maka-agent 0.2.0-dev.35.20260915 → 0.2.0-dev.37.20260915
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +6 -0
- package/README.zh-CN.md +5 -0
- package/native/runtime-host-windows-task-launcher/prebuilds/win32-x64/maka-runtime-host-task-launcher.exe +0 -0
- package/node_modules/@maka/core/dist/model-metadata.generated.js +175 -116
- package/node_modules/@maka/core/dist/models-dev-projection.js +1 -0
- package/node_modules/@maka/core/dist/provider-registry.js +17 -0
- package/node_modules/@maka/eval/dist/harbor-maka-subject.js +13 -3
- package/node_modules/@maka/eval/dist/maka-artifacts.js +28 -14
- package/node_modules/@maka/eval/dist/maka-subject.js +28 -3
- package/node_modules/@maka/eval/harbor/relay_agent.py +42 -2
- package/node_modules/@maka/runtime/dist/ai-sdk-backend.js +0 -1
- package/node_modules/@maka/runtime/dist/ai-sdk-compaction.js +40 -53
- package/node_modules/@maka/runtime/dist/ai-sdk-turn.js +26 -29
- package/node_modules/@maka/runtime/dist/builtin-tools.js +20 -12
- package/node_modules/@maka/runtime/dist/runtime-kernel.js +1 -0
- package/node_modules/@maka/runtime/dist/telemetry/model-pricing.generated.js +144 -77
- package/node_modules/@maka/runtime/node_modules/@ai-sdk/code-mode/dist/run-code-mode.js +6 -19
- package/node_modules/@maka/runtime-host/dist/client/connect-or-spawn.js +24 -3
- package/node_modules/@maka/runtime-host/dist/client/connection.js +20 -2
- package/node_modules/@maka/runtime-host/dist/client/hosted-execution-target.js +27 -6
- package/node_modules/@maka/runtime-host/dist/client/hosted-execution.js +10 -28
- package/node_modules/@maka/runtime-host/dist/client/startup-error.js +1 -1
- package/node_modules/@maka/runtime-host/dist/execution-candidate-main.js +8 -1
- package/node_modules/@maka/runtime-host/dist/protocol/agent-graph.js +1 -11
- package/node_modules/@maka/runtime-host/dist/protocol/client-capability.js +2 -2
- package/node_modules/@maka/runtime-host/dist/protocol/codec.js +11 -0
- package/node_modules/@maka/runtime-host/dist/protocol/index.js +1 -1
- package/node_modules/@maka/runtime-host/dist/protocol/workhub-coordination.js +10 -2
- package/node_modules/@maka/runtime-host/dist/server/bootstrap-runtime-policy.js +65 -0
- package/node_modules/@maka/runtime-host/dist/server/execution-candidate.js +4 -1
- package/node_modules/@maka/runtime-host/dist/server/execution-composition-factory.js +9 -3
- package/node_modules/@maka/runtime-host/dist/server/execution-composition.js +11 -0
- package/node_modules/@maka/runtime-host/dist/server/hosted-execution-tool-profile.js +3 -15
- package/node_modules/@maka/runtime-host/dist/server/interactive-run-composer.js +9 -4
- package/node_modules/@maka/runtime-host/dist/server/message-coordinator.js +1 -2
- package/node_modules/@maka/runtime-host/dist/server/session-catalog-coordinator.js +4 -1
- package/node_modules/@maka/storage/dist/agent-run-store-contract.js +11 -8
- package/node_modules/@maka/storage/dist/agent-run-store.js +1 -1
- package/node_modules/@maka/storage/dist/execution-stores.js +1 -1
- package/node_modules/@maka/storage/dist/message-admission-store.js +5 -3
- package/node_modules/@maka/storage/dist/sqlite-session-metadata-store.js +14 -6
- package/package.json +1 -1
- package/node_modules/@maka/eval/dist/maka-runtime-policy.js +0 -42
|
@@ -1,6 +1,7 @@
|
|
|
1
1
|
export const GENERATED_MODELS_DEV_METADATA = {
|
|
2
2
|
"anthropic": {
|
|
3
3
|
"claude-fable-5": { "displayName": "Claude Fable 5", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
4
|
+
"claude-fable-5-1": { "displayName": "Claude Fable 5.1", "description": "Claude model for demanding reasoning and long-horizon agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "structuredOutput": true, "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
4
5
|
"claude-haiku-4-5": { "displayName": "Claude Haiku 4.5 (latest)", "description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-02-28", "structuredOutput": true, "lastUpdated": "2025-10-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
5
6
|
"claude-haiku-4-5-20251001": { "displayName": "Claude Haiku 4.5", "description": "Fast Claude model for responsive assistance, classification, and lightweight agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-02-28", "structuredOutput": true, "lastUpdated": "2025-10-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
6
7
|
"claude-opus-4-5": { "displayName": "Claude Opus 4.5 (latest)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2025-11-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
@@ -194,6 +195,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
194
195
|
"deepseek-v4-flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
195
196
|
"deepseek-v4-pro": { "displayName": "DeepSeek V4 Pro", "description": "Open MoE flagship with million-token context for coding and long agent runs", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
196
197
|
"deepseek-v4-pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
198
|
+
"deepseek-v4.1-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
197
199
|
"glm-5": { "displayName": "GLM-5", "description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2026-02-12", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
198
200
|
"glm-5.1": { "displayName": "GLM-5.1", "description": "Strong GLM coding model for agentic engineering, terminals, and repository generation", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-04-07", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
199
201
|
"glm-5.2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-06-13", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -212,7 +214,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
212
214
|
"qwen3.7-plus": { "displayName": "Qwen3.7 Plus", "description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-06-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
213
215
|
"qwen3.8-flash": { "displayName": "Qwen3.8 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
214
216
|
"qwen3.8-max": { "displayName": "Qwen3.8 Max", "description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-03", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
|
|
215
|
-
"qwen3.8-max-preview": { "displayName": "Qwen3.8 Max Preview", "description": "Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows", "lifecycle": "
|
|
217
|
+
"qwen3.8-max-preview": { "displayName": "Qwen3.8 Max Preview", "description": "Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows", "lifecycle": "deprecated", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-19", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
216
218
|
"wan2.7-image": { "displayName": "Wan2.7 Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 0, "lastUpdated": "2026-05-29", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
217
219
|
"wan2.7-image-pro": { "displayName": "Wan2.7 Image Pro", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 0, "lastUpdated": "2026-05-29", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
218
220
|
},
|
|
@@ -240,13 +242,13 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
240
242
|
"qwen3.7-plus": { "displayName": "Qwen3.7 Plus", "description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-06-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
241
243
|
"qwen3.8-flash": { "displayName": "Qwen3.8 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
242
244
|
"qwen3.8-max": { "displayName": "Qwen3.8 Max", "description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-03", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
|
|
243
|
-
"qwen3.8-max-preview": { "displayName": "Qwen3.8 Max Preview", "description": "Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows", "lifecycle": "
|
|
245
|
+
"qwen3.8-max-preview": { "displayName": "Qwen3.8 Max Preview", "description": "Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows", "lifecycle": "deprecated", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-19", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
244
246
|
"wan2.7-image": { "displayName": "Wan2.7 Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 0, "lastUpdated": "2026-05-29", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
245
247
|
"wan2.7-image-pro": { "displayName": "Wan2.7 Image Pro", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 0, "lastUpdated": "2026-05-29", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
246
248
|
},
|
|
247
249
|
"cerebras": {
|
|
248
|
-
"gemma-4-31b": { "displayName": "Gemma 4 31B IT", "description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning", "lifecycle": "beta", "contextWindow": 131072, "maxOutputTokens": 40960, "structuredOutput": true, "lastUpdated": "2026-07-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
249
250
|
"gpt-oss-120b": { "displayName": "GPT OSS 120B", "description": "Open GPT reasoning model for self-hosted agents and controllable deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 40960, "structuredOutput": true, "lastUpdated": "2026-06-10", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
251
|
+
"qwen-3.8-27b": { "displayName": "Qwen3.8 27B", "description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-09-03", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
250
252
|
},
|
|
251
253
|
"cohere": {
|
|
252
254
|
"c4ai-aya-expanse-32b": { "displayName": "Aya Expanse 32B", "description": "Open multilingual model optimized for generation across 23 languages", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4000, "lastUpdated": "2024-10-24", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -290,7 +292,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
290
292
|
"@cf/qwen/qwq-32b": { "displayName": "Qwq 32B", "description": "Qwen reasoning model for deliberate problem solving, math, and coding", "lifecycle": "active", "contextWindow": 24000, "maxOutputTokens": 24000, "knowledgeCutoff": "2024-04", "structuredOutput": false, "lastUpdated": "2025-03-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
291
293
|
"@cf/zai-org/glm-4.7-flash": { "displayName": "GLM-4.7-Flash", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
292
294
|
"@cf/zai-org/glm-5.2": { "displayName": "Glm 5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
293
|
-
"@cf/zai-org/glm-5.3": { "displayName": "Glm 5.3", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 1310720, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"]
|
|
295
|
+
"@cf/zai-org/glm-5.3": { "displayName": "Glm 5.3", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 1310720, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
294
296
|
"@cf/zai-org/glm-5.3-flash": { "displayName": "Glm 5.3 Flash", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
295
297
|
},
|
|
296
298
|
"deepinfra": {
|
|
@@ -304,8 +306,13 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
304
306
|
"deepseek-ai/DeepSeek-V3.2": { "displayName": "DeepSeek-V3.2", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 64000, "knowledgeCutoff": "2024-12", "structuredOutput": true, "lastUpdated": "2025-12-02", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
305
307
|
"deepseek-ai/DeepSeek-V4-Flash": { "displayName": "DeepSeek V4 Flash", "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
306
308
|
"deepseek-ai/DeepSeek-V4-Flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
309
|
+
"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
307
310
|
"deepseek-ai/DeepSeek-V4-Pro": { "displayName": "DeepSeek V4 Pro", "description": "Open MoE flagship with million-token context for coding and long agent runs", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
308
311
|
"deepseek-ai/DeepSeek-V4-Pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
312
|
+
"deepseek-ai/DeepSeek-V4.1-Flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
313
|
+
"google/gemma-3-12b-it": { "displayName": "Gemma 3 12B IT", "description": "Open multimodal Gemma instruction model for multilingual text generation and image understanding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-08", "structuredOutput": true, "lastUpdated": "2025-03-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
314
|
+
"google/gemma-3-27b-it": { "displayName": "Gemma 3 27B IT", "description": "Largest open Gemma 3 instruction model for multilingual text generation and visual understanding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-08", "structuredOutput": true, "lastUpdated": "2025-03-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
315
|
+
"google/gemma-3-4b-it": { "displayName": "Gemma 3 4B IT", "description": "Open multimodal Gemma instruction model for efficient text generation and image understanding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-08", "structuredOutput": true, "lastUpdated": "2025-03-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
309
316
|
"google/gemma-4-26B-A4B-it": { "displayName": "Gemma 4 26B A4B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
310
317
|
"google/gemma-4-31B-it": { "displayName": "Gemma 4 31B IT", "description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
311
318
|
"google/gemma-4-E4B-it": { "displayName": "Gemma 4 E4B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 8192, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
|
|
@@ -313,9 +320,9 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
313
320
|
"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "displayName": "Llama 4 Maverick 17B FP8", "description": "Open multimodal Llama model for strong reasoning and fast responses", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2025-04-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
314
321
|
"meta-llama/Llama-4-Scout-17B-16E-Instruct": { "displayName": "Llama 4 Scout 17B", "description": "Open multimodal Llama model for long-context analysis and efficient agents", "lifecycle": "active", "contextWindow": 327680, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2025-04-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
315
322
|
"MiniMaxAI/MiniMax-M2.5": { "displayName": "MiniMax M2.5", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "deprecated", "contextWindow": 196608, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
316
|
-
"MiniMaxAI/MiniMax-M2.7": { "displayName": "MiniMax-M2.7", "description": "Open MiniMax flagship for coding agents, office automation, and complex environments", "lifecycle": "
|
|
323
|
+
"MiniMaxAI/MiniMax-M2.7": { "displayName": "MiniMax-M2.7", "description": "Open MiniMax flagship for coding agents, office automation, and complex environments", "lifecycle": "deprecated", "contextWindow": 196608, "maxOutputTokens": 131072, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
317
324
|
"MiniMaxAI/MiniMax-M3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 512000, "structuredOutput": true, "lastUpdated": "2026-06-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
318
|
-
"moonshotai/Kimi-K2.5": { "displayName": "Kimi K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "
|
|
325
|
+
"moonshotai/Kimi-K2.5": { "displayName": "Kimi K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
319
326
|
"moonshotai/Kimi-K2.6": { "displayName": "Kimi K2.6", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-04", "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
320
327
|
"moonshotai/Kimi-K2.7-Code": { "displayName": "Kimi K2.7 Code", "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
321
328
|
"moonshotai/Kimi-K3": { "displayName": "Kimi K3", "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
@@ -340,68 +347,69 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
340
347
|
"Qwen/Qwen3.6-35B-A3B": { "displayName": "Qwen3.6 35B A3B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 81920, "structuredOutput": true, "lastUpdated": "2026-04-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
341
348
|
"Qwen/Qwen3.7-Max": { "displayName": "Qwen3.7 Max", "description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-05-21", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
342
349
|
"Qwen/Qwen3.8-2.4T-A95B": { "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", "contextWindow": 262144, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
343
|
-
"Qwen/Qwen3.8-27B": { "displayName": "Qwen3.8 27B", "description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
350
|
+
"Qwen/Qwen3.8-27B": { "displayName": "Qwen3.8 27B", "description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
351
|
+
"Qwen/Qwen3.8-Flash": { "displayName": "Qwen3.8 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
344
352
|
"Qwen/Qwen3.8-Max": { "displayName": "Qwen3.8 Max", "description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-03", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
|
|
345
353
|
"stepfun-ai/Step-3.7-Flash": { "displayName": "Step 3.7 Flash", "description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "knowledgeCutoff": "2026-03-01", "lastUpdated": "2026-05-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
346
|
-
"tencent/Hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens":
|
|
354
|
+
"tencent/Hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "inputLimit": 192000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-07-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
347
355
|
"thinkingmachines/Inkling": { "displayName": "Inkling", "description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 1048576, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
|
|
348
356
|
"thinkingmachines/Inkling-Small": { "displayName": "Inkling Small", "description": "Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-07-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
|
|
349
357
|
"XiaomiMiMo/MiMo-V2.5": { "displayName": "MiMo-V2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-12", "structuredOutput": true, "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
|
|
350
358
|
"XiaomiMiMo/MiMo-V2.5-Pro": { "displayName": "MiMo-V2.5-Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-12", "structuredOutput": true, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "audio"], "output": ["text"] } },
|
|
351
359
|
"zai-org/GLM-4.6": { "displayName": "GLM-4.6", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09-30", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
352
360
|
"zai-org/GLM-4.7": { "displayName": "GLM-4.7", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-12-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
353
|
-
"zai-org/GLM-4.7-Flash": { "displayName": "GLM-4.7-Flash", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "
|
|
354
|
-
"zai-org/GLM-5": { "displayName": "GLM-5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "
|
|
361
|
+
"zai-org/GLM-4.7-Flash": { "displayName": "GLM-4.7-Flash", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "deprecated", "contextWindow": 202752, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
362
|
+
"zai-org/GLM-5": { "displayName": "GLM-5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "deprecated", "contextWindow": 202752, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-12", "structuredOutput": true, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
355
363
|
"zai-org/GLM-5.1": { "displayName": "GLM-5.1", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-04-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
356
364
|
"zai-org/GLM-5.2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
357
365
|
"zai-org/GLM-5.3": { "displayName": "GLM-5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
358
366
|
"zai-org/GLM-5.3-Flash": { "displayName": "GLM-5.3-Flash", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
|
|
359
367
|
},
|
|
360
368
|
"deepseek": {
|
|
361
|
-
"deepseek-
|
|
362
|
-
"deepseek-v4-flash
|
|
369
|
+
"deepseek-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
370
|
+
"deepseek-v4-flash": { "displayName": "DeepSeek V4 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
371
|
+
"deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
363
372
|
"deepseek-v4-pro": { "displayName": "DeepSeek V4 Pro", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
364
373
|
},
|
|
365
374
|
"fireworks-ai": {
|
|
366
375
|
"accounts/fireworks/models/deepseek-v4-flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
376
|
+
"accounts/fireworks/models/deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
367
377
|
"accounts/fireworks/models/deepseek-v4-pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
378
|
+
"accounts/fireworks/models/deepseek-v4p1-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
368
379
|
"accounts/fireworks/models/glm-5p2": { "displayName": "GLM 5.2", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1048575, "maxOutputTokens": 131072, "lastUpdated": "2026-06-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
