,6 @@
"displayName": "Mistral Large 3 675B Instruct 2512",
"description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -12748,7 +12133,6 @@
"displayName": "Mistral Medium 3",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"inputLimit": 131072,
"maxOutputTokens": 32768,
@@ -12769,7 +12153,6 @@
"displayName": "Mistral Medium 3.5",
"description": "Balanced Mistral model for enterprise assistants, multilingual work, and tools",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -12792,7 +12175,6 @@
"displayName": "mistral-nemotron",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2025-06-12",
@@ -12811,7 +12193,6 @@
"displayName": "mistral-small-4-119b-2603",
"description": "Efficient Mistral model for fast chat, extraction, and production assistants",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"structuredOutput": true,
@@ -12834,7 +12215,6 @@
"displayName": "Mistral: Mixtral 8x22B Instruct",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 65536,
"maxOutputTokens": 13108,
"lastUpdated": "2024-04-17",
@@ -12853,7 +12233,6 @@
"displayName": "Mistral: Mixtral 8x7B Instruct",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 32768,
"maxOutputTokens": 16384,
"lastUpdated": "2026-03-15",
@@ -12872,7 +12251,6 @@
"displayName": "Kimi K2 0905",
"description": "Kimi model for long-context chat, coding, and agentic reasoning",
"lifecycle": "deprecated",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-10",
@@ -12892,7 +12270,6 @@
"displayName": "Kimi K2.6",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "deprecated",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -12916,7 +12293,6 @@
"displayName": "Active Speaker Detection",
"description": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 0,
"maxOutputTokens": 4096,
"lastUpdated": "2026-04-16",
@@ -12935,7 +12311,6 @@
"displayName": "bevformer",
"description": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2025-07-20",
@@ -12954,7 +12329,6 @@
"displayName": "cosmos-predict1-5b",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 0,
"maxOutputTokens": 4096,
"lastUpdated": "2025-03-18",
@@ -12973,7 +12347,6 @@
"displayName": "Cosmos Reason2 8B",
"description": "Vision language model for physical-world understanding with structured reasoning on video and images",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"lastUpdated": "2025-12-01",
@@ -12992,7 +12365,6 @@
"displayName": "cosmos-transfer1-7b",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 0,
"maxOutputTokens": 4096,
"lastUpdated": "2025-06-30",
@@ -13011,7 +12383,6 @@
"displayName": "cosmos-transfer2.5-2b",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 0,
"maxOutputTokens": 4096,
"lastUpdated": "2026-02-26",
@@ -13030,7 +12401,6 @@
"displayName": "gliner-pii",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"lastUpdated": "2026-03-03",
@@ -13049,7 +12419,6 @@
"displayName": "llama-3_2-nemoretriever-300m-embed-v1",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 32768,
"maxOutputTokens": 2048,
"lastUpdated": "2025-07-24",
@@ -13068,7 +12437,6 @@
"displayName": "Llama 3.1 Nemotron 70B Instruct",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2025-04-15",
@@ -13087,7 +12455,6 @@
"displayName": "Llama 3.1 Nemotron Nano 8B v1",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"lastUpdated": "2025-03-18",
@@ -13109,7 +12476,6 @@
"displayName": "Llama 3.1 Nemotron Nano VL 8B v1",
"description": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 32768,
"maxOutputTokens": 16384,
"lastUpdated": "2025-04-10",
@@ -13128,7 +12494,6 @@
"displayName": "llama-3.1-nemotron-safety-guard-8b-v3",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"lastUpdated": "2025-10-28",
@@ -13147,7 +12512,6 @@
"displayName": "Llama 3.1 Nemotron Ultra 253B",
"description": "Flagship Nemotron model for high-throughput reasoning and complex agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"lastUpdated": "2025-04-07",
@@ -13169,7 +12533,6 @@
"displayName": "Llama 3.3 Nemotron Super 49B v1",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"lastUpdated": "2025-04-07",
@@ -13191,7 +12554,6 @@
"displayName": "Llama 3.3 Nemotron Super 49B v1.5",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"lastUpdated": "2025-07-25",
@@ -13213,7 +12575,6 @@
"displayName": "llama-nemotron-embed-vl-1b-v2",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 32768,
"maxOutputTokens": 2048,
"lastUpdated": "2026-02-10",
@@ -13232,7 +12593,6 @@
"displayName": "llama-nemotron-rerank-vl-1b-v2",
"description": "Reranking model for improving retrieval quality in search and recommendation systems",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"lastUpdated": "2026-03-31",
@@ -13251,7 +12611,6 @@
"displayName": "magpie-tts-zeroshot",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 0,
"maxOutputTokens": 4096,
"lastUpdated": "2025-06-12",
@@ -13270,7 +12629,6 @@
"displayName": "nemotron-3-content-safety",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"lastUpdated": "2026-04-16",
@@ -13289,7 +12647,6 @@
"displayName": "nemotron-3-nano-30b-a3b",
"description": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2024-09",
@@ -13312,7 +12669,6 @@
"displayName": "Nemotron 3 Nano Omni",
"description": "Open Nemotron omni model combining reasoning with text, vision, and audio",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 256000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -13335,7 +12691,6 @@
"displayName": "Nemotron 3 Super",
"description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-04",
@@ -13357,7 +12712,6 @@
"displayName": "Nemotron 3 Ultra 550B A55B",
"description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -13379,7 +12733,6 @@
"displayName": "Nemotron 3.5 Lightning 30B A3B",
"description": "Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -13402,7 +12755,6 @@
"displayName": "nemotron-content-safety-reasoning-4b",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"lastUpdated": "2026-01-22",
@@ -13421,7 +12773,6 @@
"displayName": "nemotron-mini-4b-instruct",
"description": "Compact Nemotron model for efficient reasoning and deployable AI agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2024-08-26",
@@ -13440,7 +12791,6 @@
"displayName": "Nemotron Nano 12B v2 VL",
"description": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"lastUpdated": "2025-10-28",
@@ -13459,7 +12809,6 @@
"displayName": "nemotron-voicechat",
"description": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2026-03-16",
@@ -13478,7 +12827,6 @@
"displayName": "nv-embed-v1",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 32768,
"maxOutputTokens": 2048,
"lastUpdated": "2025-07-22",
@@ -13497,7 +12845,6 @@
"displayName": "nv-embedcode-7b-v1",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 32768,
"maxOutputTokens": 2048,
"lastUpdated": "2025-05-29",
@@ -13516,7 +12863,6 @@
"displayName": "nvidia-nemotron-nano-9b-v2",
"description": "Compact Nemotron model for efficient reasoning and deployable AI agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2024-09",
@@ -13539,7 +12885,6 @@
"displayName": "rerank-qa-mistral-4b",
"description": "Reranking model for improving retrieval quality in search and recommendation systems",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"lastUpdated": "2025-01-17",
@@ -13558,7 +12903,6 @@
"displayName": "riva-translate-4b-instruct-v1_1",
"description": "Translation model for multilingual conversion, localization, and cross-language workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"lastUpdated": "2025-12-12",
@@ -13577,7 +12921,6 @@
"displayName": "sparsedrive",
"description": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2025-07-20",
@@ -13596,7 +12939,6 @@
"displayName": "streampetr",
"description": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2025-11-13",
@@ -13615,7 +12957,6 @@
"displayName": "studiovoice",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2025-06-13",
@@ -13634,7 +12975,6 @@
"displayName": "synthetic-video-detector",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 0,
"maxOutputTokens": 4096,
"lastUpdated": "2026-04-16",
@@ -13653,7 +12993,6 @@
"displayName": "usdcode",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"lastUpdated": "2026-01-01",
@@ -13672,7 +13011,6 @@
"displayName": "usdvalidate",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 0,
"maxOutputTokens": 4096,
"lastUpdated": "2025-01-08",
@@ -13691,7 +13029,6 @@
"displayName": "GPT-OSS-120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2025-08",
@@ -13715,7 +13052,6 @@
"displayName": "GPT OSS 20B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -13738,7 +13074,6 @@
"displayName": "Whisper Large v3",
"description": "Speech transcription model for accurate audio-to-text and captioning workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 0,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-09",
@@ -13758,7 +13093,6 @@
"displayName": "Laguna XS 2.1",
"description": "Agentic coding model from Poolside in the XS size class for local deployment",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"structuredOutput": false,
@@ -13778,7 +13112,6 @@
"displayName": "Qwen Image",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 0,
"maxOutputTokens": 0,
"structuredOutput": false,
@@ -13798,7 +13131,6 @@
"displayName": "Qwen Image Edit",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 0,
"maxOutputTokens": 0,
"structuredOutput": false,
@@ -13818,7 +13150,6 @@
"displayName": "Qwen2.5 Coder 32b Instruct",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"structuredOutput": true,
@@ -13838,7 +13169,6 @@
"displayName": "Qwen3 Coder 480B A35B Instruct",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 66536,
"knowledgeCutoff": "2025-04",
@@ -13858,7 +13188,6 @@
"displayName": "Qwen3-Next-80B-A3B-Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-12",
@@ -13878,7 +13207,6 @@
"displayName": "Qwen3.5 122B-A10B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -13901,7 +13229,6 @@
"displayName": "Qwen3.5-397B-A17B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 262144,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2026-01",
@@ -13925,7 +13252,6 @@
"displayName": "sarvam-m",
"description": "Efficient Indian-language reasoning model for chat, coding, and multilingual work",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2025-07-25",
@@ -13944,7 +13270,6 @@
"displayName": "Step 3.5 Flash",
"description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 256000,
"maxOutputTokens": 16384,
"lastUpdated": "2026-02-02",
@@ -13966,7 +13291,6 @@
"displayName": "Step 3.7 Flash",
"description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 256000,
"maxOutputTokens": 16384,
"lastUpdated": "2026-05-28",
@@ -13988,7 +13312,6 @@
"displayName": "Inkling",
"description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 1048576,
"maxOutputTokens": 16384,
"lastUpdated": "2026-07-15",
@@ -14007,7 +13330,6 @@
"displayName": "solar-10.7b-instruct",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"lastUpdated": "2025-04-10",
@@ -14026,7 +13348,6 @@
"displayName": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://docs.api.nvidia.com/nim/",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -14051,7 +13372,6 @@
"displayName": "deepseek-v4-flash",
"description": "Fast DeepSeek model for efficient chat, coding help, and agent loops",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 1048576,
"maxOutputTokens": 1048576,
"lastUpdated": "2026-04-24",
@@ -14073,7 +13393,6 @@
"displayName": "DeepSeek V4 Flash 0731",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 1048576,
"maxOutputTokens": 1048576,
"knowledgeCutoff": "2025-05",
@@ -14097,7 +13416,6 @@
"displayName": "deepseek-v4-pro",
"description": "Flagship DeepSeek model for coding, reasoning, and agentic work",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 1048576,
"maxOutputTokens": 1048576,
"lastUpdated": "2026-04-24",
@@ -14119,7 +13437,6 @@
"displayName": "gemma4:31b",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -14141,7 +13458,6 @@
"displayName": "glm-5.1",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 202752,
"maxOutputTokens": 131072,
"lastUpdated": "2026-04-07",
@@ -14162,7 +13478,6 @@
"displayName": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 976000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -14184,7 +13499,6 @@
"displayName": "gpt-oss:120b",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"lastUpdated": "2026-01-19",
@@ -14205,7 +13519,6 @@
"displayName": "gpt-oss:20b",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"lastUpdated": "2026-01-19",
@@ -14226,7 +13539,6 @@
"displayName": "kimi-k2.5",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"lastUpdated": "2026-01-27",
@@ -14247,7 +13559,6 @@
"displayName": "kimi-k2.6",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"lastUpdated": "2026-04-20",
@@ -14268,7 +13579,6 @@
"displayName": "kimi-k2.7-code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -14291,7 +13601,6 @@
"displayName": "kimi-k3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -14314,7 +13623,6 @@
"displayName": "minimax-m2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-01",
@@ -14333,7 +13641,6 @@
"displayName": "minimax-m2.7",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 196608,
"maxOutputTokens": 196608,
"lastUpdated": "2026-03-18",
@@ -14354,7 +13661,6 @@
"displayName": "minimax-m3",
"description": "MiniMax multimodal coding model for long-context reasoning and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 512000,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-01",
@@ -14377,7 +13683,6 @@
"displayName": "mistral-large-3:675b",
"description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"lastUpdated": "2026-01-19",
@@ -14395,7 +13700,6 @@
"displayName": "nemotron-3-nano:30b",
"description": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"lastUpdated": "2026-01-19",
@@ -14416,7 +13720,6 @@
"displayName": "nemotron-3-super",
"description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"lastUpdated": "2026-03-12",
@@ -14437,7 +13740,6 @@
"displayName": "nemotron-3-ultra",
"description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 262144,
"maxOutputTokens": 128000,
"lastUpdated": "2026-06-04",
@@ -14458,7 +13760,6 @@
"displayName": "qwen3.5:397b",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://docs.ollama.com/cloud",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"lastUpdated": "2026-02-17",
@@ -14481,7 +13782,6 @@
"displayName": "chatgpt-image-latest",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 0,
"inputLimit": 0,
"maxOutputTokens": 0,
@@ -14500,7 +13800,6 @@
"displayName": "GPT-3.5-turbo",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "deprecated",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 16385,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2021-09-01",
@@ -14520,7 +13819,6 @@
"displayName": "GPT-4",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "deprecated",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 8192,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2023-11",
@@ -14540,7 +13838,6 @@
"displayName": "GPT-4 Turbo",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "deprecated",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-12",
@@ -14560,7 +13857,6 @@
"displayName": "GPT-4.1",
"description": "Long-lived GPT workhorse for coding, instruction following, and production apps",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 1047576,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -14580,7 +13876,6 @@
"displayName": "GPT-4.1 mini",
"description": "Affordable GPT-4.1 lane for fast coding help and structured extraction",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 1047576,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -14600,7 +13895,6 @@
"displayName": "GPT-4.1 nano",
"description": "Tiny GPT-4.1 option for classification, routing, and very high-volume tasks",
"lifecycle": "deprecated",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 1047576,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -14620,7 +13914,6 @@
"displayName": "GPT-4o",
"description": "Omni-era GPT for multimodal chat, practical coding, and general assistants",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-09",
@@ -14640,7 +13933,6 @@
"displayName": "GPT-4o (2024-05-13)",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "deprecated",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-09",
@@ -14660,7 +13952,6 @@
"displayName": "GPT-4o (2024-08-06)",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-09",
@@ -14680,7 +13971,6 @@
"displayName": "GPT-4o (2024-11-20)",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-09",
@@ -14700,7 +13990,6 @@
"displayName": "GPT-4o mini",
"description": "Small omni GPT for cheap multimodal assistance and production-scale traffic",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-09",
@@ -14720,7 +14009,6 @@
"displayName": "GPT-5",
"description": "Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -14744,7 +14032,6 @@
"displayName": "GPT-5 Mini",
"description": "Small GPT-5 for responsive agents, coding help, and everyday automation",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -14768,7 +14055,6 @@
"displayName": "GPT-5 Nano",
"description": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -14792,7 +14078,6 @@
"displayName": "GPT-5 Pro",
"description": "Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 272000,
@@ -14816,7 +14101,6 @@
"displayName": "GPT-5.1",
"description": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -14840,7 +14124,6 @@
"displayName": "GPT-5.2",
"description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -14864,7 +14147,6 @@
"displayName": "GPT-5.2 Chat",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-08-31",
@@ -14887,7 +14169,6 @@
"displayName": "GPT-5.2 Pro",
"description": "Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -14911,7 +14192,6 @@
"displayName": "GPT-5.3 Chat (latest)",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-08-31",
@@ -14931,7 +14211,6 @@
"displayName": "GPT-5.3 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -14955,7 +14234,6 @@
"displayName": "GPT-5.3 Codex Spark",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 128000,
"inputLimit": 100000,
"maxOutputTokens": 32000,
@@ -14979,7 +14257,6 @@
"displayName": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -15003,7 +14280,6 @@
"displayName": "GPT-5.4 mini",
"description": "Strong small GPT for coding subagents, quick tool use, and high-volume work",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -15027,7 +14303,6 @@
"displayName": "GPT-5.4 nano",
"description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -15051,7 +14326,6 @@
"displayName": "GPT-5.4 Pro",
"description": "More exact GPT-5.4 tier for demanding professional reasoning and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -15075,7 +14349,6 @@
"displayName": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -15099,7 +14372,6 @@
"displayName": "GPT-5.5 Pro",
"description": "Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -15123,7 +14395,6 @@
"displayName": "GPT-5.6",
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -15147,7 +14418,6 @@
"displayName": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -15171,7 +14441,6 @@
"displayName": "GPT-5.6 Sol",
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -15195,7 +14464,6 @@
"displayName": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -15219,7 +14487,6 @@
"displayName": "gpt-image-1",
"description": "OpenAI image model for production generation, edits, and brand-safe visual workflows",
"lifecycle": "deprecated",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 0,
"inputLimit": 0,
"maxOutputTokens": 0,
@@ -15238,7 +14505,6 @@
"displayName": "gpt-image-1-mini",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 0,
"inputLimit": 0,
"maxOutputTokens": 0,
@@ -15257,7 +14523,6 @@
"displayName": "gpt-image-1.5",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 0,
"inputLimit": 0,
"maxOutputTokens": 0,
@@ -15276,7 +14541,6 @@
"displayName": "gpt-image-2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 0,
"inputLimit": 0,
"maxOutputTokens": 0,
@@ -15295,7 +14559,6 @@
"displayName": "GPT-Realtime-2.1",
"description": "Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 128000,
"inputLimit": 96000,
"maxOutputTokens": 32000,
@@ -15319,7 +14582,6 @@
"displayName": "o1",
"description": "O-series reasoning model for hard analysis, math, coding, and planning",
"lifecycle": "deprecated",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2023-09",
@@ -15342,7 +14604,6 @@
"displayName": "o1-pro",
"description": "O-series reasoning model for hard analysis, math, coding, and planning",
"lifecycle": "deprecated",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2023-09",
@@ -15365,7 +14626,6 @@
"displayName": "o3",
"description": "Deliberate o-series reasoner for hard math, coding, and multi-step analysis",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2024-05",
@@ -15388,7 +14648,6 @@
"displayName": "o3-mini",
"description": "Smaller o-series reasoner for economical coding, math, and planning tasks",
"lifecycle": "deprecated",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2024-05",
@@ -15411,7 +14670,6 @@
"displayName": "o3-pro",
"description": "High-effort o3 tier for difficult technical reasoning and careful answers",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2024-05",
@@ -15434,7 +14692,6 @@
"displayName": "o4-mini",
"description": "Fast o-series model for compact reasoning, coding, and tool use",
"lifecycle": "deprecated",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2024-05",
@@ -15457,7 +14714,6 @@
"displayName": "text-embedding-3-large",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 8191,
"maxOutputTokens": 3072,
"knowledgeCutoff": "2024-01",
@@ -15476,7 +14732,6 @@
"displayName": "text-embedding-3-small",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 8191,
"maxOutputTokens": 1536,
"knowledgeCutoff": "2024-01",
@@ -15495,7 +14750,6 @@
"displayName": "text-embedding-ada-002",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"lifecycle": "active",
- "docsUrl": "https://platform.openai.com/docs/models",
"contextWindow": 8192,
"maxOutputTokens": 1536,
"knowledgeCutoff": "2022-12",
@@ -15516,7 +14770,6 @@
"displayName": "Big Pickle",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 200000,
"inputLimit": 160000,
"maxOutputTokens": 32000,
@@ -15538,7 +14791,6 @@
"displayName": "Claude Haiku 3.5",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 200000,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-07-31",
@@ -15557,7 +14809,6 @@
"displayName": "Claude Fable 5",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -15579,7 +14830,6 @@
"displayName": "Claude Haiku 4.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 200000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-02-28",
@@ -15598,7 +14848,6 @@
"displayName": "Claude Opus 4.1",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 200000,
"maxOutputTokens": 32000,
"knowledgeCutoff": "2025-03-31",
@@ -15617,7 +14866,6 @@
"displayName": "Claude Opus 4.5",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 200000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-03-31",
@@ -15639,7 +14887,6 @@
"displayName": "Claude Opus 4.6",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-05-31",
@@ -15661,7 +14908,6 @@
"displayName": "Claude Opus 4.7",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -15683,7 +14929,6 @@
"displayName": "Claude Opus 4.8",
"description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01",
@@ -15705,7 +14950,6 @@
"displayName": "Claude Opus 5",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-05",
@@ -15727,7 +14971,6 @@
"displayName": "Claude Sonnet 4",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-03-31",
@@ -15746,7 +14989,6 @@
"displayName": "Claude Sonnet 4.5",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-07-31",
@@ -15765,7 +15007,6 @@
"displayName": "Claude Sonnet 4.6",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-08-31",
@@ -15787,7 +15028,6 @@
"displayName": "Claude Sonnet 5",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -15809,7 +15049,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -15833,7 +15072,6 @@
"displayName": "DeepSeek V4 Flash Free",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 200000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-05",
@@ -15857,7 +15095,6 @@
"displayName": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -15881,7 +15118,6 @@