369
|
-
"accounts/fireworks/models/glm-5p3": { "displayName": "GLM 5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow":
|
|
370
|
-
"accounts/fireworks/models/glm-5p3-flash": { "displayName": "GLM 5.3 Flash", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow":
|
|
380
|
+
"accounts/fireworks/models/glm-5p3": { "displayName": "GLM 5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1048573, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-09-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
381
|
+
"accounts/fireworks/models/glm-5p3-flash": { "displayName": "GLM 5.3 Flash", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow": 1048573, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
|
|
371
382
|
"accounts/fireworks/models/gpt-oss-120b": { "displayName": "GPT OSS 120B", "description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "lastUpdated": "2026-06-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
372
383
|
"accounts/fireworks/models/inkling": { "displayName": "Inkling", "description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
|
|
373
384
|
"accounts/fireworks/models/kimi-k2p6": { "displayName": "Kimi K2.6", "description": "Kimi reasoning model for long-horizon research, planning, and tool use", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "lastUpdated": "2026-04-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
374
385
|
"accounts/fireworks/models/kimi-k2p7-code": { "displayName": "Kimi K2.7 Code", "description": "Kimi coding model for software agents, refactors, and repository reasoning", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "lastUpdated": "2026-06-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
375
386
|
"accounts/fireworks/models/kimi-k3": { "displayName": "Kimi K3", "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
376
387
|
"accounts/fireworks/models/minimax-m3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 512000, "maxOutputTokens": 512000, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
388
|
+
"accounts/fireworks/models/mistral-large-3-fp8": { "displayName": "Mistral Large 3 675B Instruct 2512", "description": "Mistral's largest general model for enterprise agents, coding, and multilingual reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
377
389
|
"accounts/fireworks/models/muse-glimmer-30b": { "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", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2026-01-04", "structuredOutput": true, "lastUpdated": "2026-08-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
378
390
|
"accounts/fireworks/models/nemotron-3-ultra-nvfp4": { "displayName": "Nemotron 3 Ultra 550B A55B", "description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 128000, "lastUpdated": "2026-06-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
379
391
|
"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": { "displayName": "Nemotron 3.5 Lightning 30B A3B", "description": "Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-08-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
380
392
|
"accounts/fireworks/models/qwen3p7-plus": { "displayName": "Qwen 3.7 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
393
|
+
"accounts/fireworks/models/qwen3p8-2p4t-a95b": { "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", "contextWindow": 262144, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
381
394
|
"accounts/fireworks/models/qwen3p8-max": { "displayName": "Qwen3.8 Max", "description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 131072, "lastUpdated": "2026-08-03", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
382
395
|
"accounts/fireworks/routers/glm-5p2-fast": { "displayName": "GLM 5.2 Fast", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 1048575, "maxOutputTokens": 131072, "lastUpdated": "2026-06-26", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
396
|
+
"accounts/fireworks/routers/glm-5p3-fast": { "displayName": "GLM 5.3 Fast", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1048572, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-09-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
383
397
|
"accounts/fireworks/routers/kimi-k3-fast": { "displayName": "Kimi K3 Fast", "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
384
398
|
},
|
|
385
399
|
"github-copilot": {
|
|
386
400
|
"claude-fable-5": { "displayName": "Claude Fable 5", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
401
|
+
"claude-fable-5.1": { "displayName": "Claude Fable 5.1", "description": "Claude model for demanding reasoning and long-horizon agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
387
402
|
"claude-haiku-4.5": { "displayName": "Claude Haiku 4.5 (latest)", "description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 136000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
388
|
-
"claude-opus-4.5": { "displayName": "Claude Opus 4.5 (latest)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 168000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-05", "lastUpdated": "2025-11-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
389
|
-
"claude-opus-4.6": { "displayName": "Claude Opus 4.6", "description": "High-end Claude for difficult coding, planning, and slower expert reasoning", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 168000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
390
403
|
"claude-opus-4.7": { "displayName": "Claude Opus 4.7", "description": "Stronger Opus tier for advanced software work and high-stakes reasoning", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 168000, "maxOutputTokens": 32000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
391
404
|
"claude-opus-4.8": { "displayName": "Claude Opus 4.8", "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 168000, "maxOutputTokens": 64000, "knowledgeCutoff": "2026-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
392
405
|
"claude-opus-5": { "displayName": "Claude Opus 5", "description": "Strongest Claude Opus model for coding, agents, and professional work", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 936000, "maxOutputTokens": 64000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-07-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
393
|
-
"claude-sonnet-4": { "displayName": "Claude Sonnet 4 (latest)", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 216000, "inputLimit": 128000, "maxOutputTokens": 16000, "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
394
|
-
"claude-sonnet-4.5": { "displayName": "Claude Sonnet 4.5 (latest)", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 168000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-07-31", "lastUpdated": "2025-09-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
395
406
|
"claude-sonnet-4.6": { "displayName": "Claude Sonnet 4.6", "description": "Claude workhorse for coding agents, careful analysis, and production cost control", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 168000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
396
407
|
"claude-sonnet-5": { "displayName": "Claude Sonnet 5", "description": "Everyday Claude agent model for coding, planning, browsing, and general work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
397
|
-
"gemini-3.1-pro-preview": { "displayName": "Gemini 3.1 Pro Preview", "description": "Reasoning-first Gemini preview for agentic coding and complex problem solving", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 936000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-02-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
398
408
|
"gemini-3.5-flash": { "displayName": "Gemini 3.5 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 128000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-05-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
399
409
|
"gemini-3.6-flash": { "displayName": "Gemini 3.6 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 936000, "maxOutputTokens": 64000, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-07-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
400
410
|
"gemini-3.7-flash": { "displayName": "Gemini 3.7 Flash", "description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 936000, "maxOutputTokens": 64000, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-08-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
401
|
-
"
|
|
411
|
+
"gemini-3.8-flash": { "displayName": "Gemini 3.8 Flash", "description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 936000, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
402
412
|
"gpt-5-mini": { "displayName": "GPT-5 Mini", "description": "Small GPT-5 for responsive agents, coding help, and everyday automation", "lifecycle": "active", "contextWindow": 264000, "inputLimit": 128000, "maxOutputTokens": 64000, "knowledgeCutoff": "2024-05-30", "structuredOutput": true, "lastUpdated": "2025-08-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
403
|
-
"gpt-5.2": { "displayName": "GPT-5.2", "description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
404
|
-
"gpt-5.2-codex": { "displayName": "GPT-5.2 Codex", "description": "Code-specialist GPT for repository edits, reviews, and long-running software agents", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
405
413
|
"gpt-5.3-codex": { "displayName": "GPT-5.3 Codex", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-02-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
406
414
|
"gpt-5.4": { "displayName": "GPT-5.4", "description": "Agent-ready GPT for coding and computer-use workflows at a lower cost", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
407
415
|
"gpt-5.4-mini": { "displayName": "GPT-5.4 mini", "description": "Strong small GPT for coding subagents, quick tool use, and high-volume work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
@@ -410,6 +418,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
410
418
|
"gpt-5.6-luna": { "displayName": "GPT-5.6 Luna", "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
411
419
|
"gpt-5.6-sol": { "displayName": "GPT-5.6 Sol", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
412
420
|
"gpt-5.6-terra": { "displayName": "GPT-5.6 Terra", "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
421
|
+
"gpt-6-astra": { "displayName": "GPT-6 Astra", "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-30", "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
413
422
|
"grok-4.5": { "displayName": "Grok 4.5", "description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk", "lifecycle": "active", "contextWindow": 500000, "inputLimit": 372000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
414
423
|
"grok-4.6": { "displayName": "Grok 4.6", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "lifecycle": "active", "contextWindow": 500000, "inputLimit": 372000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-01", "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
415
424
|
"kimi-k2.7-code": { "displayName": "Kimi K2.7 Code", "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 224000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
@@ -444,6 +453,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
444
453
|
"gemini-3.5-live-translate-preview": { "displayName": "Gemini 3.5 Live Translate Preview", "description": "Low-latency audio-to-audio model for real-time speech translation across 70+ languages", "lifecycle": "active", "contextWindow": 16384, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["audio", "text"] } },
|
|
445
454
|
"gemini-3.6-flash": { "displayName": "Gemini 3.6 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-07-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
446
455
|
"gemini-3.7-flash": { "displayName": "Gemini 3.7 Flash", "description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-08-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
456
|
+
"gemini-3.8-flash": { "displayName": "Gemini 3.8 Flash", "description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
447
457
|
"gemini-embedding-001": { "displayName": "Gemini Embedding 001", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 2048, "maxOutputTokens": 1, "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
448
458
|
"gemini-embedding-2": { "displayName": "Gemini Embedding 2", "description": "Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1, "knowledgeCutoff": "2025-11", "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "audio", "video", "pdf"], "output": ["text"] } },
|
|
449
459
|
"gemini-flash-latest": { "displayName": "Gemini Flash Latest", "description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-08-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
@@ -484,8 +494,13 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
484
494
|
"deepseek-ai/DeepSeek-V3.2": { "displayName": "DeepSeek-V3.2", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 65536, "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
485
495
|
"deepseek-ai/DeepSeek-V4-Flash": { "displayName": "DeepSeek V4 Flash", "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
486
496
|
"deepseek-ai/DeepSeek-V4-Flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
497
|
+
"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
487
498
|
"deepseek-ai/DeepSeek-V4-Pro": { "displayName": "DeepSeek V4 Pro", "description": "Open MoE flagship with million-token context for coding and long agent runs", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 393216, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
488
499
|
"deepseek-ai/DeepSeek-V4-Pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
500
|
+
"deepseek-ai/DeepSeek-V4.1-Flash": { "displayName": "DeepSeek V4.1 Flash", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
501
|
+
"google/gemma-3-12b-it": { "displayName": "Gemma 3 12B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-08", "structuredOutput": true, "lastUpdated": "2025-03-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
502
|
+
"google/gemma-3-27b-it": { "displayName": "Gemma 3 27B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-08", "structuredOutput": true, "lastUpdated": "2025-03-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
503
|
+
"google/gemma-3-4b-it": { "displayName": "Gemma 3 4B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-08", "structuredOutput": true, "lastUpdated": "2025-03-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
489
504
|
"google/gemma-4-26B-A4B-it": { "displayName": "Gemma 4 26B A4B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
490
505
|
"google/gemma-4-31B-it": { "displayName": "Gemma 4 31B IT", "description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
491
506
|
"meta-llama/Llama-3.1-8B-Instruct": { "displayName": "Llama-3.1-8B-Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-12", "structuredOutput": true, "lastUpdated": "2024-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -530,7 +545,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
530
545
|
"Qwen/Qwen3.8-27B": { "displayName": "Qwen3.8 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
531
546
|
"stepfun-ai/Step-3.5-Flash": { "displayName": "Step 3.5 Flash", "description": "StepFun flash lane for quick multimodal reasoning and coding assistance", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
532
547
|
"stepfun-ai/Step-3.7-Flash": { "displayName": "Step 3.7 Flash", "description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "knowledgeCutoff": "2026-03-01", "lastUpdated": "2026-05-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
533
|
-
"tencent/Hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens":
|
|
548
|
+
"tencent/Hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "inputLimit": 192000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-07-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
534
549
|
"thinkingmachines/Inkling": { "displayName": "Inkling", "description": "Multimodal model for analyzing text, images, documents, and rich media", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
535
550
|
"thinkingmachines/Inkling-Small": { "displayName": "Inkling Small", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 1048576, "lastUpdated": "2026-07-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
536
551
|
"XiaomiMiMo/MiMo-V2-Flash": { "displayName": "MiMo-V2-Flash", "description": "MiMo flash model for fast multimodal assistance and agent workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -552,7 +567,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
552
567
|
"kimi-coding-plan": {
|
|
553
568
|
"k3": { "displayName": "Kimi K3", "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-16", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
554
569
|
"k3-256k": { "displayName": "Kimi K3-256K", "description": "256K-context version of Kimi K3, reducing token consumption for shorter coding sessions", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-16", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
555
|
-
"kimi-for-coding": { "displayName": "
|
|
570
|
+
"kimi-for-coding": { "displayName": "kimi-for-coding", "description": "Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 32768, "lastUpdated": "2026-09-11", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
556
571
|
"kimi-for-coding-highspeed": { "displayName": "Kimi For Coding HighSpeed", "description": "Lower-latency Kimi Code variant for interactive edits and coding-agent loops", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
557
572
|
},
|
|
558
573
|
"MiniMax": {
|
|
@@ -619,12 +634,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
619
634
|
"zai-glm-5-2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "beta", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
620
635
|
},
|
|
621
636
|
"moonshot": {
|
|
622
|
-
"kimi-k2
|
|
623
|
-
"kimi-k2-
|
|
624
|
-
"kimi-k2-
|
|
625
|
-
"kimi-
|
|
626
|
-
|
|
627
|
-
|
|
637
|
+
"kimi-k2.6": { "displayName": "Kimi K2.6", "description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
638
|
+
"kimi-k2.7-code": { "displayName": "Kimi K2.7 Code", "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
639
|
+
"kimi-k2.7-code-highspeed": { "displayName": "Kimi K2.7 Code HighSpeed", "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
640
|
+
"kimi-k3": { "displayName": "Kimi K3", "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
641
|
+
},
|
|
642
|
+
"moonshot-global": {
|
|
628
643
|
"kimi-k2.6": { "displayName": "Kimi K2.6", "description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
629
644
|
"kimi-k2.7-code": { "displayName": "Kimi K2.7 Code", "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
630
645
|
"kimi-k2.7-code-highspeed": { "displayName": "Kimi K2.7 Code HighSpeed", "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
@@ -734,11 +749,14 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
734
749
|
"thinkingmachines/inkling": { "displayName": "Inkling", "description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 16384, "lastUpdated": "2026-07-15", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
|
|
735
750
|
"upstage/solar-10.7b-instruct": { "displayName": "solar-10.7b-instruct", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-04-10", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
736
751
|
"z-ai/glm-5.2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-06-13", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
752
|
+
"z-ai/glm-5.3-flash": { "displayName": "GLM-5.3-Flash", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
|
|
737
753
|
},
|
|
738
754
|
"ollama-cloud": {
|
|
739
755
|
"deepseek-v4-flash": { "displayName": "deepseek-v4-flash", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
740
756
|
"deepseek-v4-flash:0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
741
757
|
"deepseek-v4-pro": { "displayName": "deepseek-v4-pro", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
758
|
+
"deepseek-v4-pro:0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
759
|
+
"deepseek-v4.1-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
742
760
|
"gemma4:31b": { "displayName": "gemma4:31b", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
743
761
|
"glm-5.1": { "displayName": "glm-5.1", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 131072, "lastUpdated": "2026-04-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
744
762
|
"glm-5.2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 976000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -778,9 +796,9 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
778
796
|