"displayName": "Gemini 3 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -15904,7 +15140,6 @@
"displayName": "Gemini 3 Pro",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -15927,7 +15162,6 @@
"displayName": "Gemini 3.1 Pro Preview",
"description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -15950,7 +15184,6 @@
"displayName": "Gemini 3.5 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -15973,7 +15206,6 @@
"displayName": "Gemini 3.5 Flash Lite",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2026-03",
@@ -15996,7 +15228,6 @@
"displayName": "Gemini 3.6 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2026-03",
@@ -16019,7 +15250,6 @@
"displayName": "Gemini 3.7 Flash",
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2026-03",
@@ -16042,7 +15272,6 @@
"displayName": "GLM-4.6",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -16064,7 +15293,6 @@
"displayName": "GLM-4.7",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -16086,7 +15314,6 @@
"displayName": "GLM-4.7 Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -16109,7 +15336,6 @@
"displayName": "GLM-5",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -16131,7 +15357,6 @@
"displayName": "GLM-5 Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -16154,7 +15379,6 @@
"displayName": "GLM-5.1",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -16176,7 +15400,6 @@
"displayName": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -16198,7 +15421,6 @@
"displayName": "GPT-5",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16222,7 +15444,6 @@
"displayName": "GPT-5 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16246,7 +15467,6 @@
"displayName": "GPT-5 Nano",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16270,7 +15490,6 @@
"displayName": "GPT-5.1",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16294,7 +15513,6 @@
"displayName": "GPT-5.1 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16318,7 +15536,6 @@
"displayName": "GPT-5.1 Codex Max",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16342,7 +15559,6 @@
"displayName": "GPT-5.1 Codex Mini",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16366,7 +15582,6 @@
"displayName": "GPT-5.2",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16390,7 +15605,6 @@
"displayName": "GPT-5.2 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16414,7 +15628,6 @@
"displayName": "GPT-5.3 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16438,7 +15651,6 @@
"displayName": "GPT-5.3 Codex Spark",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 128000,
"inputLimit": 128000,
"maxOutputTokens": 128000,
@@ -16462,7 +15674,6 @@
"displayName": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -16486,7 +15697,6 @@
"displayName": "GPT-5.4 Mini",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16510,7 +15720,6 @@
"displayName": "GPT-5.4 Nano",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -16534,7 +15743,6 @@
"displayName": "GPT-5.4 Pro",
"description": "Frontier GPT model for professional reasoning, coding, and multimodal work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -16558,7 +15766,6 @@
"displayName": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -16582,7 +15789,6 @@
"displayName": "GPT-5.5 Pro",
"description": "Frontier GPT model for professional reasoning, coding, and multimodal work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -16606,7 +15812,6 @@
"displayName": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -16630,7 +15835,6 @@
"displayName": "GPT-5.6 Sol (50% Off)",
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -16654,7 +15858,6 @@
"displayName": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -16678,7 +15881,6 @@
"displayName": "Grok 4.5",
"description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 500000,
"maxOutputTokens": 500000,
"structuredOutput": true,
@@ -16700,7 +15902,6 @@
"displayName": "Grok 4.6",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 500000,
"maxOutputTokens": 500000,
"knowledgeCutoff": "2026-02-01",
@@ -16723,7 +15924,6 @@
"displayName": "Grok Build 0.1",
"description": "Fast Grok coding model tuned for agentic engineering and iterative edits",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 256000,
"maxOutputTokens": 256000,
"structuredOutput": true,
@@ -16742,7 +15942,6 @@
"displayName": "Grok Code Fast 1",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 256000,
"maxOutputTokens": 256000,
"lastUpdated": "2025-08-20",
@@ -16761,7 +15960,6 @@
"displayName": "Hy3 Free",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 190000,
"maxOutputTokens": 64000,
"structuredOutput": true,
@@ -16785,7 +15983,6 @@
"displayName": "Hy3 preview Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 256000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-06",
@@ -16805,7 +16002,6 @@
"displayName": "Kimi K2",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-10",
@@ -16824,7 +16020,6 @@
"displayName": "Kimi K2 Thinking",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-10",
@@ -16843,7 +16038,6 @@
"displayName": "Kimi K2.5",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2024-10",
@@ -16865,7 +16059,6 @@
"displayName": "Kimi K2.5 Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-10",
@@ -16888,7 +16081,6 @@
"displayName": "Kimi K2.6",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2024-10",
@@ -16910,7 +16102,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -16930,7 +16121,6 @@
"displayName": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -16952,7 +16142,6 @@
"displayName": "Laguna S 2.1 Free",
"description": "Agentic coding model from Poolside in the XS size class for local deployment",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 256000,
"maxOutputTokens": 32000,
"structuredOutput": false,
@@ -16975,7 +16164,6 @@
"displayName": "Ling 2.6 Flash Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262100,
"maxOutputTokens": 32800,
"knowledgeCutoff": "2025-06",
@@ -16995,7 +16183,6 @@
"displayName": "Ling-3.0-flash Free",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -17018,7 +16205,6 @@
"displayName": "Ling-3.0-tiny Free",
"description": "Compact MoE model for responsive agents, instruction following, and multi-turn conversations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -17038,7 +16224,6 @@
"displayName": "LongCat-2.0 Free",
"description": "Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"lastUpdated": "2026-06-30",
@@ -17060,7 +16245,6 @@
"displayName": "MiMo V2 Flash Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2024-12",
@@ -17080,7 +16264,6 @@
"displayName": "MiMo V2 Omni Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2024-12",
@@ -17100,7 +16283,6 @@
"displayName": "MiMo V2 Pro Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2024-12",
@@ -17120,7 +16302,6 @@
"displayName": "MiMo V2.5 Free",
"description": "MiMo omni model for text, image, video, audio, and agents",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 200000,
"maxOutputTokens": 32000,
"knowledgeCutoff": "2024-12",
@@ -17140,7 +16321,6 @@
"displayName": "MiniMax-M2.1",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-01",
@@ -17159,7 +16339,6 @@
"displayName": "MiniMax-M2.1 Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-01",
@@ -17179,7 +16358,6 @@
"displayName": "MiniMax-M2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-01",
@@ -17198,7 +16376,6 @@
"displayName": "MiniMax-M2.5 Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-01",
@@ -17218,7 +16395,6 @@
"displayName": "MiniMax-M2.7",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-01",
@@ -17237,7 +16413,6 @@
"displayName": "MiniMax-M3",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 512000,
"maxOutputTokens": 128000,
"lastUpdated": "2026-06-01",
@@ -17255,7 +16430,6 @@
"displayName": "MiniMax-M3 Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 200000,
"maxOutputTokens": 32000,
"knowledgeCutoff": "2025-01",
@@ -17278,7 +16452,6 @@
"displayName": "Muse Spark 1.2",
"description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -17300,7 +16473,6 @@
"displayName": "Muse Spark 1.2 Free",
"description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -17323,7 +16495,6 @@
"displayName": "Nemotron 3 Super Free",
"description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-02",
@@ -17343,7 +16514,6 @@
"displayName": "Nemotron 3 Ultra Free",
"description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-02",
@@ -17363,7 +16533,6 @@
"displayName": "Nemotron 3.5 Lightning Free",
"description": "Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -17383,7 +16552,6 @@
"displayName": "North Mini Code Free",
"description": "Cohere coding model for practical software engineering and agentic edits",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 256000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-09-23",
@@ -17407,7 +16575,6 @@
"displayName": "Qwen3 Coder",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -17426,7 +16593,6 @@
"displayName": "Qwen3.5 Plus",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -17448,7 +16614,6 @@
"displayName": "Qwen3.6 Plus",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -17470,7 +16635,6 @@
"displayName": "Qwen3.6 Plus Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -17493,7 +16657,6 @@
"displayName": "Ring 2.6 1T Free",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262000,
"maxOutputTokens": 66000,
"knowledgeCutoff": "2025-06",
@@ -17513,7 +16676,6 @@
"displayName": "Trinity Large Preview",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-06",
@@ -17533,7 +16695,6 @@
"displayName": "Ox Alpha Free (Unlimited)",
"description": "Stealth reasoning model for coding, agentic tasks, and tool use",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -17558,7 +16719,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -17581,7 +16741,6 @@
"displayName": "DeepSeek V4 Pro (New)",
"description": "Flagship DeepSeek model for coding, reasoning, and agentic work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -17604,7 +16763,6 @@
"displayName": "GLM-5",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 202752,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -17623,7 +16781,6 @@
"displayName": "GLM-5.1",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 202752,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -17642,7 +16799,6 @@
"displayName": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -17664,7 +16820,6 @@
"displayName": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -17686,7 +16841,6 @@
"displayName": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -17710,7 +16864,6 @@
"displayName": "Grok 4.5",
"description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 500000,
"maxOutputTokens": 500000,
"structuredOutput": true,
@@ -17732,7 +16885,6 @@
"displayName": "Hy3 (8x usage)",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 256000,
"maxOutputTokens": 64000,
"lastUpdated": "2026-07-06",
@@ -17753,7 +16905,6 @@
"displayName": "Kimi K2.5",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2024-10",
@@ -17772,7 +16923,6 @@
"displayName": "Kimi K2.6",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2024-10",
@@ -17791,7 +16941,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -17811,7 +16960,6 @@
"displayName": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -17833,7 +16981,6 @@
"displayName": "MiMo V2 Omni",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-12",
@@ -17852,7 +16999,6 @@
"displayName": "MiMo V2 Pro",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-12",
@@ -17871,7 +17017,6 @@
"displayName": "MiMo V2.5",
"description": "MiMo omni model for text, image, video, audio, and agents",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-12",
@@ -17890,7 +17035,6 @@
"displayName": "MiMo V2.5 Pro",
"description": "MiMo pro model for strong multimodal reasoning and agent execution",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-12",
@@ -17909,7 +17053,6 @@
"displayName": "MiniMax-M2.5",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -17928,7 +17071,6 @@
"displayName": "MiniMax-M2.7",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-01",
@@ -17947,7 +17089,6 @@
"displayName": "MiniMax-M3",
"description": "MiniMax multimodal coding model for long-context reasoning and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-01",
@@ -17969,7 +17110,6 @@
"displayName": "Muse Spark 1.2 Contributor",
"description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -17991,7 +17131,6 @@
"displayName": "Ox Alpha Free (Unlimited)",
"description": "Stealth reasoning model for coding, agentic tasks, and tool use",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -18014,7 +17153,6 @@
"displayName": "Qwen3.5 Plus",
"description": "Legacy model retained for compatibility with older integrations",
"lifecycle": "deprecated",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -18036,7 +17174,6 @@
"displayName": "Qwen3.6 Plus",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -18058,7 +17195,6 @@
"displayName": "Qwen3.7 Max",
"description": "Flagship model for demanding analysis, coding, and production agent workflows",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"lastUpdated": "2026-05-21",
@@ -18079,7 +17215,6 @@
"displayName": "Qwen3.7 Plus",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"lastUpdated": "2026-06-02",
@@ -18100,7 +17235,6 @@
"displayName": "Qwen3.8 Max",
"description": "2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://opencode.ai/docs/zen",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -18124,7 +17258,6 @@
"displayName": "Claude Fable Latest",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -18146,7 +17279,6 @@
"displayName": "Anthropic Claude Haiku Latest",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 64000,
"structuredOutput": true,
@@ -18168,7 +17300,6 @@
"displayName": "Claude Opus Latest",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -18191,7 +17322,6 @@
"displayName": "Anthropic Claude Sonnet Latest",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -18215,7 +17345,6 @@
"displayName": "DeepSeek V4 Flash Latest",
"description": "Fast DeepSeek model for efficient chat, coding help, and agent loops",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1310720,
"maxOutputTokens": 1048576,
"structuredOutput": true,
@@ -18238,7 +17367,6 @@
"displayName": "Google Gemini Flash Latest",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01-01",
@@ -18261,7 +17389,6 @@
"displayName": "Google Gemini Pro Latest",
"description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -18284,7 +17411,6 @@
"displayName": "MoonshotAI Kimi Latest",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 974842,
"structuredOutput": true,
@@ -18307,7 +17433,6 @@
"displayName": "OpenAI GPT Latest",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-02-16",
@@ -18330,7 +17455,6 @@
"displayName": "OpenAI GPT Mini Latest",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-08-31",
@@ -18353,7 +17477,6 @@
"displayName": "Grok Latest",
"description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 500000,
"maxOutputTokens": 1000000,
"structuredOutput": true,
@@ -18375,7 +17498,6 @@
"displayName": "GLM Latest",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": false,
@@ -18397,7 +17519,6 @@
"displayName": "Aion-2.0",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -18416,7 +17537,6 @@
"displayName": "Aion-3.0",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -18435,7 +17555,6 @@
"displayName": "Aion-3.0-Mini",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -18454,7 +17573,6 @@
"displayName": "Aion-RP 1.0 (8B)",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32768,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2023-12-31",
@@ -18474,7 +17592,6 @@
"displayName": "Olmo 3 32B Think",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 65536,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -18493,7 +17610,6 @@
"displayName": "Nova 2 Lite",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 65535,
"structuredOutput": false,
@@ -18512,7 +17628,6 @@
"displayName": "Nova Lite 1.0",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 300000,
"maxOutputTokens": 5120,
"knowledgeCutoff": "2024-10-31",
@@ -18532,7 +17647,6 @@
"displayName": "Nova Micro 1.0",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 5120,
"knowledgeCutoff": "2024-10-31",
@@ -18552,7 +17666,6 @@
"displayName": "Nova Premier 1.0",
"description": "Flagship model for demanding analysis, coding, and production agent workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 32000,
"structuredOutput": false,
@@ -18571,7 +17684,6 @@
"displayName": "Nova Pro 1.0",
"description": "Flagship model for demanding analysis, coding, and production agent workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 300000,
"maxOutputTokens": 5120,
"knowledgeCutoff": "2024-10-31",
@@ -18591,7 +17703,6 @@
"displayName": "Magnum v4 72B",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32768,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2024-06-30",
@@ -18611,7 +17722,6 @@
"displayName": "Claude 3 Haiku",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-08-31",
@@ -18631,7 +17741,6 @@
"displayName": "Claude Fable 5",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -18654,7 +17763,6 @@
"displayName": "Claude Haiku 4.5 (latest)",
"description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-02-28",
@@ -18677,7 +17785,6 @@
"displayName": "Claude Opus 4",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 32000,
"knowledgeCutoff": "2025-01-31",
@@ -18700,7 +17807,6 @@
"displayName": "Claude Opus 4.1 (latest)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 32000,
"knowledgeCutoff": "2025-03-31",
@@ -18723,7 +17829,6 @@
"displayName": "Claude Opus 4.5 (latest)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-05",
@@ -18747,7 +17852,6 @@
"displayName": "Claude Opus 4.6",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-05-31",
@@ -18771,7 +17875,6 @@
"displayName": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -18795,7 +17898,6 @@
"displayName": "Claude Opus 4.7 (Fast)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -18819,7 +17921,6 @@
"displayName": "Claude Opus 4.8",
"description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01",
@@ -18843,7 +17944,6 @@
"displayName": "Claude Opus 4.8 (Fast)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01",
@@ -18867,7 +17967,6 @@
"displayName": "Claude Opus 5",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-05",
@@ -18891,7 +17990,6 @@
"displayName": "Claude Opus 5 (Fast)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-05",
@@ -18915,7 +18013,6 @@
"displayName": "Claude Sonnet 4",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-01-31",
@@ -18938,7 +18035,6 @@
"displayName": "Claude Sonnet 4.5 (latest)",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-07-31",
@@ -18961,7 +18057,6 @@
"displayName": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2025-08-31",
@@ -18985,7 +18080,6 @@
"displayName": "Claude Sonnet 5",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2026-01-31",
@@ -19009,7 +18103,6 @@
"displayName": "Trinity Large Thinking",
"description": "Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -19028,7 +18121,6 @@
"displayName": "Virtuoso Large",
"description": "Flagship model for demanding analysis, coding, and production agent workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 64000,
"knowledgeCutoff": "2025-03-31",
@@ -19048,7 +18140,6 @@
"displayName": "ERNIE 4.5 VL 424B A47B ",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 123000,
"maxOutputTokens": 16000,
"knowledgeCutoff": "2025-03-31",
@@ -19068,7 +18159,6 @@
"displayName": "Seed 1.6",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -19087,7 +18177,6 @@
"displayName": "Seed 1.6 Flash",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -19106,7 +18195,6 @@
"displayName": "Seed 2.1 Turbo",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -19125,7 +18213,6 @@
"displayName": "Seed 2.0 Code",
"description": "Coding model for repository understanding, refactors, and agentic engineering tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -19148,7 +18235,6 @@
"displayName": "Seed 2.0 Lite",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -19171,7 +18257,6 @@
"displayName": "Seed 2.0 Mini",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -19194,7 +18279,6 @@
"displayName": "UI-TARS 7B ",
"description": "Multimodal model for analyzing text, images, documents, and rich media",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 2048,
"knowledgeCutoff": "2025-01-31",
@@ -19214,7 +18298,6 @@
"displayName": "Uncensored",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-04-30",
@@ -19234,7 +18317,6 @@
"displayName": "Command A",
"description": "Cohere command model for multilingual enterprise agents, tools, and chat",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-08-31",
@@ -19254,7 +18336,6 @@
"displayName": "Command R",
"description": "Cohere retrieval model for long-context chat and enterprise RAG workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 4000,
"knowledgeCutoff": "2024-06-01",
@@ -19274,7 +18355,6 @@
"displayName": "Command R+",
"description": "Cohere's RAG workhorse for long-context enterprise search and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 4000,
"knowledgeCutoff": "2024-06-01",
@@ -19294,7 +18374,6 @@
"displayName": "Command R7B",
"description": "Cohere retrieval model for long-context chat and enterprise RAG workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 4000,
"knowledgeCutoff": "2024-06-01",
@@ -19314,7 +18393,6 @@
"displayName": "North Mini Code (free)",
"description": "Cohere coding model for practical software engineering and agentic edits",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 64000,
"structuredOutput": false,
@@ -19334,7 +18412,6 @@
"displayName": "Cogito v2.1 671B",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -19353,7 +18430,6 @@
"displayName": "DeepSeek Chat",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 163840,
"maxOutputTokens": 16000,
"knowledgeCutoff": "2025-09",
@@ -19373,7 +18449,6 @@
"displayName": "DeepSeek V3 0324",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 163840,
"maxOutputTokens": 163840,
"knowledgeCutoff": "2024-07-31",
@@ -19393,7 +18468,6 @@
"displayName": "DeepSeek V3.1",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 163840,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -19416,7 +18490,6 @@
"displayName": "DeepSeek-R1",
"description": "Classic open reasoning model for transparent math, coding, and deliberate problem solving",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 64000,
"maxOutputTokens": 16000,
"knowledgeCutoff": "2024-07",
@@ -19436,7 +18509,6 @@
"displayName": "R1 0528",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 163840,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -19456,7 +18528,6 @@
"displayName": "R1 Distill Llama 70B",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 8192,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-07-31",
@@ -19476,7 +18547,6 @@
"displayName": "DeepSeek V3.1 Terminus",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 163840,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -19499,7 +18569,6 @@
"displayName": "DeepSeek V3.2",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 163840,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2024-07",
@@ -19522,7 +18591,6 @@
"displayName": "DeepSeek V3.2 Exp",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 163840,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-07-31",
@@ -19545,7 +18613,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -19569,7 +18636,6 @@
"displayName": "DeepSeek V4 Flash 0731",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1310720,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -19593,7 +18659,6 @@
"displayName": "DeepSeek V4 Flash Vision Exp",
"description": "Fast DeepSeek model for efficient chat, coding help, and agent loops",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 384000,
"structuredOutput": false,
@@ -19616,7 +18681,6 @@
"displayName": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 393216,
"knowledgeCutoff": "2025-05",
@@ -19640,7 +18704,6 @@
"displayName": "DeepSeek V4 Pro 0813",
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 384000,
"structuredOutput": true,
@@ -19663,7 +18726,6 @@
"displayName": "Dots3-Note Preview (free)",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 512000,
"maxOutputTokens": 512000,
"structuredOutput": true,
@@ -19683,7 +18745,6 @@
"displayName": "Gemini 2.5 Flash",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65535,