"gpt-5-pro": { "displayName": "GPT-5 Pro", "description": "Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 272000, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-10-06", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
779
797
|
"gpt-5.1": { "displayName": "GPT-5.1", "description": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-11-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
780
798
|
"gpt-5.2": { "displayName": "GPT-5.2", "description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
781
|
-
"gpt-5.2-chat-latest": { "displayName": "GPT-5.2 Chat", "description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "lifecycle": "
|
|
799
|
+
"gpt-5.2-chat-latest": { "displayName": "GPT-5.2 Chat", "description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "lifecycle": "deprecated", "contextWindow": 128000, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
782
800
|
"gpt-5.2-pro": { "displayName": "GPT-5.2 Pro", "description": "Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": false, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
783
|
-
"gpt-5.3-chat-latest": { "displayName": "GPT-5.3 Chat (latest)", "description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "lifecycle": "
|
|
801
|
+
"gpt-5.3-chat-latest": { "displayName": "GPT-5.3 Chat (latest)", "description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "lifecycle": "deprecated", "contextWindow": 128000, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-03", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
784
802
|
"gpt-5.3-codex": { "displayName": "GPT-5.3 Codex", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-02-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
785
803
|
"gpt-5.3-codex-spark": { "displayName": "GPT-5.3 Codex Spark", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 128000, "inputLimit": 100000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-02-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
786
804
|
"gpt-5.4": { "displayName": "GPT-5.4", "description": "Agent-ready GPT for coding and computer-use workflows at a lower cost", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
@@ -793,6 +811,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
793
811
|
"gpt-5.6-luna": { "displayName": "GPT-5.6 Luna", "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
794
812
|
"gpt-5.6-sol": { "displayName": "GPT-5.6 Sol", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
795
813
|
"gpt-5.6-terra": { "displayName": "GPT-5.6 Terra", "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
814
|
+
"gpt-6-astra": { "displayName": "GPT-6 Astra", "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-30", "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
796
815
|
"gpt-image-1": { "displayName": "gpt-image-1", "description": "OpenAI image model for production generation, edits, and brand-safe visual workflows", "lifecycle": "deprecated", "contextWindow": 0, "inputLimit": 0, "maxOutputTokens": 0, "lastUpdated": "2025-04-24", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["image"] } },
|
|
797
816
|
"gpt-image-1-mini": { "displayName": "gpt-image-1-mini", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "inputLimit": 0, "maxOutputTokens": 0, "lastUpdated": "2025-09-26", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
|
|
798
817
|
"gpt-image-1.5": { "displayName": "gpt-image-1.5", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "inputLimit": 0, "maxOutputTokens": 0, "lastUpdated": "2025-11-25", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
|
|
@@ -812,6 +831,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
812
831
|
"big-pickle": { "displayName": "Big Pickle", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 160000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-10-17", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
813
832
|
"claude-3-5-haiku": { "displayName": "Claude Haiku 3.5", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 200000, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-07-31", "lastUpdated": "2024-10-22", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
814
833
|
"claude-fable-5": { "displayName": "Claude Fable 5", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
834
|
+
"claude-fable-5-1": { "displayName": "Claude Fable 5.1", "description": "Claude model for demanding reasoning and long-horizon agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
815
835
|
"claude-haiku-4-5": { "displayName": "Claude Haiku 4.5", "description": "Fast Claude model for responsive assistance, classification, and lightweight agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
816
836
|
"claude-opus-4-1": { "displayName": "Claude Opus 4.1", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "deprecated", "contextWindow": 200000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
817
837
|
"claude-opus-4-5": { "displayName": "Claude Opus 4.5", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-11-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
@@ -825,6 +845,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
825
845
|
"claude-sonnet-5": { "displayName": "Claude Sonnet 5", "description": "Everyday Claude agent model for coding, planning, browsing, and general work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
826
846
|
"deepseek-v4-flash": { "displayName": "DeepSeek V4 Flash", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
827
847
|
"deepseek-v4-flash-free": { "displayName": "DeepSeek V4 Flash Free", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "deprecated", "contextWindow": 200000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
848
|
+
"deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
828
849
|
"deepseek-v4-pro": { "displayName": "DeepSeek V4 Pro", "description": "Open MoE flagship with million-token context for coding and long agent runs", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
829
850
|
"gemini-3-flash": { "displayName": "Gemini 3 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-12-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
830
851
|
"gemini-3-pro": { "displayName": "Gemini 3 Pro", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-11-18", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
@@ -833,6 +854,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
833
854
|
"gemini-3.5-flash-lite": { "displayName": "Gemini 3.5 Flash Lite", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-07-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
834
855
|
"gemini-3.6-flash": { "displayName": "Gemini 3.6 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-07-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
835
856
|
"gemini-3.7-flash": { "displayName": "Gemini 3.7 Flash", "description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-08-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
857
|
+
"gemini-3.8-flash": { "displayName": "Gemini 3.8 Flash", "description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
836
858
|
"glm-4.6": { "displayName": "GLM-4.6", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
837
859
|
"glm-4.7": { "displayName": "GLM-4.7", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
838
860
|
"glm-4.7-free": { "displayName": "GLM-4.7 Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -840,6 +862,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
840
862
|
"glm-5-free": { "displayName": "GLM-5 Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-11", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
841
863
|
"glm-5.1": { "displayName": "GLM-5.1", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
842
864
|
"glm-5.2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
865
|
+
"glm-5.3": { "displayName": "GLM-5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
866
|
+
"glm-5.3-flash": { "displayName": "GLM-5.3-Flash", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
|
|
843
867
|
"gpt-5": { "displayName": "GPT-5", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-08-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
844
868
|
"gpt-5-codex": { "displayName": "GPT-5 Codex", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-09-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
845
869
|
"gpt-5-nano": { "displayName": "GPT-5 Nano", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-05-30", "structuredOutput": true, "lastUpdated": "2025-08-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
@@ -860,11 +884,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
860
884
|
"gpt-5.6-luna": { "displayName": "GPT-5.6 Luna", "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
861
885
|
"gpt-5.6-sol": { "displayName": "GPT-5.6 Sol (50% Off)", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
862
886
|
"gpt-5.6-terra": { "displayName": "GPT-5.6 Terra", "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
887
|
+
"gpt-6-astra": { "displayName": "GPT-6 Astra", "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-30", "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
863
888
|
"grok-4.5": { "displayName": "Grok 4.5", "description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
864
889
|
"grok-4.6": { "displayName": "Grok 4.6", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "knowledgeCutoff": "2026-02-01", "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
865
890
|
"grok-build-0.1": { "displayName": "Grok Build 0.1", "description": "Fast Grok coding model tuned for agentic engineering and iterative edits", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "structuredOutput": true, "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
866
891
|
"grok-code": { "displayName": "Grok Code Fast 1", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 256000, "maxOutputTokens": 256000, "lastUpdated": "2025-08-20", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
867
|
-
"hy3-free": { "displayName": "Hy3 Free", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "deprecated", "contextWindow": 190000, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-07-06", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
892
|
+
"hy3-free": { "displayName": "Hy3 Free", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "deprecated", "contextWindow": 190000, "inputLimit": 192000, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-07-06", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
868
893
|
"hy3-preview-free": { "displayName": "Hy3 preview Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-04-20", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
869
894
|
"kimi-k2": { "displayName": "Kimi K2", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
870
895
|
"kimi-k2-thinking": { "displayName": "Kimi K2 Thinking", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -892,6 +917,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
892
917
|
"minimax-m3-free": { "displayName": "MiniMax-M3 Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 200000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-31", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
893
918
|
"muse-spark-1.2": { "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", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
894
919
|
"muse-spark-1.2-contributor-free": { "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", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-05", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
920
|
+
"muse-spark-1.3": { "displayName": "Muse Spark 1.3", "description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
921
|
+
"muse-spark-1.3-contributor-free": { "displayName": "Muse Spark 1.3 Free", "description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
895
922
|
"nemotron-3-super-free": { "displayName": "Nemotron 3 Super Free", "description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02", "lastUpdated": "2026-03-11", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
896
923
|
"nemotron-3-ultra-free": { "displayName": "Nemotron 3 Ultra Free", "description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02", "lastUpdated": "2026-06-04", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
897
924
|
"nemotron-3.5-lightning-free": { "displayName": "Nemotron 3.5 Lightning Free", "description": "Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-08-11", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -908,15 +935,16 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
908
935
|
"deepseek-v4-flash": { "displayName": "DeepSeek V4 Flash", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
909
936
|
"deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
910
937
|
"deepseek-v4-pro": { "displayName": "DeepSeek V4 Pro (New)", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
938
|
+
"deepseek-v4.1-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
911
939
|
"glm-5": { "displayName": "GLM-5", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 202752, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
912
940
|
"glm-5.1": { "displayName": "GLM-5.1", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
913
941
|
"glm-5.2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
914
942
|
"glm-5.3": { "displayName": "GLM-5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
915
|
-
"glm-5.3-flash": { "displayName": "GLM-5.3-Flash
|
|
943
|
+
"glm-5.3-flash": { "displayName": "GLM-5.3-Flash", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
|
|
916
944
|
"gpt-5.6-luna": { "displayName": "GPT-5.6 Luna", "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
917
945
|
"grok-4.5": { "displayName": "Grok 4.5", "description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk", "lifecycle": "deprecated", "contextWindow": 500000, "maxOutputTokens": 500000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
918
946
|
"grok-4.6": { "displayName": "Grok 4.6", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "knowledgeCutoff": "2026-02-01", "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
919
|
-
"hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens":
|
|
947
|
+
"hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 192000, "maxOutputTokens": 128000, "lastUpdated": "2026-07-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
920
948
|
"hy4-preview": { "displayName": "Hy4 preview", "description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.", "lifecycle": "active", "contextWindow": 1024000, "maxOutputTokens": 64000, "lastUpdated": "2026-08-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
921
949
|
"kimi-k2.5": { "displayName": "Kimi K2.5", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2024-10", "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
922
950
|
"kimi-k2.6": { "displayName": "Kimi K2.6", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2024-10", "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
@@ -931,6 +959,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
931
959
|
"minimax-m2.7": { "displayName": "MiniMax-M2.7", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
932
960
|
"minimax-m3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-31", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
933
961
|
"muse-spark-1.2-contributor": { "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", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
962
|
+
"muse-spark-1.3-contributor": { "displayName": "Muse Spark 1.3 Contributor", "description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
963
|
+
"omen-alpha": { "displayName": "Omen Alpha", "description": "oH man anothEr aLPha ModEl", "lifecycle": "deprecated", "contextWindow": 500000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
934
964
|
"ox-alpha-free": { "displayName": "Ox Alpha Free (Unlimited)", "description": "Stealth reasoning model for coding, agentic tasks, and tool use", "lifecycle": "deprecated", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-21", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
935
965
|
"qwen3.5-plus": { "displayName": "Qwen3.5 Plus", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
936
966
|
"qwen3.6-plus": { "displayName": "Qwen3.6 Plus", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
@@ -941,17 +971,23 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
941
971
|
},
|
|
942
972
|
"openrouter": {
|
|
943
973
|
"~anthropic/claude-fable-latest": { "displayName": "Claude Fable Latest", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
944
|
-
"~anthropic/claude-haiku-latest": { "displayName": "
|
|
974
|
+
"~anthropic/claude-haiku-latest": { "displayName": "Claude Haiku Latest", "description": "Fast Claude model for responsive assistance, classification, and lightweight agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
945
975
|
"~anthropic/claude-opus-latest": { "displayName": "Claude Opus Latest", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
946
|
-
"~anthropic/claude-sonnet-latest": { "displayName": "
|
|
976
|
+
"~anthropic/claude-sonnet-latest": { "displayName": "Claude Sonnet Latest", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
977
|
+
"~deepseek/deepseek-flash-latest": { "displayName": "DeepSeek Flash Latest", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-09-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
978
|
+
"~deepseek/deepseek-pro-latest": { "displayName": "DeepSeek Pro Latest", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-09-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
947
979
|
"~deepseek/deepseek-v4-flash-latest": { "displayName": "DeepSeek V4 Flash Latest", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 393216, "structuredOutput": true, "lastUpdated": "2026-08-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
948
|
-
"~google/gemini-flash-latest": { "displayName": "
|
|
949
|
-
"~google/gemini-pro-latest": { "displayName": "
|
|
950
|
-
"~moonshotai/kimi-latest": { "displayName": "
|
|
951
|
-
"~openai/gpt-latest": { "displayName": "
|
|
952
|
-
"~openai/gpt-
|
|
980
|
+
"~google/gemini-flash-latest": { "displayName": "Gemini Flash Latest", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01-01", "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
981
|
+
"~google/gemini-pro-latest": { "displayName": "Gemini Pro Latest", "description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["audio", "pdf", "image", "text", "video"], "output": ["text"] } },
|
|
982
|
+
"~moonshotai/kimi-latest": { "displayName": "Kimi Latest", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
983
|
+
"~openai/gpt-astra-latest": { "displayName": "GPT Astra Latest", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-09-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
|
|
984
|
+
"~openai/gpt-luna-latest": { "displayName": "GPT Luna Latest", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-09-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
|
|
985
|
+
"~openai/gpt-mini-latest": { "displayName": "GPT Mini Latest", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 400000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
|
|
986
|
+
"~openai/gpt-sol-latest": { "displayName": "GPT Sol Latest", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-09-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
|
|
987
|
+
"~openai/gpt-terra-latest": { "displayName": "GPT Terra Latest", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-09-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
|
|
953
988
|
"~x-ai/grok-latest": { "displayName": "Grok Latest", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 450000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
954
|
-
"~z-ai/glm-latest": { "displayName": "GLM Latest", "description": "
|
|
989
|
+
"~z-ai/glm-flash-latest": { "displayName": "GLM Flash Latest", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
990
|
+
"~z-ai/glm-latest": { "displayName": "GLM Latest", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
955
991
|
"aion-labs/aion-2.0": { "displayName": "Aion-2.0", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-02-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
956
992
|
"aion-labs/aion-3.0": { "displayName": "Aion-3.0", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
957
993
|
"aion-labs/aion-3.0-mini": { "displayName": "Aion-3.0-Mini", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -964,17 +1000,15 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
964
1000
|
"anthracite-org/magnum-v4-72b": { "displayName": "Magnum v4 72B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-06-30", "structuredOutput": true, "lastUpdated": "2024-10-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
965
1001
|