"knowledgeCutoff": "2025-01",
@@ -19706,7 +18767,6 @@
"displayName": "Nano Banana",
"description": "Nano Banana image model for fast generation, edits, and character-consistent assets",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32768,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2024-06",
@@ -19726,7 +18786,6 @@
"displayName": "Gemini 2.5 Flash-Lite",
"description": "Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65535,
"knowledgeCutoff": "2025-01",
@@ -19749,7 +18808,6 @@
"displayName": "Gemini 2.5 Pro",
"description": "Google's proven reasoning model for coding, math, and multimodal analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -19769,7 +18827,6 @@
"displayName": "Gemini 2.5 Pro Preview 06-05",
"description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01-31",
@@ -19789,7 +18846,6 @@
"displayName": "Gemini 2.5 Pro Preview 05-06",
"description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65535,
"knowledgeCutoff": "2025-01-31",
@@ -19809,7 +18865,6 @@
"displayName": "Gemini 3 Flash Preview",
"description": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -19833,7 +18888,6 @@
"displayName": "Nano Banana Pro",
"description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -19853,7 +18907,6 @@
"displayName": "Nano Banana Pro",
"description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 65536,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -19873,7 +18926,6 @@
"displayName": "Nano Banana 2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-01",
@@ -19897,7 +18949,6 @@
"displayName": "Nano Banana 2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 65536,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -19921,7 +18972,6 @@
"displayName": "Gemini 3.1 Flash Lite",
"description": "Low-latency Gemini model for high-volume multimodal and agent workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -19945,7 +18995,6 @@
"displayName": "Nano Banana 2 Lite",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 65536,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -19969,7 +19018,6 @@
"displayName": "Gemini 3.1 Flash Lite Preview",
"description": "Low-latency Gemini model for high-volume multimodal and agent workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -19993,7 +19041,6 @@
"displayName": "Gemini 3.1 Pro Preview",
"description": "Reasoning-first Gemini preview for agentic coding and complex problem solving",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -20016,7 +19063,6 @@
"displayName": "Gemini 3.1 Pro Preview Custom Tools",
"description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -20039,7 +19085,6 @@
"displayName": "Gemini 3.5 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -20062,7 +19107,6 @@
"displayName": "Gemini 3.5 Flash Lite",
"description": "Low-latency Gemini model for high-volume multimodal and agent workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2026-03",
@@ -20085,7 +19129,6 @@
"displayName": "Gemini 3.6 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2026-03",
@@ -20108,7 +19151,6 @@
"displayName": "Gemini 3.7 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2026-03",
@@ -20131,7 +19173,6 @@
"displayName": "Gemma 2 27B",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 8192,
"maxOutputTokens": 2048,
"knowledgeCutoff": "2024-06-30",
@@ -20151,7 +19192,6 @@
"displayName": "Gemma 3 12B",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-08-31",
@@ -20171,7 +19211,6 @@
"displayName": "Gemma 3 27B",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2024-08-31",
@@ -20191,7 +19230,6 @@
"displayName": "Gemma 3 4B",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-08-31",
@@ -20211,7 +19249,6 @@
"displayName": "Gemma 3n 4B",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32768,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-08-31",
@@ -20231,7 +19268,6 @@
"displayName": "Gemma 4 26B A4B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -20253,7 +19289,6 @@
"displayName": "Gemma 4 26B A4B (free)",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -20276,7 +19311,6 @@
"displayName": "Gemma 4 31B IT",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -20298,7 +19332,6 @@
"displayName": "Gemma 4 31B (free)",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -20321,7 +19354,6 @@
"displayName": "Lyria 3 Clip Preview",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"structuredOutput": false,
@@ -20341,7 +19373,6 @@
"displayName": "Lyria 3 Pro Preview",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"structuredOutput": false,
@@ -20361,7 +19392,6 @@
"displayName": "MythoMax 13B",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 8192,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-06-30",
@@ -20381,7 +19411,6 @@
"displayName": "Granite 4.0 Micro",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131000,
"maxOutputTokens": 131000,
"structuredOutput": false,
@@ -20400,7 +19429,6 @@
"displayName": "Granite 4.1 8B",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -20419,7 +19447,6 @@
"displayName": "Mercury 2",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 50000,
"structuredOutput": true,
@@ -20441,7 +19468,6 @@
"displayName": "Ling-2.6-1T",
"description": "Tool-capable chat model for instruction following and agentic application workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -20460,7 +19486,6 @@
"displayName": "Ling-2.6-flash",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -20479,7 +19504,6 @@
"displayName": "Ling-3.0-flash",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -20498,7 +19522,6 @@
"displayName": "Ring-2.6-1T",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": false,
@@ -20520,7 +19543,6 @@
"displayName": "KAT-Coder-Air V2.5",
"description": "Coding model for repository understanding, refactors, and agentic engineering tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 80000,
"structuredOutput": true,
@@ -20539,7 +19561,6 @@
"displayName": "KAT-Coder-Pro V2",
"description": "Coding model for repository understanding, refactors, and agentic engineering tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 80000,
"structuredOutput": true,
@@ -20558,7 +19579,6 @@
"displayName": "KAT-Coder-Pro V2.5",
"description": "Coding model for repository understanding, refactors, and agentic engineering tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 80000,
"structuredOutput": true,
@@ -20577,7 +19597,6 @@
"displayName": "LFM2.5-2.6B (free)",
"description": "Free provider route for experiments, demos, and cost-sensitive chat workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 65536,
"maxOutputTokens": 8192,
"structuredOutput": true,
@@ -20597,7 +19616,6 @@
"displayName": "Weaver (alpha)",
"description": "General-purpose chat model for instruction following, writing, and analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 8000,
"maxOutputTokens": 6000,
"knowledgeCutoff": "2023-06-30",
@@ -20617,7 +19635,6 @@
"displayName": "LongCat 2.0",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048756,
"maxOutputTokens": 262144,
"structuredOutput": false,
@@ -20636,7 +19653,6 @@
"displayName": "Llama 3.1 70B Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-12-31",
@@ -20656,7 +19672,6 @@
"displayName": "Llama-3.1-8B-Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2023-12",
@@ -20676,7 +19691,6 @@
"displayName": "Llama 3.2 1B Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 60000,
"maxOutputTokens": 60000,
"knowledgeCutoff": "2023-12-31",
@@ -20696,7 +19710,6 @@
"displayName": "Llama 3.2 3B Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2023-12-31",
@@ -20716,7 +19729,6 @@
"displayName": "Llama-3.3-70B-Instruct",
"description": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-12",
@@ -20736,7 +19748,6 @@
"displayName": "Llama 4 Maverick",
"description": "Open multimodal Llama model for strong reasoning and fast responses",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-08-31",
@@ -20756,7 +19767,6 @@
"displayName": "Llama 4 Scout",
"description": "Open multimodal Llama model for long-context analysis and efficient agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1310720,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-08-31",
@@ -20776,7 +19786,6 @@
"displayName": "Llama Guard 4 12B",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-08-31",
@@ -20796,7 +19805,6 @@
"displayName": "Muse Glimmer 30B",
"description": "Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2026-01-04",
@@ -20819,7 +19827,6 @@
"displayName": "Muse Spark 1.1",
"description": "Open Llama multimodal model for image understanding and text reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 1048576,
"structuredOutput": true,
@@ -20841,7 +19848,6 @@
"displayName": "Muse Spark 1.2",
"description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 1048576,
"structuredOutput": true,
@@ -20863,7 +19869,6 @@
"displayName": "Phi 4",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 16384,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-06-30",
@@ -20883,7 +19888,6 @@
"displayName": "WizardLM-2 8x22B",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 65535,
"maxOutputTokens": 8000,
"knowledgeCutoff": "2024-04-30",
@@ -20903,7 +19907,6 @@
"displayName": "MiniMax-01",
"description": "MiniMax multimodal coding model for long-context reasoning and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000192,
"maxOutputTokens": 1000192,
"knowledgeCutoff": "2024-03-31",
@@ -20923,7 +19926,6 @@
"displayName": "MiniMax M1",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 40000,
"knowledgeCutoff": "2024-06-30",
@@ -20943,7 +19945,6 @@
"displayName": "MiniMax-M2",
"description": "Efficient open MiniMax model built for coding agents and tool-heavy workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -20962,7 +19963,6 @@
"displayName": "MiniMax-M2 Her",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 65536,
"maxOutputTokens": 2048,
"structuredOutput": false,
@@ -20981,7 +19981,6 @@
"displayName": "MiniMax-M2.1",
"description": "Earlier MiniMax agent model for practical coding and productivity tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"structuredOutput": false,
@@ -21000,7 +19999,6 @@
"displayName": "MiniMax-M2.5",
"description": "Prior MiniMax coding model for agent workflows, office edits, and automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 204800,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -21019,7 +20017,6 @@
"displayName": "MiniMax-M2.7",
"description": "Open MiniMax flagship for coding agents, office automation, and complex environments",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -21038,7 +20035,6 @@
"displayName": "MiniMax-M3",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 512000,
"structuredOutput": true,
@@ -21057,7 +20053,6 @@
"displayName": "Codestral 2508",
"description": "Mistral coding model for code completion, generation, and developer workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 256000,
"knowledgeCutoff": "2025-03-31",
@@ -21077,7 +20072,6 @@
"displayName": "Ministral 3 14B 2512",
"description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -21096,7 +20090,6 @@
"displayName": "Ministral 3 3B 2512",
"description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -21115,7 +20108,6 @@
"displayName": "Ministral 8B",
"description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-09-30",
@@ -21135,7 +20127,6 @@
"displayName": "Ministral 3 8B 2512",
"description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -21154,7 +20145,6 @@
"displayName": "Mistral Large",
"description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-11-30",
@@ -21174,7 +20164,6 @@
"displayName": "Mistral Large 2407",
"description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2024-03-31",
@@ -21194,7 +20183,6 @@
"displayName": "Mistral Large 3",
"description": "Mistral's largest general model for enterprise agents, coding, and multilingual reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2024-11",
@@ -21214,7 +20202,6 @@
"displayName": "Mistral Medium 3",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-03-31",
@@ -21234,7 +20221,6 @@
"displayName": "Mistral Medium 3.5",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -21256,7 +20242,6 @@
"displayName": "Mistral Medium 3.1",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-06-30",