"anthropic/claude-3-haiku": { "displayName": "Claude 3 Haiku", "description": "Fast Claude model for responsive assistance, classification, and lightweight agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-08-31", "structuredOutput": false, "lastUpdated": "2024-03-13", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
966
1002
|
"anthropic/claude-fable-5": { "displayName": "Claude Fable 5", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "structuredOutput": true, "lastUpdated": "2026-06-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1003
|
+
"anthropic/claude-fable-5.1": { "displayName": "Claude Fable 5.1", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "structuredOutput": true, "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
967
1004
|
"anthropic/claude-haiku-4.5": { "displayName": "Claude Haiku 4.5 (latest)", "description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-02-28", "structuredOutput": true, "lastUpdated": "2025-10-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
968
1005
|
"anthropic/claude-opus-4": { "displayName": "Claude Opus 4", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-01-31", "structuredOutput": false, "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "pdf"], "output": ["text"] } },
|
|
969
1006
|
"anthropic/claude-opus-4.1": { "displayName": "Claude Opus 4.1 (latest)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-03-31", "structuredOutput": false, "lastUpdated": "2025-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
970
1007
|
"anthropic/claude-opus-4.5": { "displayName": "Claude Opus 4.5 (latest)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2025-11-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
971
1008
|
"anthropic/claude-opus-4.6": { "displayName": "Claude Opus 4.6", "description": "High-end Claude for difficult coding, planning, and slower expert reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-05-31", "structuredOutput": true, "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
972
1009
|
"anthropic/claude-opus-4.7": { "displayName": "Claude Opus 4.7", "description": "Stronger Opus tier for advanced software work and high-stakes reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "structuredOutput": true, "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
973
|
-
"anthropic/claude-opus-4.7-fast": { "displayName": "Claude Opus 4.7 (Fast)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "structuredOutput": true, "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
974
1010
|
"anthropic/claude-opus-4.8": { "displayName": "Claude Opus 4.8", "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01", "structuredOutput": true, "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
975
|
-
"anthropic/claude-opus-4.8-fast": { "displayName": "Claude Opus 4.8 (Fast)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01", "structuredOutput": true, "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
976
1011
|
"anthropic/claude-opus-5": { "displayName": "Claude Opus 5", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-07-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
977
|
-
"anthropic/claude-opus-5-fast": { "displayName": "Claude Opus 5 (Fast)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-07-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
978
1012
|
"anthropic/claude-sonnet-4": { "displayName": "Claude Sonnet 4", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-31", "structuredOutput": false, "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "pdf"], "output": ["text"] } },
|
|
979
1013
|
"anthropic/claude-sonnet-4.5": { "displayName": "Claude Sonnet 4.5 (latest)", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-07-31", "structuredOutput": true, "lastUpdated": "2025-09-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
980
1014
|
"anthropic/claude-sonnet-4.6": { "displayName": "Claude Sonnet 4.6", "description": "Claude workhorse for coding agents, careful analysis, and production cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
@@ -996,8 +1030,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
996
1030
|
"cohere/north-mini-code:free": { "displayName": "North Mini Code (free)", "description": "Cohere coding model for practical software engineering and agentic edits", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 64000, "structuredOutput": false, "lastUpdated": "2026-06-17", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
997
1031
|
"deepseek/deepseek-chat": { "displayName": "DeepSeek Chat", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 16000, "knowledgeCutoff": "2025-09", "structuredOutput": true, "lastUpdated": "2026-02-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
998
1032
|
"deepseek/deepseek-chat-v3-0324": { "displayName": "DeepSeek V3 0324", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 147456, "knowledgeCutoff": "2024-07-31", "structuredOutput": true, "lastUpdated": "2025-03-24", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
999
|
-
"deepseek/deepseek-chat-v3.1": { "displayName": "DeepSeek V3.1", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens":
|
|
1000
|
-
"deepseek/deepseek-r1": { "displayName": "DeepSeek-R1", "description": "Classic open reasoning model for transparent math, coding, and deliberate problem solving", "lifecycle": "active", "contextWindow": 64000, "maxOutputTokens": 16000, "knowledgeCutoff": "2024-07", "structuredOutput":
|
|
1033
|
+
"deepseek/deepseek-chat-v3.1": { "displayName": "DeepSeek V3.1", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-08-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1034
|
+
"deepseek/deepseek-r1": { "displayName": "DeepSeek-R1", "description": "Classic open reasoning model for transparent math, coding, and deliberate problem solving", "lifecycle": "active", "contextWindow": 64000, "maxOutputTokens": 16000, "knowledgeCutoff": "2024-07", "structuredOutput": false, "lastUpdated": "2025-05-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1001
1035
|
"deepseek/deepseek-r1-0528": { "displayName": "R1 0528", "description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-05-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1002
1036
|
"deepseek/deepseek-r1-distill-llama-70b": { "displayName": "R1 Distill Llama 70B", "description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 7372, "knowledgeCutoff": "2024-07-31", "structuredOutput": false, "lastUpdated": "2025-01-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1003
1037
|
"deepseek/deepseek-v3.1-terminus": { "displayName": "DeepSeek V3.1 Terminus", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-09-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -1005,21 +1039,21 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1005
1039
|
"deepseek/deepseek-v3.2-exp": { "displayName": "DeepSeek V3.2 Exp", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-07-31", "structuredOutput": true, "lastUpdated": "2025-09-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1006
1040
|
"deepseek/deepseek-v4-flash": { "displayName": "DeepSeek V4 Flash", "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1007
1041
|
"deepseek/deepseek-v4-flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 943718, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1008
|
-
"deepseek/deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens":
|
|
1042
|
+
"deepseek/deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1009
1043
|
"deepseek/deepseek-v4-pro": { "displayName": "DeepSeek V4 Pro", "description": "Open MoE flagship with million-token context for coding and long agent runs", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 393216, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1010
1044
|
"deepseek/deepseek-v4-pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1045
|
+
"deepseek/deepseek-v4.1-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1011
1046
|
"dots-studio/dots-3-note-preview:free": { "displayName": "Dots3-Note Preview (free)", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 512000, "maxOutputTokens": 460800, "structuredOutput": true, "lastUpdated": "2026-08-14", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1012
1047
|
"google/gemini-2.5-flash": { "displayName": "Gemini 2.5 Flash", "description": "Fast Gemini workhorse for multimodal apps where latency and price matter", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65535, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-06-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video", "pdf"], "output": ["text"] } },
|
|
1013
1048
|
"google/gemini-2.5-flash-image": { "displayName": "Nano Banana", "description": "Nano Banana image model for fast generation, edits, and character-consistent assets", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-06", "structuredOutput": true, "lastUpdated": "2025-08-26", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
|
|
1014
1049
|
"google/gemini-2.5-flash-lite": { "displayName": "Gemini 2.5 Flash-Lite", "description": "Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65535, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-06-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video", "pdf"], "output": ["text"] } },
|
|
1015
1050
|
"google/gemini-2.5-pro": { "displayName": "Gemini 2.5 Pro", "description": "Google's proven reasoning model for coding, math, and multimodal analysis", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-06-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio", "video", "pdf"], "output": ["text"] } },
|
|
1016
1051
|
"google/gemini-2.5-pro-preview": { "displayName": "Gemini 2.5 Pro Preview 06-05", "description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01-31", "structuredOutput": true, "lastUpdated": "2025-06-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["pdf", "image", "text", "audio"], "output": ["text"] } },
|
|
1017
|
-
"google/gemini-2.5-pro-preview-05-06": { "displayName": "Gemini 2.5 Pro Preview 05-06", "description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65535, "knowledgeCutoff": "2025-01-31", "structuredOutput": true, "lastUpdated": "2025-05-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf", "audio", "video"], "output": ["text"] } },
|
|
1018
1052
|
"google/gemini-3-flash-preview": { "displayName": "Gemini 3 Flash Preview", "description": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-12-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
1019
1053
|
"google/gemini-3-pro-image": { "displayName": "Nano Banana Pro", "description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
|
|
1020
|
-
"google/gemini-3-pro-image-preview": { "displayName": "Nano Banana Pro", "description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-11-20", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
|
|
1054
|
+
"google/gemini-3-pro-image-preview": { "displayName": "Nano Banana Pro Preview", "description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-11-20", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
|
|
1021
1055
|
"google/gemini-3.1-flash-image": { "displayName": "Nano Banana 2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["minimal", "high"], "toggle": true }, "modalities": { "input": ["image", "text"], "output": ["text", "image"] } },
|
|
1022
|
-
"google/gemini-3.1-flash-image-preview": { "displayName": "Nano Banana 2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 58982, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-02-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["minimal", "high"], "toggle": true }, "modalities": { "input": ["image", "text"], "output": ["text", "image"] } },
|
|
1056
|
+
"google/gemini-3.1-flash-image-preview": { "displayName": "Nano Banana 2 Preview", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 58982, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-02-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["minimal", "high"], "toggle": true }, "modalities": { "input": ["image", "text"], "output": ["text", "image"] } },
|
|
1023
1057
|
"google/gemini-3.1-flash-lite": { "displayName": "Gemini 3.1 Flash Lite", "description": "Low-latency Gemini model for high-volume multimodal and agent workloads", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-05-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
1024
1058
|
"google/gemini-3.1-flash-lite-image": { "displayName": "Nano Banana 2 Lite", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 58982, "knowledgeCutoff": "2025-01", "structuredOutput": false, "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["minimal", "high"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
|
|
1025
1059
|
"google/gemini-3.1-flash-lite-preview": { "displayName": "Gemini 3.1 Flash Lite Preview", "description": "Low-latency Gemini model for high-volume multimodal and agent workloads", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-03-03", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
@@ -1029,11 +1063,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1029
1063
|
"google/gemini-3.5-flash-lite": { "displayName": "Gemini 3.5 Flash Lite", "description": "Low-latency Gemini model for high-volume multimodal and agent workloads", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-07-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
1030
1064
|
"google/gemini-3.6-flash": { "displayName": "Gemini 3.6 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-07-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
1031
1065
|
"google/gemini-3.7-flash": { "displayName": "Gemini 3.7 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-08-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
1066
|
+
"google/gemini-3.8-flash": { "displayName": "Gemini 3.8 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
|
|
1032
1067
|
"google/gemma-2-27b-it": { "displayName": "Gemma 2 27B", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 2048, "knowledgeCutoff": "2024-06-30", "structuredOutput": true, "lastUpdated": "2024-07-13", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1033
|
-
"google/gemma-3-12b-it": { "displayName": "Gemma 3 12B", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-08
|
|
1034
|
-
"google/gemma-3-27b-it": { "displayName": "Gemma 3 27B", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "knowledgeCutoff": "2024-08
|
|
1035
|
-
"google/gemma-3-4b-it": { "displayName": "Gemma 3 4B", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-08
|
|
1036
|
-
"google/gemma-4-26b-a4b-it": { "displayName": "Gemma 4 26B A4B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens":
|
|
1068
|
+
"google/gemma-3-12b-it": { "displayName": "Gemma 3 12B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-08", "structuredOutput": true, "lastUpdated": "2025-03-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1069
|
+
"google/gemma-3-27b-it": { "displayName": "Gemma 3 27B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "knowledgeCutoff": "2024-08", "structuredOutput": true, "lastUpdated": "2025-03-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1070
|
+
"google/gemma-3-4b-it": { "displayName": "Gemma 3 4B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-08", "structuredOutput": true, "lastUpdated": "2025-03-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1071
|
+
"google/gemma-4-26b-a4b-it": { "displayName": "Gemma 4 26B A4B IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "video"], "output": ["text"] } },
|
|
1037
1072
|
"google/gemma-4-26b-a4b-it:free": { "displayName": "Gemma 4 26B A4B (free)", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-04-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "video"], "output": ["text"] } },
|
|
1038
1073
|
"google/gemma-4-31b-it": { "displayName": "Gemma 4 31B IT", "description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "video"], "output": ["text"] } },
|
|
1039
1074
|
"google/gemma-4-31b-it:free": { "displayName": "Gemma 4 31B (free)", "description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-04-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "video"], "output": ["text"] } },
|
|
@@ -1041,28 +1076,36 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1041
1076
|
"google/lyria-3-pro-preview": { "displayName": "Lyria 3 Pro Preview", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "structuredOutput": false, "lastUpdated": "2026-03-25", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "audio"] } },
|
|
1042
1077
|
"gryphe/mythomax-l2-13b": { "displayName": "MythoMax 13B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 3686, "knowledgeCutoff": "2023-06-30", "structuredOutput": true, "lastUpdated": "2023-07-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1043
1078
|
"ibm-granite/granite-4.0-h-micro": { "displayName": "Granite 4.0 Micro", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 117900, "structuredOutput": false, "lastUpdated": "2025-10-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1044
|
-
"ibm-granite/granite-4.1-8b": { "displayName": "Granite 4.1 8B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "structuredOutput": true, "lastUpdated": "2026-04-30", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1045
1079
|
"ibm-granite/granite-4.2-8b": { "displayName": "Granite 4.2 8B", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "structuredOutput": true, "lastUpdated": "2026-08-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1046
1080
|
"inception/mercury-2": { "displayName": "Mercury 2", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 50000, "structuredOutput": true, "lastUpdated": "2026-03-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1047
|
-
"
|
|
1081
|
+
"inception/mercury-2.5": { "displayName": "Mercury 2.5", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 260000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-09-08", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1082
|
+
"inclusionai/ling-3.0-flash": { "displayName": "Ling 3.0 Flash", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1083
|
+
"inclusionai/ling-3.0-flash-fin": { "displayName": "Ling 3.0 Flash Fin", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-08-27", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1048
1084
|
"inclusionai/ling-3.0-flash-fin:free": { "displayName": "Ling 3.0 Flash Fin (free)", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-08-27", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1085
|
+
"inclusionai/ling-3.0-flash-sante:free": { "displayName": "Ling 3.0 Flash Sante (free)", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-09-04", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1086
|
+
"inclusionai/ling-3.0-flash-vl": { "displayName": "Ling 3.0 Flash VL", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1087
|
+
"inclusionai/ling-3.0-flash-vl:free": { "displayName": "Ling 3.0 Flash VL (free)", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-09-10", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1088
|
+
"inference-net/schematron-v2-small": { "displayName": "Schematron V2 Small", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2026-09-12", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1089
|
+
"inference-net/schematron-v2-turbo": { "displayName": "Schematron V2 Turbo", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "structuredOutput": true, "lastUpdated": "2026-09-12", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1049
1090
|
"kwaipilot/kat-coder-pro-v2": { "displayName": "KAT-Coder-Pro V2", "description": "Coding model for repository understanding, refactors, and agentic engineering tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 144000, "structuredOutput": true, "lastUpdated": "2026-03-27", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1050
1091
|
"kwaipilot/kat-coder-pro-v2.5": { "displayName": "KAT-Coder-Pro V2.5", "description": "Coding model for repository understanding, refactors, and agentic engineering tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-07-10", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1051
1092
|
"liquid/lfm-2.5-2.6b:free": { "displayName": "LFM2.5-2.6B (free)", "description": "Free provider route for experiments, demos, and cost-sensitive chat workloads", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 8192, "structuredOutput": true, "lastUpdated": "2026-08-11", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1052
1093
|
"mancer/weaver": { "displayName": "Weaver (alpha)", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 8000, "maxOutputTokens": 6000, "knowledgeCutoff": "2023-06-30", "structuredOutput": false, "lastUpdated": "2023-08-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1053
1094
|
"meituan/longcat-2.0": { "displayName": "LongCat 2.0", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 1048756, "maxOutputTokens": 262144, "structuredOutput": false, "lastUpdated": "2026-07-20", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1054
|
-
"meta-llama/llama-3.1-70b-instruct": { "displayName": "Llama
|
|
1095
|
+
"meta-llama/llama-3.1-70b-instruct": { "displayName": "Llama-3.1-70B-Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2023-12", "structuredOutput": true, "lastUpdated": "2024-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1055
1096
|
"meta-llama/llama-3.1-8b-instruct": { "displayName": "Llama-3.1-8B-Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "knowledgeCutoff": "2023-12", "structuredOutput": true, "lastUpdated": "2024-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1056
1097
|
"meta-llama/llama-3.2-1b-instruct": { "displayName": "Llama 3.2 1B Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 60000, "maxOutputTokens": 54000, "knowledgeCutoff": "2023-12-31", "structuredOutput": false, "lastUpdated": "2024-09-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1057
1098
|
"meta-llama/llama-3.2-3b-instruct": { "displayName": "Llama 3.2 3B Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "knowledgeCutoff": "2023-12-31", "structuredOutput": true, "lastUpdated": "2024-09-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1058
|
-
"meta-llama/llama-3.3-70b-instruct": { "displayName": "Llama-3.3-70B-Instruct", "description": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens":
|
|
1059
|
-
"meta-llama/llama-4-maverick": { "displayName": "Llama 4 Maverick", "description": "Open multimodal Llama model for strong reasoning and fast responses", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens":
|
|
1099
|
+
"meta-llama/llama-3.3-70b-instruct": { "displayName": "Llama-3.3-70B-Instruct", "description": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2023-12", "structuredOutput": true, "lastUpdated": "2024-12-06", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1100
|
+
"meta-llama/llama-4-maverick": { "displayName": "Llama 4 Maverick", "description": "Open multimodal Llama model for strong reasoning and fast responses", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-08-31", "structuredOutput": true, "lastUpdated": "2025-04-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1060
1101
|
"meta-llama/llama-4-scout": { "displayName": "Llama 4 Scout", "description": "Open multimodal Llama model for long-context analysis and efficient agents", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-08-31", "structuredOutput": true, "lastUpdated": "2025-04-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1061
1102
|
"meta-llama/llama-guard-4-12b": { "displayName": "Llama Guard 4 12B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-08-31", "structuredOutput": false, "lastUpdated": "2025-04-30", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
|
|
1062
|
-
"meta/muse-glimmer-30b": { "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", "contextWindow": 131072, "maxOutputTokens":
|
|
1103
|
+
"meta/muse-glimmer-30b": { "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", "contextWindow": 131072, "maxOutputTokens": 117964, "knowledgeCutoff": "2026-01-04", "structuredOutput": true, "lastUpdated": "2026-08-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1063
1104
|
"meta/muse-spark-1.1": { "displayName": "Muse Spark 1.1", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
1064
1105
|
"meta/muse-spark-1.2": { "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", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
1065
1106
|
"meta/muse-spark-1.2-contributor": { "displayName": "Muse Spark 1.2 Contributor", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
1107
|
+
"meta/muse-spark-1.3": { "displayName": "Muse Spark 1.3", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
1108
|
+
"meta/muse-spark-1.3-contributor": { "displayName": "Muse Spark 1.3 Contributor", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
|
|
1066
1109
|
"microsoft/phi-4": { "displayName": "Phi 4", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 16384, "maxOutputTokens": 14745, "knowledgeCutoff": "2024-06-30", "structuredOutput": true, "lastUpdated": "2025-01-10", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1067
1110
|
"microsoft/wizardlm-2-8x22b": { "displayName": "WizardLM-2 8x22B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 65535, "maxOutputTokens": 8000, "knowledgeCutoff": "2024-04-30", "structuredOutput": false, "lastUpdated": "2024-04-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1068
1111
|
"minimax/minimax-01": { "displayName": "MiniMax-01", "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 1000192, "maxOutputTokens": 900172, "knowledgeCutoff": "2024-03-31", "structuredOutput": false, "lastUpdated": "2025-01-15", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
@@ -1072,9 +1115,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1072
1115
|
"minimax/minimax-m2.1": { "displayName": "MiniMax-M2.1", "description": "Earlier MiniMax agent model for practical coding and productivity tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "structuredOutput": false, "lastUpdated": "2025-12-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1073
1116
|
"minimax/minimax-m2.5": { "displayName": "MiniMax-M2.5", "description": "Prior MiniMax coding model for agent workflows, office edits, and automation", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1074
1117
|
"minimax/minimax-m2.7": { "displayName": "MiniMax-M2.7", "description": "Open MiniMax flagship for coding agents, office automation, and complex environments", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1075
|
-
"minimax/minimax-m2.7:free": { "displayName": "MiniMax M2.7 (free)", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 196608, "maxOutputTokens": 176947, "structuredOutput": false, "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1076
1118
|
"minimax/minimax-m3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 512000, "structuredOutput": true, "lastUpdated": "2026-06-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1077
|
-
"minimax/minimax-m3:free": { "displayName": "MiniMax M3 (free)", "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": false, "lastUpdated": "2026-06-01", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1078
1119
|
"mistralai/codestral-2508": { "displayName": "Codestral 2508", "description": "Mistral coding model for code completion, generation, and developer workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 204800, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-08-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "pdf"], "output": ["text"] } },
|
|
1079
1120
|
"mistralai/devstral-2512": { "displayName": "Devstral 2", "description": "Mistral coding agent model for repository tasks and software engineering workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 209715, "knowledgeCutoff": "2025-12", "structuredOutput": true, "lastUpdated": "2025-12-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "pdf"], "output": ["text"] } },
|
|
1080
1121
|
"mistralai/ministral-14b-2512": { "displayName": "Ministral 3 14B 2512", "description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 209715, "structuredOutput": true, "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
@@ -1091,30 +1132,30 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1091
1132
|
"mistralai/mistral-small-24b-instruct-2501": { "displayName": "Mistral Small 3", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "knowledgeCutoff": "2023-10-31", "structuredOutput": true, "lastUpdated": "2025-01-30", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1092
1133
|
"mistralai/mistral-small-2603": { "displayName": "Mistral Small 4", "description": "Fast Mistral production model for chat, extraction, and cost-sensitive agents", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 209715, "knowledgeCutoff": "2025-06", "structuredOutput": true, "lastUpdated": "2026-03-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1093
1134
|
"mistralai/mistral-small-3.1-24b-instruct": { "displayName": "Mistral Small 3.1 24B", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 102400, "knowledgeCutoff": "2023-10-31", "structuredOutput": false, "lastUpdated": "2025-03-17", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1094
|
-
"mistralai/mistral-small-3.2-24b-instruct": { "displayName": "Mistral Small 3.2 24B", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow":
|
|
1135
|
+
"mistralai/mistral-small-3.2-24b-instruct": { "displayName": "Mistral Small 3.2 24B", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 16384, "knowledgeCutoff": "2023-10-31", "structuredOutput": true, "lastUpdated": "2025-06-20", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
|
|
1095
1136
|
"mistralai/mixtral-8x22b-instruct": { "displayName": "Mixtral 8x22B Instruct", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 52428, "knowledgeCutoff": "2024-01-31", "structuredOutput": true, "lastUpdated": "2024-04-17", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "pdf"], "output": ["text"] } },
|
|
1096
|
-
"mistralai/voxtral-small-24b-2507": { "displayName": "Voxtral Small 24B 2507", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 26214, "structuredOutput": true, "lastUpdated": "2025-
|
|
1097
|
-
"moonshotai/kimi-k2": { "displayName": "Kimi K2 0711", "description": "Kimi model for long-context chat, coding, and agentic reasoning", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens":
|
|
1098
|
-
"moonshotai/kimi-k2-0905": { "displayName": "Kimi K2 0905", "description": "Kimi model for long-context chat, coding, and agentic reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens":
|
|
1099
|
-
"moonshotai/kimi-k2-thinking": { "displayName": "Kimi K2 Thinking", "description": "Thinking Kimi model for slower research passes, planning, and hard technical questions", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens":
|
|
1137
|
+
"mistralai/voxtral-small-24b-2507": { "displayName": "Voxtral Small 24B 2507", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 26214, "structuredOutput": true, "lastUpdated": "2025-07-15", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "audio", "pdf"], "output": ["text"] } },
|
|
1138
|
+
"moonshotai/kimi-k2": { "displayName": "Kimi K2 0711", "description": "Kimi model for long-context chat, coding, and agentic reasoning", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 98304, "knowledgeCutoff": "2024-12-31", "structuredOutput": false, "lastUpdated": "2025-07-11", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1139
|
+
"moonshotai/kimi-k2-0905": { "displayName": "Kimi K2 0905", "description": "Kimi model for long-context chat, coding, and agentic reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 98304, "knowledgeCutoff": "2024-12-31", "structuredOutput": true, "lastUpdated": "2025-09-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1140
|
+
"moonshotai/kimi-k2-thinking": { "displayName": "Kimi K2 Thinking", "description": "Thinking Kimi model for slower research passes, planning, and hard technical questions", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 98304, "knowledgeCutoff": "2024-08", "structuredOutput": true, "lastUpdated": "2025-11-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1100
1141
|
"moonshotai/kimi-k2.5": { "displayName": "Kimi K2.5", "description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1101
1142
|
"moonshotai/kimi-k2.6": { "displayName": "Kimi K2.6", "description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1102
1143
|
"moonshotai/kimi-k2.7-code": { "displayName": "Kimi K2.7 Code", "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1103
1144
|
"moonshotai/kimi-k3": { "displayName": "Kimi K3", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-07-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1104
1145
|
"morph/morph-v3-fast": { "displayName": "Morph V3 Fast", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 81920, "maxOutputTokens": 38000, "structuredOutput": false, "lastUpdated": "2025-07-07", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1105
1146
|
"morph/morph-v3-large": { "displayName": "Morph V3 Large", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2025-07-07", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1106
|
-
"nex-agi/nex-n2-mini": { "displayName": "Nex-N2-Mini", "description": "
|
|
1107
|
-
"nex-agi/nex-n2-pro": { "displayName": "Nex-N2-Pro", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput":
|
|
1147
|
+
"nex-agi/nex-n2.5-mini:free": { "displayName": "Nex-N2.5-Mini (free)", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-09-08", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1148
|
+
"nex-agi/nex-n2.5-pro:free": { "displayName": "Nex-N2.5-Pro (free)", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-09-08", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1108
1149
|
"nousresearch/hermes-3-llama-3.1-405b": { "displayName": "Hermes 3 405B Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2023-12-31", "structuredOutput": true, "lastUpdated": "2024-08-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1109
1150
|
"nousresearch/hermes-3-llama-3.1-70b": { "displayName": "Hermes 3 70B Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2023-12-31", "structuredOutput": true, "lastUpdated": "2024-08-18", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1110
1151
|
"nousresearch/hermes-4-405b": { "displayName": "Hermes 4 405B", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "knowledgeCutoff": "2024-08-31", "structuredOutput": false, "lastUpdated": "2025-08-26", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1111
|
-
"
|
|
1112
|
-
"nvidia/nemotron-3-nano-30b-a3b": { "displayName": "Nemotron 3 Nano 30B A3B", "description": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 228000, "structuredOutput": true, "lastUpdated": "2025-12-15", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1152
|
+
"nvidia/nemotron-3-nano-30b-a3b": { "displayName": "Nemotron 3 Nano 30B A3B", "description": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2025-12-15", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1113
1153
|
"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { "displayName": "Nemotron 3 Nano Omni (free)", "description": "Open Nemotron omni model combining reasoning with text, vision, and audio", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 65536, "structuredOutput": false, "lastUpdated": "2026-04-28", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video", "audio"], "output": ["text"] } },
|
|
1114
|
-
"nvidia/nemotron-3-super-120b-a12b": { "displayName": "Nemotron 3 Super 120B A12B", "description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads", "lifecycle": "active", "contextWindow":
|
|
1154
|
+
"nvidia/nemotron-3-super-120b-a12b": { "displayName": "Nemotron 3 Super 120B A12B", "description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-03-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1115
1155
|
"nvidia/nemotron-3-super-120b-a12b:free": { "displayName": "Nemotron 3 Super (free)", "description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-03-11", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1116
|
-
"nvidia/nemotron-3-ultra-550b-a55b": { "displayName": "Nemotron 3 Ultra 550B A55B", "description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens":
|
|
1156
|
+
"nvidia/nemotron-3-ultra-550b-a55b": { "displayName": "Nemotron 3 Ultra 550B A55B", "description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 182520, "structuredOutput": true, "lastUpdated": "2026-06-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1117
1157
|
"nvidia/nemotron-3-ultra-550b-a55b:free": { "displayName": "Nemotron 3 Ultra (free)", "description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "structuredOutput": false, "lastUpdated": "2026-06-04", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1158
|
+
"nvidia/nemotron-3.5-content-safety": { "displayName": "Nemotron 3.5 Content Safety", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "structuredOutput": false, "lastUpdated": "2026-06-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1118
1159
|
"nvidia/nemotron-3.5-content-safety:free": { "displayName": "Nemotron 3.5 Content Safety (free)", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "structuredOutput": false, "lastUpdated": "2026-06-04", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1119
1160
|
"nvidia/nemotron-3.5-lightning": { "displayName": "Nemotron 3.5 Lightning 30B A3B", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1120
1161
|
"nvidia/nemotron-3.5-lightning:free": { "displayName": "Nemotron 3.5 Lightning (free)", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "structuredOutput": false, "lastUpdated": "2026-08-11", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -1124,7 +1165,6 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1124
1165
|
"openai/gpt-3.5-turbo-instruct": { "displayName": "GPT-3.5 Turbo Instruct", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 4095, "maxOutputTokens": 3685, "knowledgeCutoff": "2021-09-30", "structuredOutput": true, "lastUpdated": "2023-09-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1125
1166
|
"openai/gpt-4": { "displayName": "GPT-4", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 8191, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-11", "structuredOutput": true, "lastUpdated": "2024-04-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1126
1167
|
"openai/gpt-4-turbo": { "displayName": "GPT-4 Turbo", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-12", "structuredOutput": true, "lastUpdated": "2024-04-09", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1127
|
-
"openai/gpt-4-turbo-preview": { "displayName": "GPT-4 Turbo Preview", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-12-31", "structuredOutput": true, "lastUpdated": "2024-01-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1128
1168
|
"openai/gpt-4.1": { "displayName": "GPT-4.1", "description": "Long-lived GPT workhorse for coding, instruction following, and production apps", "lifecycle": "active", "contextWindow": 1047576, "maxOutputTokens": 32768, "knowledgeCutoff": "2024-04", "structuredOutput": true, "lastUpdated": "2025-04-14", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1129
1169
|
"openai/gpt-4.1-mini": { "displayName": "GPT-4.1 mini", "description": "Affordable GPT-4.1 lane for fast coding help and structured extraction", "lifecycle": "active", "contextWindow": 1047576, "maxOutputTokens": 32768, "knowledgeCutoff": "2024-04", "structuredOutput": true, "lastUpdated": "2025-04-14", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1130
1170
|
"openai/gpt-4.1-nano": { "displayName": "GPT-4.1 nano", "description": "Tiny GPT-4.1 option for classification, routing, and very high-volume tasks", "lifecycle": "active", "contextWindow": 1047576, "maxOutputTokens": 32768, "knowledgeCutoff": "2024-04", "structuredOutput": true, "lastUpdated": "2025-04-14", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["image", "text", "pdf"], "output": ["text"] } },
|
|
@@ -1162,12 +1202,14 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1162
1202
|
"openai/gpt-5.6-sol-pro": { "displayName": "GPT-5.6 Sol Pro", "description": "Frontier GPT model for professional reasoning, coding, and multimodal work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1163
1203
|
"openai/gpt-5.6-terra": { "displayName": "GPT-5.6 Terra", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1164
1204
|
"openai/gpt-5.6-terra-pro": { "displayName": "GPT-5.6 Terra Pro", "description": "Frontier GPT model for professional reasoning, coding, and multimodal work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1205
|
+
"openai/gpt-6-astra": { "displayName": "GPT-6 Astra", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-30", "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1206
|
+
"openai/gpt-6-astra-pro": { "displayName": "GPT-6 Astra Pro", "description": "Frontier GPT model for professional reasoning, coding, and multimodal work", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
|
|
1165
1207
|
"openai/gpt-audio": { "displayName": "GPT Audio", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
|
|
1166
1208
|
"openai/gpt-audio-mini": { "displayName": "GPT Audio Mini", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
|
|
1167
1209
|
"openai/gpt-chat-latest": { "displayName": "GPT Chat Latest", "description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "lifecycle": "active", "contextWindow": 400000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-05-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1168