@@ -21276,7 +20261,6 @@
"displayName": "Mistral Nemo",
"description": "Efficient Mistral-NVIDIA open model for multilingual chat and local deployment",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-07",
@@ -21296,7 +20280,6 @@
"displayName": "Saba",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32768,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-09-30",
@@ -21316,7 +20299,6 @@
"displayName": "Mistral Small 3",
"description": "Efficient Mistral model for fast chat, extraction, and production assistants",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32768,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-10-31",
@@ -21336,7 +20318,6 @@
"displayName": "Mistral Small 4",
"description": "Fast Mistral production model for chat, extraction, and cost-sensitive agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-06",
@@ -21359,7 +20340,6 @@
"displayName": "Mistral Small 3.1 24B",
"description": "Efficient Mistral model for fast chat, extraction, and production assistants",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2023-10-31",
@@ -21379,7 +20359,6 @@
"displayName": "Mistral Small 3.2 24B",
"description": "Efficient Mistral model for fast chat, extraction, and production assistants",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-10-31",
@@ -21399,7 +20378,6 @@
"displayName": "Mixtral 8x22B Instruct",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 65536,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2024-01-31",
@@ -21419,7 +20397,6 @@
"displayName": "Voxtral Small 24B 2507",
"description": "Efficient Mistral model for fast chat, extraction, and production assistants",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32000,
"maxOutputTokens": 32000,
"structuredOutput": true,
@@ -21438,7 +20415,6 @@
"displayName": "Kimi K2 0711",
"description": "Kimi model for long-context chat, coding, and agentic reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 100352,
"knowledgeCutoff": "2024-12-31",
@@ -21458,7 +20434,6 @@
"displayName": "Kimi K2 0905",
"description": "Kimi model for long-context chat, coding, and agentic reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 100352,
"knowledgeCutoff": "2024-12-31",
@@ -21478,7 +20453,6 @@
"displayName": "Kimi K2 Thinking",
"description": "Thinking Kimi model for slower research passes, planning, and hard technical questions",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 100352,
"knowledgeCutoff": "2024-08",
@@ -21498,7 +20472,6 @@
"displayName": "Kimi K2.5",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -21518,7 +20491,6 @@
"displayName": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -21538,7 +20510,6 @@
"displayName": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-01",
@@ -21558,7 +20529,6 @@
"displayName": "Kimi K3",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 1048576,
"structuredOutput": true,
@@ -21581,7 +20551,6 @@
"displayName": "Morph V3 Fast",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 81920,
"maxOutputTokens": 38000,
"structuredOutput": false,
@@ -21600,7 +20569,6 @@
"displayName": "Morph V3 Large",
"description": "Flagship model for demanding analysis, coding, and production agent workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -21619,7 +20587,6 @@
"displayName": "Nex-N2-Mini",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -21638,7 +20605,6 @@
"displayName": "Nex-N2-Pro",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": false,
@@ -21657,7 +20623,6 @@
"displayName": "Hermes 3 405B Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-12-31",
@@ -21677,7 +20642,6 @@
"displayName": "Hermes 3 70B Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-12-31",
@@ -21697,7 +20661,6 @@
"displayName": "Hermes 4 405B",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2024-08-31",
@@ -21720,7 +20683,6 @@
"displayName": "Hermes 4 70B",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2024-08-31",
@@ -21743,7 +20705,6 @@
"displayName": "Nemotron 3 Nano 30B A3B",
"description": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -21762,7 +20723,6 @@
"displayName": "Nemotron 3 Nano 30B A3B (free)",
"description": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 256000,
"structuredOutput": false,
@@ -21782,7 +20742,6 @@
"displayName": "Nemotron 3 Nano Omni (free)",
"description": "Open Nemotron omni model combining reasoning with text, vision, and audio",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 65536,
"structuredOutput": false,
@@ -21802,7 +20761,6 @@
"displayName": "Nemotron 3 Super 120B A12B",
"description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -21825,7 +20783,6 @@
"displayName": "Nemotron 3 Super (free)",
"description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -21849,7 +20806,6 @@
"displayName": "Nemotron 3 Ultra 550B A55B",
"description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 512288,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -21872,7 +20828,6 @@
"displayName": "Nemotron 3 Ultra (free)",
"description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": false,
@@ -21896,7 +20851,6 @@
"displayName": "Nemotron 3.5 Content Safety (free)",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 8192,
"structuredOutput": false,
@@ -21916,7 +20870,6 @@
"displayName": "Nemotron 3.5 Lightning 30B A3B",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -21938,7 +20891,6 @@
"displayName": "Nemotron 3.5 Lightning (free)",
"description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": false,
@@ -21961,7 +20913,6 @@
"displayName": "Nemotron Nano 12B 2 VL (free)",
"description": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"structuredOutput": false,
@@ -21981,7 +20932,6 @@
"displayName": "Nemotron Nano 9B V2 (free)",
"description": "Compact Nemotron model for efficient reasoning and deployable AI agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -22001,7 +20951,6 @@
"displayName": "GPT-3.5-turbo",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 16385,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2021-09-01",
@@ -22021,7 +20970,6 @@
"displayName": "GPT-3.5 Turbo (older v0613)",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 4095,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2021-09-30",
@@ -22041,7 +20989,6 @@
"displayName": "GPT-3.5 Turbo 16k",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 16385,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2021-09-30",
@@ -22061,7 +21008,6 @@
"displayName": "GPT-3.5 Turbo Instruct",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 4095,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2021-09-30",
@@ -22081,7 +21027,6 @@
"displayName": "GPT-4",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 8191,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-11",
@@ -22101,7 +21046,6 @@
"displayName": "GPT-4 Turbo",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-12",
@@ -22121,7 +21065,6 @@
"displayName": "GPT-4 Turbo Preview",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-12-31",
@@ -22141,7 +21084,6 @@
"displayName": "GPT-4.1",
"description": "Long-lived GPT workhorse for coding, instruction following, and production apps",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1047576,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -22161,7 +21103,6 @@
"displayName": "GPT-4.1 mini",
"description": "Affordable GPT-4.1 lane for fast coding help and structured extraction",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1047576,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -22181,7 +21122,6 @@
"displayName": "GPT-4.1 nano",
"description": "Tiny GPT-4.1 option for classification, routing, and very high-volume tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1047576,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -22201,7 +21141,6 @@
"displayName": "GPT-4o",
"description": "Omni-era GPT for multimodal chat, practical coding, and general assistants",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-09",
@@ -22221,7 +21160,6 @@
"displayName": "GPT-4o (2024-05-13)",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 4096,
"knowledgeCutoff": "2023-09",
@@ -22241,7 +21179,6 @@
"displayName": "GPT-4o (2024-08-06)",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-09",
@@ -22261,7 +21198,6 @@
"displayName": "GPT-4o (2024-11-20)",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-09",
@@ -22281,7 +21217,6 @@
"displayName": "GPT-4o mini",
"description": "Small omni GPT for cheap multimodal assistance and production-scale traffic",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-09",
@@ -22301,7 +21236,6 @@
"displayName": "GPT-4o-mini (2024-07-18)",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-10-31",
@@ -22321,7 +21255,6 @@
"displayName": "GPT-5",
"description": "Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22345,7 +21278,6 @@
"displayName": "GPT-5 Image",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-10-01",
@@ -22365,7 +21297,6 @@
"displayName": "GPT-5 Image Mini",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -22384,7 +21315,6 @@
"displayName": "GPT-5 Mini",
"description": "Small GPT-5 for responsive agents, coding help, and everyday automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22408,7 +21338,6 @@
"displayName": "GPT-5 Nano",
"description": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22432,7 +21361,6 @@
"displayName": "GPT-5 Pro",
"description": "Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22456,7 +21384,6 @@
"displayName": "GPT-5.1",
"description": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22480,7 +21407,6 @@
"displayName": "GPT-5.1 Codex",
"description": "Codex GPT for repository edits, code review, and practical software agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22504,7 +21430,6 @@
"displayName": "GPT-5.1 Codex Max",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22528,7 +21453,6 @@
"displayName": "GPT-5.1 Codex mini",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22553,7 +21477,6 @@
"displayName": "GPT-5.2",
"description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22577,7 +21500,6 @@
"displayName": "GPT-5.2 Chat",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 32000,
"knowledgeCutoff": "2025-08-31",
@@ -22597,7 +21519,6 @@
"displayName": "GPT-5.2 Codex",
"description": "Code-specialist GPT for repository edits, reviews, and long-running software agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22621,7 +21542,6 @@
"displayName": "GPT-5.2 Pro",
"description": "Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22645,7 +21565,6 @@
"displayName": "GPT-5.3 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22669,7 +21588,6 @@
"displayName": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -22693,7 +21611,6 @@
"displayName": "GPT-5.4 Image 2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 272000,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -22715,7 +21632,6 @@
"displayName": "GPT-5.4 mini",
"description": "Strong small GPT for coding subagents, quick tool use, and high-volume work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22739,7 +21655,6 @@
"displayName": "GPT-5.4 nano",
"description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"inputLimit": 272000,
"maxOutputTokens": 128000,
@@ -22763,7 +21678,6 @@
"displayName": "GPT-5.4 Pro",
"description": "More exact GPT-5.4 tier for demanding professional reasoning and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -22787,7 +21701,6 @@
"displayName": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -22811,7 +21724,6 @@
"displayName": "GPT-5.5 Pro",
"description": "Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -22835,7 +21747,6 @@
"displayName": "GPT-5.6 Luna",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -22859,7 +21770,6 @@
"displayName": "GPT-5.6 Luna Pro",
"description": "Frontier GPT model for professional reasoning, coding, and multimodal work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -22883,7 +21793,6 @@
"displayName": "GPT-5.6 Sol",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -22907,7 +21816,6 @@
"displayName": "GPT-5.6 Sol Pro",
"description": "Frontier GPT model for professional reasoning, coding, and multimodal work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -22931,7 +21839,6 @@