1210
|
"openai/gpt-oss-120b": { "displayName": "GPT OSS 120B", "description": "Open GPT reasoning model for self-hosted agents and controllable deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1169
1211
|
"openai/gpt-oss-20b": { "displayName": "GPT OSS 20B", "description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1170
|
-
"openai/gpt-oss-safeguard-20b": { "displayName": "
|
|
1212
|
+
"openai/gpt-oss-safeguard-20b": { "displayName": "GPT OSS Safeguard 20B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2025-10-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1171
1213
|
"openai/o1": { "displayName": "o1", "description": "O-series reasoning model for hard analysis, math, coding, and planning", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 100000, "knowledgeCutoff": "2023-09", "structuredOutput": true, "lastUpdated": "2024-12-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1172
1214
|
"openai/o1-pro": { "displayName": "o1-pro", "description": "O-series reasoning model for hard analysis, math, coding, and planning", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 100000, "knowledgeCutoff": "2023-09", "structuredOutput": true, "lastUpdated": "2025-03-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1173
1215
|
"openai/o3": { "displayName": "o3", "description": "Deliberate o-series reasoner for hard math, coding, and multi-step analysis", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 100000, "knowledgeCutoff": "2024-05", "structuredOutput": true, "lastUpdated": "2025-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
@@ -1196,12 +1238,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1196
1238
|
"qwen/qwen-2.5-coder-32b-instruct": { "displayName": "Qwen2.5 Coder 32B Instruct", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 29491, "knowledgeCutoff": "2024-06-30", "structuredOutput": false, "lastUpdated": "2024-11-11", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1197
1239
|
"qwen/qwen-plus": { "displayName": "Qwen Plus", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 32768, "knowledgeCutoff": "2024-04", "structuredOutput": true, "lastUpdated": "2025-09-11", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1198
1240
|
"qwen/qwen-plus-2025-07-28": { "displayName": "Qwen Plus 0728", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-09-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1199
|
-
"qwen/qwen2.5-vl-72b-instruct": { "displayName": "Qwen2.5 VL 72B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens":
|
|
1241
|
+
"qwen/qwen2.5-vl-72b-instruct": { "displayName": "Qwen2.5 VL 72B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 115200, "knowledgeCutoff": "2024-06-30", "structuredOutput": true, "lastUpdated": "2025-02-01", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1200
1242
|
"qwen/qwen3-14b": { "displayName": "Qwen3 14B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-04-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1201
1243
|
"qwen/qwen3-235b-a22b": { "displayName": "Qwen3 235B-A22B", "description": "Large open Qwen MoE for multilingual reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 8192, "knowledgeCutoff": "2025-04", "structuredOutput": false, "lastUpdated": "2025-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1202
1244
|
"qwen/qwen3-235b-a22b-2507": { "displayName": "Qwen3 235B A22B Instruct 2507", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "knowledgeCutoff": "2025-06-30", "structuredOutput": true, "lastUpdated": "2025-07-21", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1203
1245
|
"qwen/qwen3-235b-a22b-thinking-2507": { "displayName": "Qwen3 235B A22B Thinking 2507", "description": "Qwen reasoning model for deliberate problem solving, math, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "knowledgeCutoff": "2025-06-30", "structuredOutput": false, "lastUpdated": "2025-07-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1204
|
-
"qwen/qwen3-30b-a3b": { "displayName": "Qwen3 30B A3B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "structuredOutput":
|
|
1246
|
+
"qwen/qwen3-30b-a3b": { "displayName": "Qwen3 30B A3B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2025-04-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1205
1247
|
"qwen/qwen3-30b-a3b-instruct-2507": { "displayName": "Qwen3 30B A3B Instruct 2507", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-06-30", "structuredOutput": true, "lastUpdated": "2025-07-29", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1206
1248
|
"qwen/qwen3-30b-a3b-thinking-2507": { "displayName": "Qwen3 30B A3B Thinking 2507", "description": "Qwen reasoning model for deliberate problem solving, math, and coding", "lifecycle": "active", "contextWindow": 81920, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-06-30", "structuredOutput": false, "lastUpdated": "2025-08-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1207
1249
|
"qwen/qwen3-32b": { "displayName": "Qwen3 32B", "description": "Dense open Qwen model for self-hosted chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -1213,7 +1255,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1213
1255
|
"qwen/qwen3-coder-plus": { "displayName": "Qwen3 Coder Plus", "description": "Hosted Qwen coder for software agents, repo edits, and long-context code", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1214
1256
|
"qwen/qwen3-max": { "displayName": "Qwen3 Max", "description": "Flagship Qwen3 model for coding agents, complex reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1215
1257
|
"qwen/qwen3-max-thinking": { "displayName": "Qwen3 Max Thinking", "description": "Qwen reasoning model for deliberate problem solving, math, and coding", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-09", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1216
|
-
"qwen/qwen3-next-80b-a3b-instruct": { "displayName": "Qwen3-Next 80B-A3B Instruct", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens":
|
|
1258
|
+
"qwen/qwen3-next-80b-a3b-instruct": { "displayName": "Qwen3-Next 80B-A3B Instruct", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1217
1259
|
"qwen/qwen3-next-80b-a3b-thinking": { "displayName": "Qwen3-Next 80B-A3B (Thinking)", "description": "Efficient Qwen thinking model for local reasoning, math, and coding agents", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1218
1260
|
"qwen/qwen3-vl-235b-a22b-instruct": { "displayName": "Qwen3 VL 235B A22B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-09-23", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1219
1261
|
"qwen/qwen3-vl-235b-a22b-thinking": { "displayName": "Qwen3 VL 235B A22B Thinking", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-09-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
@@ -1222,15 +1264,15 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1222
1264
|
"qwen/qwen3-vl-32b-instruct": { "displayName": "Qwen3 VL 32B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2025-10-23", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1223
1265
|
"qwen/qwen3-vl-8b-instruct": { "displayName": "Qwen3 VL 8B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2025-10-14", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
|
|
1224
1266
|
"qwen/qwen3-vl-8b-thinking": { "displayName": "Qwen3 VL 8B Thinking", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2025-10-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
|
|
1225
|
-
"qwen/qwen3.5-122b-a10b": { "displayName": "Qwen3.5 122B-A10B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens":
|
|
1267
|
+
"qwen/qwen3.5-122b-a10b": { "displayName": "Qwen3.5 122B-A10B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1226
1268
|
"qwen/qwen3.5-27b": { "displayName": "Qwen3.5 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1227
|
-
"qwen/qwen3.5-35b-a3b": { "displayName": "Qwen3.5 35B-A3B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens":
|
|
1228
|
-
"qwen/qwen3.5-397b-a17b": { "displayName": "Qwen3.5 397B-A17B", "description": "Large open Qwen multimodal MoE for visual agents and long technical tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens":
|
|
1269
|
+
"qwen/qwen3.5-35b-a3b": { "displayName": "Qwen3.5 35B-A3B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1270
|
+
"qwen/qwen3.5-397b-a17b": { "displayName": "Qwen3.5 397B-A17B", "description": "Large open Qwen multimodal MoE for visual agents and long technical tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-02-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1229
1271
|
"qwen/qwen3.5-9b": { "displayName": "Qwen3.5 9B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1230
1272
|
"qwen/qwen3.5-flash-02-23": { "displayName": "Qwen3.5-Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-25", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1231
1273
|
"qwen/qwen3.5-plus-02-15": { "displayName": "Qwen3.5 Plus 2026-02-15", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-02-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1232
1274
|
"qwen/qwen3.5-plus-20260420": { "displayName": "Qwen3.5 Plus 2026-04-20", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1233
|
-
"qwen/qwen3.6-27b": { "displayName": "Qwen3.6 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens":
|
|
1275
|
+
"qwen/qwen3.6-27b": { "displayName": "Qwen3.6 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1234
1276
|
"qwen/qwen3.6-35b-a3b": { "displayName": "Qwen3.6 35B-A3B", "description": "Open multimodal Qwen MoE for local agents that need vision, audio, and code", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-04-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1235
1277
|
"qwen/qwen3.6-flash": { "displayName": "Qwen3.6 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1236
1278
|
"qwen/qwen3.6-max-preview": { "displayName": "Qwen3.6 Max Preview", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-04-20", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -1238,15 +1280,17 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1238
1280
|
"qwen/qwen3.7-flash": { "displayName": "Qwen3.7 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 991000, "maxOutputTokens": 65536, "structuredOutput": false, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1239
1281
|
"qwen/qwen3.7-max": { "displayName": "Qwen3.7 Max", "description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-05-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1240
1282
|
"qwen/qwen3.7-plus": { "displayName": "Qwen3.7 Plus", "description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-06-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1241
|
-
"qwen/qwen3.8-2.4t-a95b": { "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", "contextWindow": 1048576, "maxOutputTokens":
|
|
1283
|
+
"qwen/qwen3.8-2.4t-a95b": { "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", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1242
1284
|
"qwen/qwen3.8-27b": { "displayName": "Qwen3.8 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1243
1285
|
"qwen/qwen3.8-flash": { "displayName": "Qwen3.8 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1244
|
-
"qwen/qwen3.8-max": { "displayName": "Qwen3.8 Max", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-
|
|
1286
|
+
"qwen/qwen3.8-max-0902": { "displayName": "Qwen3.8 Max 0902", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1245
1287
|
"rekaai/reka-edge": { "displayName": "Reka Edge", "description": "Multimodal model for analyzing text, images, documents, and rich media", "lifecycle": "active", "contextWindow": 16384, "maxOutputTokens": 14745, "structuredOutput": true, "lastUpdated": "2026-03-20", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["image", "text", "video"], "output": ["text"] } },
|
|
1246
1288
|
"rekaai/reka-flash-3": { "displayName": "Reka Flash 3", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 58982, "knowledgeCutoff": "2025-01-31", "structuredOutput": true, "lastUpdated": "2025-03-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1247
1289
|
"relace/relace-apply-3": { "displayName": "Relace Apply 3", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 128000, "structuredOutput": false, "lastUpdated": "2025-09-26", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1248
1290
|
"relace/relace-search": { "displayName": "Relace Search", "description": "Tool-capable chat model for instruction following and agentic application workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 128000, "structuredOutput": false, "lastUpdated": "2025-12-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1291
|
+
"sakana/fugu-max": { "displayName": "Fugu Max", "description": "Multi-agent model for routing expert agents across complex analytical tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-09-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1249
1292
|
"sakana/fugu-ultra": { "displayName": "Fugu Ultra", "description": "Quality-first multi-agent model for hard research, analysis, and competitions", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1293
|
+
"sakana/fugu-ultra-v2": { "displayName": "Fugu Ultra v2", "description": "Quality-first multi-agent model for hard research, analysis, and competitions", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-08-28", "structuredOutput": true, "lastUpdated": "2026-09-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1250
1294
|
"sakana/sakana-namazu": { "displayName": "Sakana Namazu", "description": "Multi-agent model for routing expert agents across complex analytical tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-08-03", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1251
1295
|
"sao10k/l3-lunaris-8b": { "displayName": "Llama 3 8B Lunaris", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 7372, "knowledgeCutoff": "2023-12-31", "structuredOutput": true, "lastUpdated": "2024-08-13", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1252
1296
|
"sao10k/l3.1-euryale-70b": { "displayName": "Llama 3.1 Euryale 70B v2.2", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2023-12-31", "structuredOutput": true, "lastUpdated": "2024-08-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -1257,17 +1301,17 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1257
1301
|
"tencent/hy-mt2-1.8b": { "displayName": "Hy-MT2-1.8B", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 4096, "structuredOutput": false, "lastUpdated": "2026-08-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1258
1302
|
"tencent/hy-mt2-30b-a3b": { "displayName": "Hy-MT2-30B-A3B", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2026-08-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1259
1303
|
"tencent/hy-mt2-7b": { "displayName": "Hy-MT2-7B", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2026-08-19", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1260
|
-
"tencent/hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-07-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1304
|
+
"tencent/hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "inputLimit": 192000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-07-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1261
1305
|
"tencent/hy3-preview": { "displayName": "Hy3 preview", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": false, "lastUpdated": "2026-04-20", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1262
1306
|
"tencent/hy4-preview": { "displayName": "Hy4 preview", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-08-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1263
1307
|
"thedrummer/cydonia-24b-v4.1": { "displayName": "Cydonia 24B V4.1", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "knowledgeCutoff": "2024-04-30", "structuredOutput": true, "lastUpdated": "2025-09-27", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1264
1308
|
"thedrummer/skyfall-36b-v2": { "displayName": "Skyfall 36B V2", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 29491, "knowledgeCutoff": "2024-06-30", "structuredOutput": true, "lastUpdated": "2025-03-10", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1265
|
-
"thedrummer/unslopnemo-12b": { "displayName": "UnslopNemo 12B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 1024000, "maxOutputTokens":
|
|
1309
|
+
"thedrummer/unslopnemo-12b": { "displayName": "UnslopNemo 12B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 1024000, "maxOutputTokens": 819200, "knowledgeCutoff": "2024-04-30", "structuredOutput": true, "lastUpdated": "2024-11-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1266
1310
|
"thinkingmachines/inkling": { "displayName": "Inkling", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 471859, "structuredOutput": false, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
|
|
1267
1311
|
"thinkingmachines/inkling-small": { "displayName": "Inkling Small", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 262144, "structuredOutput": false, "lastUpdated": "2026-07-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
|
|
1268
1312
|
"thinkingmachines/inkling-small:free": { "displayName": "Inkling Small (free)", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 262144, "structuredOutput": false, "lastUpdated": "2026-07-30", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
|
|
1269
1313
|
"thinkingmachines/inkling:free": { "displayName": "Inkling (free)", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 262144, "structuredOutput": false, "lastUpdated": "2026-07-15", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
|
|
1270
|
-
"undi95/remm-slerp-l2-13b": { "displayName": "ReMM SLERP 13B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 6144, "maxOutputTokens":
|
|
1314
|
+
"undi95/remm-slerp-l2-13b": { "displayName": "ReMM SLERP 13B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 6144, "maxOutputTokens": 5529, "knowledgeCutoff": "2023-06-30", "structuredOutput": true, "lastUpdated": "2023-07-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1271
1315
|
"upstage/solar-pro-3": { "displayName": "Solar Pro 3", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "structuredOutput": true, "lastUpdated": "2026-01-27", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1272
1316
|
"upstage/solar-pro4": { "displayName": "Solar Pro 4", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-10", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1273
1317
|
"writer/palmyra-x5": { "displayName": "Palmyra X5", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 1040000, "maxOutputTokens": 8192, "structuredOutput": false, "lastUpdated": "2026-01-21", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -1285,13 +1329,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1285
1329
|
"z-ai/glm-4.6": { "displayName": "GLM-4.6", "description": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09-30", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1286
1330
|
"z-ai/glm-4.6v": { "displayName": "GLM-4.6V", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "structuredOutput": false, "lastUpdated": "2025-12-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1287
1331
|
"z-ai/glm-4.7": { "displayName": "GLM-4.7", "description": "Mature GLM model for dependable coding, reasoning, and structured agent tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-12-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1288
|
-
"z-ai/glm-4.7-flash": { "displayName": "GLM-4.7-Flash", "description": "Budget GLM lane for fast coding help, routing, and everyday automation", "lifecycle": "active", "contextWindow":
|
|
1332
|
+
"z-ai/glm-4.7-flash": { "displayName": "GLM-4.7-Flash", "description": "Budget GLM lane for fast coding help, routing, and everyday automation", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 117964, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1289
1333
|
"z-ai/glm-5": { "displayName": "GLM-5", "description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1290
1334
|
"z-ai/glm-5-turbo": { "displayName": "GLM-5-Turbo", "description": "Faster GLM-5 lane for coding agents that need lower latency", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 131072, "structuredOutput": false, "lastUpdated": "2026-03-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1291
1335
|
"z-ai/glm-5.1": { "displayName": "GLM-5.1", "description": "Strong GLM coding model for agentic engineering, terminals, and repository generation", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-04-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1292
|
-
"z-ai/glm-5.2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens":
|
|
1293
|
-
"z-ai/glm-5.
|
|
1294
|
-
"z-ai/glm-5.3": { "displayName": "GLM-5.3", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1336
|
+
"z-ai/glm-5.2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1337
|
+
"z-ai/glm-5.3": { "displayName": "GLM-5.3", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 943717, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1295
1338
|
"z-ai/glm-5.3-flash": { "displayName": "GLM-5.3-Flash", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
|
|
1296
1339
|
"z-ai/glm-5v-turbo": { "displayName": "GLM-5V-Turbo", "description": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 131072, "structuredOutput": false, "lastUpdated": "2026-04-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "video"], "output": ["text"] } },
|
|
1297
1340
|
},
|
|
@@ -1385,6 +1428,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1385
1428
|
"deepseek-ai/DeepSeek-V4-Flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1386
1429
|
"deepseek-ai/DeepSeek-V4-Pro": { "displayName": "DeepSeek V4 Pro", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 512000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1387
1430
|
"deepseek-ai/DeepSeek-V4-Pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1431
|
+
"deepseek-ai/DeepSeek-V4.1-Flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1388
1432
|
"essentialai/Rnj-1-Instruct": { "displayName": "Rnj-1 Instruct", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "deprecated", "contextWindow": 32768, "maxOutputTokens": 32768, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-05", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1389
1433
|
"google/gemma-3n-E4B-it": { "displayName": "Gemma 3N E4B Instruct", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2025-05-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1390
1434
|
"google/gemma-4-31B-it": { "displayName": "Gemma 4 31B Instruct", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-04-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
@@ -1428,11 +1472,11 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1428
1472
|
"tc-code-latest": { "displayName": "Auto", "description": "Automatic model router for matching prompts to suitable backends and budgets", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2026-03-08", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1429
1473
|
},
|
|
1430
1474
|
"tencent-token-plan": {
|
|
1431
|
-
"hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens":
|
|
1475
|
+
"hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 192000, "maxOutputTokens": 128000, "lastUpdated": "2026-07-06", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1432
1476
|
"hy4-preview": { "displayName": "Hy4 preview", "description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.", "lifecycle": "active", "contextWindow": 1024000, "maxOutputTokens": 64000, "lastUpdated": "2026-08-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1433
1477
|
},
|
|
1434
1478
|
"tencent-tokenhub": {
|
|
1435
|
-
"hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens":
|
|
1479
|
+
"hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 192000, "maxOutputTokens": 128000, "lastUpdated": "2026-07-06", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1436
1480
|
"hy3-preview": { "displayName": "Hy3 preview", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 64000, "lastUpdated": "2026-04-20", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1437
1481
|
"hy4-preview": { "displayName": "Hy4 preview", "description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.", "lifecycle": "active", "contextWindow": 1024000, "maxOutputTokens": 64000, "lastUpdated": "2026-08-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1438
1482
|
},
|
|
@@ -1468,8 +1512,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1468
1512
|
"alibaba/qwen3.8-2.4t-a95b": { "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", "contextWindow": 262144, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1469
1513
|
"alibaba/qwen3.8-27b": { "displayName": "Qwen3.8 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1470
1514
|
"alibaba/qwen3.8-flash": { "displayName": "Qwen 3.8 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 991000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1471
|
-
"alibaba/qwen3.8-flash-next": { "displayName": "Qwen 3.8 Flash Next", "description": "Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1472
1515
|
"alibaba/qwen3.8-max": { "displayName": "Qwen 3.8 Max", "description": "Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "lastUpdated": "2026-07-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1516
|
+
"alibaba/qwen3.8-max-0902": { "displayName": "Qwen3.8 Max 0902", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 991000, "maxOutputTokens": 128000, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1473
1517
|
"alibaba/wan-v2.5-t2v-preview": { "displayName": "Wan v2.5 Text-to-Video Preview", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2025-09-24", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
|
|
1474
1518
|
"alibaba/wan-v2.6-i2v": { "displayName": "Wan v2.6 Image-to-Video", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2025-12-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
|
|
1475
1519
|
"alibaba/wan-v2.6-i2v-flash": { "displayName": "Wan v2.6 Image-to-Video Flash", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2025-12-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
|
|
@@ -1481,12 +1525,13 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1481
1525
|
"alibaba/wan-v3.0-video": { "displayName": "Wan v3.0 Video", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-08-23", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
|
|
1482
1526
|
"alibaba/wan-v3.0-video-prime": { "displayName": "Wan v3.0 Video Prime", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-08-28", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
|
|
1483
1527
|
"amazon/nova-2-lite": { "displayName": "Nova 2 Lite", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1484
|
-
"amazon/nova-lite": { "displayName": "Nova Lite", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 300000, "maxOutputTokens":
|
|
1485
|
-
"amazon/nova-micro": { "displayName": "Nova Micro", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens":
|
|
1486
|
-
"amazon/nova-pro": { "displayName": "Nova Pro", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "lifecycle": "active", "contextWindow": 300000, "maxOutputTokens":
|
|
1528
|
+
"amazon/nova-lite": { "displayName": "Nova Lite", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 300000, "maxOutputTokens": 10000, "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-03", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
|
|
1529
|
+
"amazon/nova-micro": { "displayName": "Nova Micro", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 10000, "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-03", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1530
|
+
"amazon/nova-pro": { "displayName": "Nova Pro", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "lifecycle": "active", "contextWindow": 300000, "maxOutputTokens": 10000, "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-03", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
|
|
1487
1531
|
"amazon/titan-embed-text-v2": { "displayName": "Titan Text Embeddings V2", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1536, "lastUpdated": "2024-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1488
1532
|
"anthropic/claude-3-haiku": { "displayName": "Claude Haiku 3", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-03-13", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1489
1533
|
"anthropic/claude-fable-5": { "displayName": "Claude Fable 5", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1534
|
+
"anthropic/claude-fable-5.1": { "displayName": "Claude Fable 5.1", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1490
1535
|
"anthropic/claude-haiku-4.5": { "displayName": "Claude Haiku 4.5", "description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1491
1536
|
"anthropic/claude-opus-4": { "displayName": "Claude Opus 4", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 8192, "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1492
1537
|
"anthropic/claude-opus-4.5": { "displayName": "Claude Opus 4.5", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-05", "lastUpdated": "2025-11-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
@@ -1514,6 +1559,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1514
1559
|
"bfl/flux-pro-1.1-ultra": { "displayName": "FLUX1.1 [pro] Ultra", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 512, "maxOutputTokens": 0, "lastUpdated": "2024-11", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
1515
1560
|
"bytedance/seed-1.6": { "displayName": "Seed 1.6", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1516
1561
|
"bytedance/seed-1.8": { "displayName": "Seed 1.8", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1562
|
+
"bytedance/seed-2.1-turbo": { "displayName": "Seed 2.1 Turbo", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "lastUpdated": "2026-06-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1517
1563
|
"bytedance/seedance-2.0": { "displayName": "Seedance 2.0", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-04-14", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
|
|
1518
1564
|
"bytedance/seedance-2.0-fast": { "displayName": "Seedance 2.0 Fast", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-04-14", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
|
|
1519
1565
|
"bytedance/seedance-2.0-mini": { "displayName": "Seedance 2.0 Mini", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-06-22", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
|
|
@@ -1530,17 +1576,17 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1530
1576
|
"cohere/rerank-v3.5": { "displayName": "Cohere Rerank 3.5", "description": "Reranking model for improving retrieval quality in search and recommendation systems", "lifecycle": "active", "contextWindow": 4096, "maxOutputTokens": 4096, "lastUpdated": "2024-12-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1531
1577
|
"cohere/rerank-v4-fast": { "displayName": "Cohere Rerank 4 Fast", "description": "Reranking model for improving retrieval quality in search and recommendation systems", "lifecycle": "active", "contextWindow": 32000, "maxOutputTokens": 32000, "lastUpdated": "2025-12-11", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1532
1578
|
"cohere/rerank-v4-pro": { "displayName": "Cohere Rerank 4 Pro", "description": "Reranking model for improving retrieval quality in search and recommendation systems", "lifecycle": "active", "contextWindow": 32000, "maxOutputTokens": 32000, "lastUpdated": "2025-12-11", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1533
|
-
"deepseek/deepseek-r1": { "displayName": "DeepSeek-R1", "description": "
|
|
1534
|
-
"deepseek/deepseek-v3": { "displayName": "DeepSeek V3 0324", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 163840, "lastUpdated": "2024-12-26", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1579
|
+
"deepseek/deepseek-r1": { "displayName": "DeepSeek-R1", "description": "Classic open reasoning model for transparent math, coding, and deliberate problem solving", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 32768, "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1535
1580
|
"deepseek/deepseek-v3.1": { "displayName": "DeepSeek-V3.1", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 128000, "lastUpdated": "2025-08-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1536
1581
|
"deepseek/deepseek-v3.1-terminus": { "displayName": "DeepSeek V3.1 Terminus", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-07", "lastUpdated": "2025-09-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1537
1582
|
"deepseek/deepseek-v3.2": { "displayName": "DeepSeek V3.2", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8000, "knowledgeCutoff": "2024-07", "structuredOutput": true, "lastUpdated": "2025-12-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1538
1583
|
"deepseek/deepseek-v3.2-thinking": { "displayName": "DeepSeek V3.2 Thinking", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8000, "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1539
1584
|
"deepseek/deepseek-v4-flash": { "displayName": "DeepSeek V4 Flash", "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1540
1585
|
"deepseek/deepseek-v4-flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1541
|
-
"deepseek/deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow":
|
|
1586
|
+
"deepseek/deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1542
1587
|
"deepseek/deepseek-v4-pro": { "displayName": "DeepSeek V4 Pro", "description": "Open MoE flagship with million-token context for coding and long agent runs", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1543
1588
|
"deepseek/deepseek-v4-pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1589
|
+
"deepseek/deepseek-v4.1-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1544
1590
|
"fish-audio/s1": { "displayName": "S1", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2025-10-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
|
|
1545
1591
|
"fish-audio/s1-free": { "displayName": "S1 (Free)", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2025-10-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
|
|
1546
1592
|
"fish-audio/s2-pro": { "displayName": "S2 Pro", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-03-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
|
|
@@ -1566,6 +1612,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1566
1612
|
"google/gemini-3.5-transcribe-live": { "displayName": "Gemini 3.5 Transcribe Live", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-08-26", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["text"] } },
|
|
1567
1613
|
"google/gemini-3.6-flash": { "displayName": "Gemini 3.6 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-07-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1568
1614
|
"google/gemini-3.7-flash": { "displayName": "Gemini 3.7 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-08-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1615
|
+
"google/gemini-3.8-flash": { "displayName": "Gemini 3.8 Flash", "description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1569
1616
|
"google/gemini-embedding-001": { "displayName": "Gemini Embedding 001", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1536, "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1570
1617
|
"google/gemini-embedding-2": { "displayName": "Gemini Embedding 2", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "knowledgeCutoff": "2025-11", "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1571
1618
|
"google/gemini-omni-flash-preview": { "displayName": "Gemini Omni Flash Preview", "description": "Omni-modal model for text, vision, audio, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 57920, "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
@@ -1579,10 +1626,15 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1579
1626
|
"google/veo-3.1-generate-001": { "displayName": "Veo 3.1", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-06-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
|
|
1580
1627
|
"google/veo-3.1-lite-generate-001": { "displayName": "Veo 3.1 Lite Generate", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-04-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
|
|
1581
1628
|
"inception/mercury-2": { "displayName": "Mercury 2", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "lastUpdated": "2026-03-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1629
|
+
"inception/mercury-2.5": { "displayName": "Mercury 2.5", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 260000, "maxOutputTokens": 65536, "lastUpdated": "2026-09-08", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1582
1630
|
"inception/mercury-coder-small": { "displayName": "Mercury Coder Small Beta", "description": "Coding model for repository understanding, refactors, and agentic engineering tasks", "lifecycle": "active", "contextWindow": 32000, "maxOutputTokens": 16384, "lastUpdated": "2025-02-26", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1583
1631
|
"inclusionai/ling-3.0-flash": { "displayName": "Ling 3.0 Flash", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "lastUpdated": "2026-08-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1584
1632
|
"inclusionai/ling-3.0-flash-fin": { "displayName": "Ling 3.0 Flash Fin", "description": "Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "lastUpdated": "2026-08-27", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1585
1633
|
"inclusionai/ling-3.0-flash-fin-free": { "displayName": "Ling 3.0 Flash Fin (Free)", "description": "Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "lastUpdated": "2026-08-27", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1634
|
+
"inclusionai/ling-3.0-flash-sante": { "displayName": "Ling 3.0 Flash Sante", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "lastUpdated": "2026-09-04", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1635
|
+
"inclusionai/ling-3.0-flash-sante-free": { "displayName": "Ling 3.0 Flash Sante (Free)", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "lastUpdated": "2026-09-04", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1636
|
+
"inclusionai/ling-3.0-flash-vl": { "displayName": "Ling 3.0 Flash VL", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "lastUpdated": "2026-09-08", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1637
|
+
"inclusionai/ling-3.0-flash-vl-free": { "displayName": "Ling 3.0 Flash VL (Free)", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "lastUpdated": "2026-09-08", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1586
1638
|
"interfaze/interfaze-beta": { "displayName": "Interfaze Beta", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 32000, "lastUpdated": "2026-04-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1587
1639
|
"klingai/kling-v2.5-turbo-i2v": { "displayName": "Kling v2.5 Turbo Image-to-Video", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2025-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
|
|
1588
1640
|
"klingai/kling-v2.5-turbo-t2v": { "displayName": "Kling v2.5 Turbo Text-to-Video", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2025-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
|
|
@@ -1605,7 +1657,9 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1605
1657
|
"meta/muse-image-1.0": { "displayName": "Muse Image 1.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["image"] } },
|
|
1606
1658
|
"meta/muse-spark-1.1": { "displayName": "Muse Spark 1.1", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1607
1659
|
"meta/muse-spark-1.2": { "displayName": "Muse Spark 1.2", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1608
|
-
"meta/muse-spark-1.2-contributor": { "displayName": "Muse Spark 1.2 Contributor", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "lastUpdated": "2026-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1660
|
+
"meta/muse-spark-1.2-contributor": { "displayName": "Muse Spark 1.2 Contributor", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "lastUpdated": "2026-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1661
|
+
"meta/muse-spark-1.3": { "displayName": "Muse Spark 1.3", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1662
|
+
"meta/muse-spark-1.3-contributor": { "displayName": "Muse Spark 1.3 Contributor", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1609