"displayName": "GPT-5.6 Terra",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -22955,7 +21862,6 @@
"displayName": "GPT-5.6 Terra Pro",
"description": "Frontier GPT model for professional reasoning, coding, and multimodal work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"inputLimit": 922000,
"maxOutputTokens": 128000,
@@ -22979,7 +21885,6 @@
"displayName": "GPT Audio",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -22998,7 +21903,6 @@
"displayName": "GPT Audio Mini",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -23017,7 +21921,6 @@
"displayName": "GPT Chat Latest",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 400000,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -23036,7 +21939,6 @@
"displayName": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -23058,7 +21960,6 @@
"displayName": "GPT OSS 20B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -23080,7 +21981,6 @@
"displayName": "gpt-oss-20b (free)",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -23103,7 +22003,6 @@
"displayName": "gpt-oss-safeguard-20b",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -23125,7 +22024,6 @@
"displayName": "o1",
"description": "O-series reasoning model for hard analysis, math, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2023-09",
@@ -23148,7 +22046,6 @@
"displayName": "o1-pro",
"description": "O-series reasoning model for hard analysis, math, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2023-09",
@@ -23168,7 +22065,6 @@
"displayName": "o3",
"description": "Deliberate o-series reasoner for hard math, coding, and multi-step analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2024-05",
@@ -23191,7 +22087,6 @@
"displayName": "o3-mini",
"description": "Smaller o-series reasoner for economical coding, math, and planning tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2024-05",
@@ -23214,7 +22109,6 @@
"displayName": "o3 Mini High",
"description": "O-series reasoning model for hard analysis, math, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2023-10-31",
@@ -23237,7 +22131,6 @@
"displayName": "o3-pro",
"description": "High-effort o3 tier for difficult technical reasoning and careful answers",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2024-05",
@@ -23260,7 +22153,6 @@
"displayName": "o4-mini",
"description": "Fast o-series model for compact reasoning, coding, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2024-05",
@@ -23283,7 +22175,6 @@
"displayName": "o4 Mini High",
"description": "O-series reasoning model for hard analysis, math, coding, and planning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 100000,
"knowledgeCutoff": "2024-06-30",
@@ -23306,7 +22197,6 @@
"displayName": "Auto Router",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 2000000,
"maxOutputTokens": 2000000,
"structuredOutput": true,
@@ -23325,7 +22215,6 @@
"displayName": "Body Builder (beta)",
"description": "Preview model for early access evaluation, prototyping, and compatibility testing",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"structuredOutput": false,
@@ -23344,7 +22233,6 @@
"displayName": "Free Models Router",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"inputLimit": 200000,
"maxOutputTokens": 8000,
@@ -23365,7 +22253,6 @@
"displayName": "Fusion",
"description": "General-purpose chat model for instruction following, writing, and analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"structuredOutput": false,
@@ -23384,7 +22271,6 @@
"displayName": "Pareto Code Router",
"description": "Coding model for repository understanding, refactors, and agentic engineering tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 2000000,
"maxOutputTokens": 200000,
"structuredOutput": false,
@@ -23403,7 +22289,6 @@
"displayName": "Perceptron Mk1",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32768,
"maxOutputTokens": 8192,
"structuredOutput": true,
@@ -23422,7 +22307,6 @@
"displayName": "Sonar",
"description": "Sonar search model for current answers, retrieval, and citation-backed chat",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 127072,
"maxOutputTokens": 127072,
"structuredOutput": false,
@@ -23441,7 +22325,6 @@
"displayName": "Sonar Deep Research",
"description": "Sonar search model for current answers, retrieval, and citation-backed chat",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"structuredOutput": false,
@@ -23460,7 +22343,6 @@
"displayName": "Sonar Pro",
"description": "Advanced Sonar search model for deeper research and cited synthesis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 8000,
"structuredOutput": false,
@@ -23479,7 +22361,6 @@
"displayName": "Sonar Pro Search",
"description": "Advanced Sonar search model for deeper research and cited synthesis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 200000,
"maxOutputTokens": 8000,
"structuredOutput": true,
@@ -23498,7 +22379,6 @@
"displayName": "Sonar Reasoning Pro",
"description": "Web-grounded reasoning model for multi-step research and cited answers",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"structuredOutput": false,
@@ -23517,7 +22397,6 @@
"displayName": "Laguna S 2.1",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": false,
@@ -23536,7 +22415,6 @@
"displayName": "Laguna S 2.1 (free)",
"description": "Free provider route for experiments, demos, and cost-sensitive chat workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -23556,7 +22434,6 @@
"displayName": "Laguna XS 2.1",
"description": "Agentic coding model from Poolside in the XS size class for local deployment",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -23575,7 +22452,6 @@
"displayName": "Laguna XS 2.1 (free)",
"description": "Free provider route for experiments, demos, and cost-sensitive chat workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": false,
@@ -23595,7 +22471,6 @@
"displayName": "Qwen2.5 72B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32768,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2024-06-30",
@@ -23615,7 +22490,6 @@
"displayName": "Qwen2.5 7B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32768,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-06-30",
@@ -23635,7 +22509,6 @@
"displayName": "Qwen2.5 Coder 32B Instruct",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32768,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-06-30",
@@ -23655,7 +22528,6 @@
"displayName": "Qwen Plus",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-04",
@@ -23675,7 +22547,6 @@
"displayName": "Qwen Plus 0728",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -23695,7 +22566,6 @@
"displayName": "Qwen Plus 0728 (thinking)",
"description": "Qwen reasoning model for deliberate problem solving, math, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -23715,7 +22585,6 @@
"displayName": "Qwen2.5 VL 72B Instruct",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 128000,
"maxOutputTokens": 128000,
"knowledgeCutoff": "2024-06-30",
@@ -23735,7 +22604,6 @@
"displayName": "Qwen3 14B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-03-31",
@@ -23758,7 +22626,6 @@
"displayName": "Qwen3 235B-A22B",
"description": "Large open Qwen MoE for multilingual reasoning, coding, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2025-04",
@@ -23781,7 +22648,6 @@
"displayName": "Qwen3 235B A22B Instruct 2507",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-06-30",
@@ -23801,7 +22667,6 @@
"displayName": "Qwen3 235B A22B Thinking 2507",
"description": "Qwen reasoning model for deliberate problem solving, math, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-06-30",
@@ -23821,7 +22686,6 @@
"displayName": "Qwen3 30B A3B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"structuredOutput": false,
@@ -23843,7 +22707,6 @@
"displayName": "Qwen3 30B A3B Instruct 2507",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32000,
"knowledgeCutoff": "2025-06-30",
@@ -23863,7 +22726,6 @@
"displayName": "Qwen3 30B A3B Thinking 2507",
"description": "Qwen reasoning model for deliberate problem solving, math, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 81920,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-06-30",
@@ -23883,7 +22745,6 @@
"displayName": "Qwen3 32B",
"description": "Dense open Qwen model for self-hosted chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -23906,7 +22767,6 @@
"displayName": "Qwen3 8B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 8192,
"knowledgeCutoff": "2025-03-31",
@@ -23929,7 +22789,6 @@
"displayName": "Qwen3 Coder 480B A35B",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-06-30",
@@ -23949,7 +22808,6 @@
"displayName": "Qwen3-Coder 30B-A3B Instruct",
"description": "Smaller Qwen coder for efficient local agents and repo-level fixes",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-04",
@@ -23969,7 +22827,6 @@
"displayName": "Qwen3 Coder Flash",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -23989,7 +22846,6 @@
"displayName": "Qwen3 Coder Next",
"description": "Qwen coding model for software agents, repository edits, and code reasoning",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"knowledgeCutoff": "2025-09",
@@ -24009,7 +22865,6 @@
"displayName": "Qwen3 Coder Plus",
"description": "Hosted Qwen coder for software agents, repo edits, and long-context code",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -24029,7 +22884,6 @@
"displayName": "Qwen3 Max",
"description": "Flagship Qwen3 model for coding agents, complex reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -24049,7 +22903,6 @@
"displayName": "Qwen3 Max Thinking",
"description": "Qwen reasoning model for deliberate problem solving, math, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -24068,7 +22921,6 @@
"displayName": "Qwen3-Next 80B-A3B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -24088,7 +22940,6 @@
"displayName": "Qwen3-Next 80B-A3B (Thinking)",
"description": "Efficient Qwen thinking model for local reasoning, math, and coding agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -24108,7 +22959,6 @@
"displayName": "Qwen3 VL 235B A22B Instruct",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -24128,7 +22978,6 @@
"displayName": "Qwen3 VL 235B A22B Thinking",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -24148,7 +22997,6 @@
"displayName": "Qwen3 VL 30B A3B Instruct",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -24168,7 +23016,6 @@
"displayName": "Qwen3 VL 30B A3B Thinking",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-03-31",
@@ -24188,7 +23035,6 @@
"displayName": "Qwen3 VL 32B Instruct",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -24207,7 +23053,6 @@
"displayName": "Qwen3 VL 8B Instruct",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -24226,7 +23071,6 @@
"displayName": "Qwen3 VL 8B Thinking",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"structuredOutput": true,
@@ -24245,7 +23089,6 @@
"displayName": "Qwen3.5 122B-A10B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -24267,7 +23110,6 @@
"displayName": "Qwen3.5 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -24289,7 +23131,6 @@
"displayName": "Qwen3.5 35B-A3B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -24311,7 +23152,6 @@
"displayName": "Qwen3.5 397B-A17B",
"description": "Large open Qwen multimodal MoE for visual agents and long technical tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -24333,7 +23173,6 @@
"displayName": "Qwen3.5 9B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -24355,7 +23194,6 @@
"displayName": "Qwen3.5-Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -24377,7 +23215,6 @@
"displayName": "Qwen3.5 Plus 2026-02-15",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -24400,7 +23237,6 @@
"displayName": "Qwen3.5 Plus 2026-04-20",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -24422,7 +23258,6 @@
"displayName": "Qwen3.6 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -24444,7 +23279,6 @@
"displayName": "Qwen3.6 35B-A3B",
"description": "Open multimodal Qwen MoE for local agents that need vision, audio, and code",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -24466,7 +23300,6 @@
"displayName": "Qwen3.6 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -24488,7 +23321,6 @@
"displayName": "Qwen3.6 Max Preview",
"description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -24511,7 +23343,6 @@
"displayName": "Qwen3.6 Plus",
"description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-04",
@@ -24534,7 +23365,6 @@
"displayName": "Qwen3.7 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"inputLimit": 991000,
"maxOutputTokens": 65536,
@@ -24554,7 +23384,6 @@
"displayName": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -24576,7 +23405,6 @@
"displayName": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -24599,7 +23427,6 @@
"displayName": "Qwen3.8 2.4T A95B",
"description": "Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -24621,7 +23448,6 @@
"displayName": "Qwen3.8 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -24644,7 +23470,6 @@
"displayName": "Qwen3.8 Max",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -24666,7 +23491,6 @@
"displayName": "Reka Edge",
"description": "Multimodal model for analyzing text, images, documents, and rich media",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 16384,
"maxOutputTokens": 16384,
"structuredOutput": true,
@@ -24685,7 +23509,6 @@
"displayName": "Reka Flash 3",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 65536,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01-31",
@@ -24705,7 +23528,6 @@
"displayName": "Relace Apply 3",
"description": "General-purpose chat model for instruction following, writing, and analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 128000,
"structuredOutput": false,
@@ -24724,7 +23546,6 @@
"displayName": "Relace Search",
"description": "Tool-capable chat model for instruction following and agentic application workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 128000,
"structuredOutput": false,
@@ -24743,7 +23564,6 @@
"displayName": "Fugu Ultra",
"description": "Quality-first multi-agent model for hard research, analysis, and competitions",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -24765,7 +23585,6 @@
"displayName": "Sakana Namazu",
"description": "Multi-agent model for routing expert agents across complex analytical tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"structuredOutput": true,
@@ -24787,7 +23606,6 @@
"displayName": "Llama 3 8B Lunaris",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 8192,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-12-31",
@@ -24807,7 +23625,6 @@
"displayName": "Llama 3.1 Euryale 70B v2.2",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-12-31",
@@ -24827,7 +23644,6 @@
"displayName": "Llama 3.3 Euryale 70B",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2023-12-31",
@@ -24847,7 +23663,6 @@
"displayName": "Ox Alpha",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": false,
@@ -24870,7 +23685,6 @@
"displayName": "Step 3.5 Flash",
"description": "StepFun flash lane for quick multimodal reasoning and coding assistance",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2025-01",
@@ -24890,7 +23704,6 @@
"displayName": "Step 3.7 Flash",
"description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"inputLimit": 256000,
"maxOutputTokens": 256000,
@@ -24914,7 +23727,6 @@
"displayName": "Hunyuan A13B Instruct",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-03-31",
@@ -24934,7 +23746,6 @@
"displayName": "Hy-MT2-1.8B",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 8192,
"maxOutputTokens": 4096,
"structuredOutput": false,
@@ -24953,7 +23764,6 @@
"displayName": "Hy-MT2-30B-A3B",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 8192,
"maxOutputTokens": 4096,
"structuredOutput": true,
@@ -24972,7 +23782,6 @@
"displayName": "Hy3",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -24994,7 +23803,6 @@
"displayName": "Hy3 preview",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": false,
@@ -25016,7 +23824,6 @@
"displayName": "Cydonia 24B V4.1",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2024-04-30",
@@ -25036,7 +23843,6 @@
"displayName": "Rocinante 12B",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 65536,
"maxOutputTokens": 65536,
"knowledgeCutoff": "2024-04-30",
@@ -25056,7 +23862,6 @@
"displayName": "Skyfall 36B V2",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 32768,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2024-06-30",
@@ -25076,7 +23881,6 @@
"displayName": "UnslopNemo 12B",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1024000,
"maxOutputTokens": 1024000,
"knowledgeCutoff": "2024-04-30",
@@ -25096,7 +23900,6 @@
"displayName": "Inkling",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 262144,
"structuredOutput": false,
@@ -25118,7 +23921,6 @@
"displayName": "Inkling Small",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -25140,7 +23942,6 @@
"displayName": "ReMM SLERP 13B",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 6144,
"maxOutputTokens": 6144,
"knowledgeCutoff": "2023-06-30",
@@ -25160,7 +23961,6 @@
"displayName": "Solar Pro 3",
"description": "Flagship model for demanding analysis, coding, and production agent workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -25179,7 +23979,6 @@
"displayName": "Solar Pro 4",
"description": "Flagship model for demanding analysis, coding, and production agent workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 524288,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -25198,7 +23997,6 @@
"displayName": "Palmyra X5",
"description": "General-purpose chat model for instruction following, writing, and analysis",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1040000,
"maxOutputTokens": 8192,
"structuredOutput": false,
@@ -25217,7 +24015,6 @@
"displayName": "Grok 4.20",
"description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 2000000,
"maxOutputTokens": 2000000,
"knowledgeCutoff": "2025-09-01",
@@ -25237,7 +24034,6 @@
"displayName": "Grok 4.20 Multi-Agent",
"description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 2000000,
"maxOutputTokens": 2000000,
"knowledgeCutoff": "2025-09-01",
@@ -25260,7 +24056,6 @@
"displayName": "Grok 4.3",
"description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1000000,
"maxOutputTokens": 1000000,
"structuredOutput": true,
@@ -25282,7 +24077,6 @@
"displayName": "Grok 4.5",
"description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 500000,
"maxOutputTokens": 500000,
"structuredOutput": true,
@@ -25304,7 +24098,6 @@
"displayName": "Grok 4.6",
"description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 500000,
"maxOutputTokens": 500000,
"knowledgeCutoff": "2026-02-01",
@@ -25327,7 +24120,6 @@
"displayName": "Grok Build 0.1",
"description": "Fast Grok coding model tuned for agentic engineering and iterative edits",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 256000,
"structuredOutput": true,
@@ -25346,7 +24138,6 @@
"displayName": "MiMo-V2.5",
"description": "Open MiMo model for multimodal coding agents and long-context automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2024-12",
@@ -25369,7 +24160,6 @@
"displayName": "MiMo-V2.5-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1050000,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2024-12",
@@ -25392,7 +24182,6 @@
"displayName": "GLM-4.5",
"description": "Hybrid-reasoning GLM release that made the 4.5 line broadly useful",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 98304,
"knowledgeCutoff": "2025-04",
@@ -25415,7 +24204,6 @@
"displayName": "GLM-4.5-Air",
"description": "Lighter GLM-4.5 variant for fast coding assistance and cheaper agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 98304,
"knowledgeCutoff": "2025-04",
@@ -25438,7 +24226,6 @@
"displayName": "GLM-4.5V",
"description": "GLM vision model for visual reasoning, documents, and multimodal agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 65536,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -25461,7 +24248,6 @@
"displayName": "GLM-4.6",
"description": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -25481,7 +24267,6 @@
"displayName": "GLM-4.6V",
"description": "GLM vision model for visual reasoning, documents, and multimodal agents",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 131072,
"maxOutputTokens": 32768,
"knowledgeCutoff": "2025-04",
@@ -25501,7 +24286,6 @@
"displayName": "GLM-4.7",
"description": "Mature GLM model for dependable coding, reasoning, and structured agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 204800,
"maxOutputTokens": 131072,
"knowledgeCutoff": "2025-04",
@@ -25521,7 +24305,6 @@
"displayName": "GLM-4.7-Flash",
"description": "Budget GLM lane for fast coding help, routing, and everyday automation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 202752,
"maxOutputTokens": 16384,
"knowledgeCutoff": "2025-04",
@@ -25541,7 +24324,6 @@
"displayName": "GLM-5",
"description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 204800,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -25560,7 +24342,6 @@
"displayName": "GLM-5-Turbo",
"description": "Faster GLM-5 lane for coding agents that need lower latency",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 202752,
"maxOutputTokens": 131072,
"structuredOutput": false,
@@ -25579,7 +24360,6 @@
"displayName": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 204800,
"maxOutputTokens": 128000,
"structuredOutput": true,
@@ -25598,7 +24378,6 @@
"displayName": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": true,
@@ -25621,7 +24400,6 @@
"displayName": "GLM 5.2 (free)",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 256000,
"maxOutputTokens": 256000,
"structuredOutput": true,
@@ -25645,7 +24423,6 @@
"displayName": "GLM-5.3",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"structuredOutput": false,
@@ -25667,7 +24444,6 @@
"displayName": "GLM-5V-Turbo",
"description": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks",
"lifecycle": "active",
- "docsUrl": "https://openrouter.ai/models",
"contextWindow": 202752,
"maxOutputTokens": 131072,
"structuredOutput": false,
@@ -25688,7 +24464,6 @@
"displayName": "baidu/ERNIE-4.5-300B-A47B",
"description": "Tool-capable chat model for instruction following and agentic application workflows",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
"contextWindow": 131000,
"maxOutputTokens": 131000,
"structuredOutput": true,
@@ -25707,7 +24482,6 @@
"displayName": "ByteDance-Seed/Seed-OSS-36B-Instruct",
"description": "Tool-capable chat model for instruction following and agentic application workflows",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
"contextWindow": 262000,
"maxOutputTokens": 262000,
"structuredOutput": true,
@@ -25726,7 +24500,6 @@
"displayName": "deepseek-ai/DeepSeek-R1",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
"contextWindow": 164000,
"maxOutputTokens": 164000,
"structuredOutput": true,
@@ -25745,7 +24518,6 @@
"displayName": "deepseek-ai/DeepSeek-V3",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
"contextWindow": 164000,
"maxOutputTokens": 164000,
"structuredOutput": true,
@@ -25764,7 +24536,6 @@
"displayName": "deepseek-ai/DeepSeek-V3.1",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
"contextWindow": 164000,
"maxOutputTokens": 164000,
"structuredOutput": true,
@@ -25786,7 +24557,6 @@
"displayName": "deepseek-ai/DeepSeek-V3.1-Terminus",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
"contextWindow": 164000,
"maxOutputTokens": 164000,
"structuredOutput": true,
@@ -25808,7 +24578,6 @@
"displayName": "deepseek-ai/DeepSeek-V3.2",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
"contextWindow": 164000,
"maxOutputTokens": 164000,
"structuredOutput": true,
@@ -25830,7 +24599,6 @@
"displayName": "deepseek-ai/DeepSeek-V3.2-Exp",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
"contextWindow": 164000,
"maxOutputTokens": 164000,
"structuredOutput": true,
@@ -25852,7 +24620,6 @@
"displayName": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -25872,7 +24639,6 @@
"displayName": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
"contextWindow": 1000000,
"maxOutputTokens": 384000,
"knowledgeCutoff": "2025-05",
@@ -25892,7 +24658,6 @@
"displayName": "Gemma 4 26B A4B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
"contextWindow": 262144,
"maxOutputTokens": 262144,
"structuredOutput": true,
@@ -25911,7 +24676,6 @@
"displayName": "Gemma 4 31B IT",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"lifecycle": "active",
- "docsUrl": "https://cloud.siliconflow.com/models",
... 5095 lines suppressed ...
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@maka.apache.org
For additional commands, e-mail: commits-help@maka.apache.org