1663
|
"minimax/minimax-h3": { "displayName": "MiniMax H3", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-07-30", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
|
|
1610
1664
|
"minimax/minimax-h3-max": { "displayName": "MiniMax H3 Max", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-08-27", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
|
|
1611
1665
|
"minimax/minimax-m2": { "displayName": "MiniMax M2", "description": "Efficient open MiniMax model built for coding agents and tool-heavy workflows", "lifecycle": "active", "contextWindow": 205000, "maxOutputTokens": 205000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10-27", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -1614,10 +1668,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1614
1668
|
"minimax/minimax-m2.5": { "displayName": "MiniMax M2.5", "description": "Prior MiniMax coding model for agent workflows, office edits, and automation", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131000, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1615
1669
|
"minimax/minimax-m2.5-highspeed": { "displayName": "MiniMax M2.5 High Speed", "description": "High-speed MiniMax model for low-latency coding and agent workflows", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131000, "lastUpdated": "2026-02-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1616
1670
|
"minimax/minimax-m2.7": { "displayName": "Minimax M2.7", "description": "Open MiniMax flagship for coding agents, office automation, and complex environments", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131000, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1617
|
-
"minimax/minimax-m2.7-free": { "displayName": "Minimax M2.7 (Free)", "description": "Open MiniMax flagship for coding agents, office automation, and complex environments", "lifecycle": "active", "contextWindow": 196608, "maxOutputTokens": 196608, "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1618
1671
|
"minimax/minimax-m2.7-highspeed": { "displayName": "MiniMax M2.7 High Speed", "description": "Low-latency M2.7 variant for interactive coding plans and agent loops", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131100, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1619
1672
|
"minimax/minimax-m3": { "displayName": "MiniMax M3", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 512000, "maxOutputTokens": 512000, "lastUpdated": "2026-06-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1620
|
-
"minimax/minimax-m3-free": { "displayName": "MiniMax M3 (Free)", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "lastUpdated": "2026-06-01", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1621
1673
|
"mistral/codestral": { "displayName": "Codestral (latest)", "description": "Mistral code model for completions, refactors, and developer IDE workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-01-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1622
1674
|
"mistral/codestral-embed": { "displayName": "Codestral Embed", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1536, "lastUpdated": "2025-05-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1623
1675
|
"mistral/devstral-2": { "displayName": "Devstral 2", "description": "Mistral coding agent model for repository tasks and software engineering workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
@@ -1695,14 +1747,18 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1695
1747
|
"openai/gpt-5.6-sol-fast": { "displayName": "GPT 5.6 Sol (Fast)", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1696
1748
|
"openai/gpt-5.6-terra": { "displayName": "GPT 5.6 Terra", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1697
1749
|
"openai/gpt-5.6-terra-fast": { "displayName": "GPT 5.6 Terra (Fast)", "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1750
|
+
"openai/gpt-6-astra": { "displayName": "GPT-6 Astra", "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-30", "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1751
|
+
"openai/gpt-6-astra-fast": { "displayName": "GPT-6 Astra (Fast)", "description": "Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1698
1752
|
"openai/gpt-image-1": { "displayName": "GPT Image 1", "description": "OpenAI image model for production generation, edits, and brand-safe visual workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2025-04-24", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
1699
1753
|
"openai/gpt-image-1-mini": { "displayName": "GPT Image 1 Mini", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2025-10-06", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
1700
1754
|
"openai/gpt-image-1.5": { "displayName": "GPT Image 1.5", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
1701
1755
|
"openai/gpt-image-2": { "displayName": "GPT Image 2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-04-21", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
1756
|
+
"openai/gpt-image-2.5-flare": { "displayName": "GPT Image 2.5 Flare", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-09-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
1757
|
+
"openai/gpt-image-2.5-sunburst": { "displayName": "GPT Image 2.5 Sunburst", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-09-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
1702
1758
|
"openai/gpt-oss-120b": { "displayName": "GPT OSS 120B", "description": "Open GPT reasoning model for self-hosted agents and controllable deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-10", "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1703
1759
|
"openai/gpt-oss-20b": { "displayName": "GPT OSS 20B", "description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads", "lifecycle": "active", "contextWindow": 131072, "inputLimit": 122880, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-10", "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1704
1760
|
"openai/gpt-oss-safeguard-120b": { "displayName": "GPT OSS Safeguard 120B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "inputLimit": 112000, "maxOutputTokens": 16000, "structuredOutput": true, "lastUpdated": "2025-10-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1705
|
-
"openai/gpt-oss-safeguard-20b": { "displayName": "gpt-oss-safeguard-20b", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "inputLimit": 112000, "maxOutputTokens": 16000, "
|
|
1761
|
+
"openai/gpt-oss-safeguard-20b": { "displayName": "gpt-oss-safeguard-20b", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "inputLimit": 112000, "maxOutputTokens": 16000, "structuredOutput": true, "lastUpdated": "2025-10-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1706
1762
|
"openai/gpt-realtime-1.5": { "displayName": "GPT-Realtime-1.5", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-02-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
|
|
1707
1763
|
"openai/gpt-realtime-2": { "displayName": "gpt-realtime-2", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-05-07", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
|
|
1708
1764
|
"openai/gpt-realtime-2.1": { "displayName": "gpt-realtime-2.1", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 128000, "inputLimit": 96000, "maxOutputTokens": 32000, "knowledgeCutoff": "2024-09-30", "structuredOutput": false, "lastUpdated": "2026-07-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
|
|
@@ -1738,10 +1794,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1738
1794
|
"recraft/recraft-v4.1-pro": { "displayName": "Recraft V4.1 Pro", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-05-14", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
1739
1795
|
"recraft/recraft-v4.1-utility": { "displayName": "Recraft V4.1 Utility", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-05-14", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
1740
1796
|
"recraft/recraft-v4.1-utility-pro": { "displayName": "Recraft V4.1 Utility Pro", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-05-14", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
1797
|
+
"sakana/fugu-max": { "displayName": "Fugu Max", "description": "Multi-agent model for routing expert agents across complex analytical tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1741
1798
|
"sakana/fugu-ultra": { "displayName": "Fugu Ultra", "description": "Quality-first multi-agent model for hard research, analysis, and competitions", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "structuredOutput": true, "lastUpdated": "2026-06-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1799
|
+
"sakana/fugu-ultra-v2": { "displayName": "Fugu Ultra v2", "description": "Quality-first multi-agent model for hard research, analysis, and competitions", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1742
1800
|
"sakana/namazu": { "displayName": "Sakana Namazu", "description": "Multi-agent model for routing expert agents across complex analytical tasks", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "lastUpdated": "2026-08-03", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1743
1801
|
"spacexai/grok-4.1-fast-non-reasoning": { "displayName": "Grok 4.1 Fast Non-Reasoning", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "lastUpdated": "2025-11-19", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1744
|
-
"spacexai/grok-4.1-fast-reasoning": { "displayName": "Grok 4.1 Fast Reasoning", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "lastUpdated": "2025-11-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1802
|
+
"spacexai/grok-4.1-fast-reasoning": { "displayName": "Grok 4.1 Fast Reasoning", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "structuredOutput": true, "lastUpdated": "2025-11-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1745
1803
|
"spacexai/grok-4.20-multi-agent": { "displayName": "Grok 4.20 Multi-Agent", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1746
1804
|
"spacexai/grok-4.20-multi-agent-beta": { "displayName": "Grok 4.20 Multi Agent Beta", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1747
1805
|
"spacexai/grok-4.20-non-reasoning": { "displayName": "Grok 4.20 Non-Reasoning", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-10", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
@@ -1756,7 +1814,6 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1756
1814
|
"spacexai/grok-imagine-image-2.0": { "displayName": "Grok Imagine Image 2.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-08-07", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
|
|
1757
1815
|
"spacexai/grok-imagine-video": { "displayName": "Grok Imagine", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-01-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
|
|
1758
1816
|
"spacexai/grok-imagine-video-1.5": { "displayName": "Grok Imagine Video 1.5", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-05-30", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
|
|
1759
|
-
"spacexai/grok-imagine-video-1.5-preview": { "displayName": "Grok Imagine Video 1.5 Preview", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-05-30", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
|
|
1760
1817
|
"spacexai/grok-stt": { "displayName": "Grok STT", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-03-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["text"] } },
|
|
1761
1818
|
"spacexai/grok-tts": { "displayName": "Grok TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-03-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
|
|
1762
1819
|
"spacexai/grok-voice-think-fast-1.0": { "displayName": "Grok Voice Think Fast 1.0", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 0, "maxOutputTokens": 0, "lastUpdated": "2026-04-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
|
|
@@ -1784,7 +1841,6 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1784
1841
|
"voyage/voyage-law-2": { "displayName": "voyage-law-2", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1536, "lastUpdated": "2024-03", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1785
1842
|
"xiaomi/mimo-v2.5": { "displayName": "MiMo M2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 131100, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1786
1843
|
"xiaomi/mimo-v2.5-pro": { "displayName": "MiMo V2.5 Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 131000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1787
|
-
"xiaomi/mimo-v2.5-pro-ultraspeed": { "displayName": "MiMo V2.5 Pro UltraSpeed", "description": "MiMo pro model for strong multimodal reasoning and agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-06-09", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1788
1844
|
"zai/glm-4.5": { "displayName": "GLM 4.5", "description": "Hybrid-reasoning GLM release that made the 4.5 line broadly useful", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 96000, "knowledgeCutoff": "2025-07", "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1789
1845
|
"zai/glm-4.5-air": { "displayName": "GLM 4.5 Air", "description": "Lighter GLM-4.5 variant for fast coding assistance and cheaper agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 96000, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1790
1846
|
"zai/glm-4.5v": { "displayName": "GLM 4.5V", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 66000, "maxOutputTokens": 16000, "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
@@ -1798,6 +1854,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1798
1854
|
"zai/glm-5.2": { "displayName": "GLM 5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1799
1855
|
"zai/glm-5.2-fast": { "displayName": "GLM 5.2 Fast", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1800
1856
|
"zai/glm-5.3": { "displayName": "GLM 5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1857
|
+
"zai/glm-5.3-fast": { "displayName": "GLM 5.3 Fast", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
|
|
1801
1858
|
"zai/glm-5.3-flash": { "displayName": "GLM 5.3 Flash", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131000, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1802
1859
|
"zai/glm-5v-turbo": { "displayName": "GLM 5V Turbo", "description": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "lastUpdated": "2026-04-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1803
1860
|
},
|
|
@@ -1809,9 +1866,9 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1809
1866
|
"grok-4.5": { "displayName": "Grok 4.5", "description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1810
1867
|
"grok-4.6": { "displayName": "Grok 4.6", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "knowledgeCutoff": "2026-02-01", "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1811
1868
|
"grok-build-0.1": { "displayName": "Grok Build 0.1", "description": "Fast Grok coding model tuned for agentic engineering and iterative edits", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "structuredOutput": true, "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1812
|
-
"grok-imagine-image": { "displayName": "Grok Imagine Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow":
|
|
1813
|
-
"grok-imagine-image-2.0": { "displayName": "Grok Imagine Image 2.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow":
|
|
1814
|
-
"grok-imagine-image-quality": { "displayName": "Grok Imagine Image Quality", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow":
|
|
1869
|
+
"grok-imagine-image": { "displayName": "Grok Imagine Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 16000, "maxOutputTokens": 0, "lastUpdated": "2026-01-28", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "pdf"], "output": ["image", "pdf"] } },
|
|
1870
|
+
"grok-imagine-image-2.0": { "displayName": "Grok Imagine Image 2.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 64000, "maxOutputTokens": 0, "lastUpdated": "2026-08-07", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "pdf"], "output": ["image", "pdf"] } },
|
|
1871
|
+
"grok-imagine-image-quality": { "displayName": "Grok Imagine Image Quality", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 16000, "maxOutputTokens": 0, "lastUpdated": "2026-04-03", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "pdf"], "output": ["image", "pdf"] } },
|
|
1815
1872
|
"grok-imagine-video": { "displayName": "Grok Imagine Video", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 1024, "maxOutputTokens": 0, "lastUpdated": "2026-01-28", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["video"] } },
|
|
1816
1873
|
"grok-imagine-video-1.5": { "displayName": "Grok Imagine Video 1.5", "description": "Video model for image-to-video generation, editing, and extension workflows", "lifecycle": "active", "contextWindow": 1024, "maxOutputTokens": 0, "lastUpdated": "2026-05-30", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "audio", "pdf"], "output": ["video"] } },
|
|
1817
1874
|
},
|
|
@@ -1930,7 +1987,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
|
|
|
1930
1987
|
"openai/gpt-5": { "displayName": "GPT-5", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 400000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-08-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
|
|
1931
1988
|
"openai/gpt-5-codex": { "displayName": "GPT-5 Codex", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-09-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1932
1989
|
"openai/gpt-5.1": { "displayName": "GPT-5.1", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 400000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["image", "text", "pdf"], "output": ["text"] } },
|
|
1933
|
-
"openai/gpt-5.1-chat": { "displayName": "GPT-5.1 Chat", "description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "lifecycle": "
|
|
1990
|
+
"openai/gpt-5.1-chat": { "displayName": "GPT-5.1 Chat", "description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "lifecycle": "deprecated", "contextWindow": 128000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-13", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
|
|
1934
1991
|
"openai/gpt-5.1-codex": { "displayName": "GPT-5.1-Codex", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
|
|
1935
1992
|
"openai/gpt-5.1-codex-mini": { "displayName": "GPT-5.1-Codex-Mini", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
|
|
1936
1993
|
"openai/gpt-5.2": { "displayName": "GPT-5.2", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 400000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["image", "text", "pdf"], "output": ["text"] } },
|
|
@@ -2024,11 +2081,12 @@ export const GENERATED_MODELS_DEV_MODEL_PROVIDER_OVERRIDES = {
|
|
|
2024
2081
|
"minimax-coding-plan": {},
|
|
2025
2082
|
"mistral": {},
|
|
2026
2083
|
"moonshot": {},
|
|
2084
|
+
"moonshot-global": {},
|
|
2027
2085
|
"nvidia": {},
|
|
2028
2086
|
"ollama-cloud": {},
|
|
2029
2087
|
"openai": {},
|
|
2030
|
-
"opencode": { "claude-3-5-haiku": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-fable-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-haiku-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-1": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-6": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-7": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-8": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4-6": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "gemini-3-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3-pro": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.1-pro": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.5-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.5-flash-lite": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.6-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.7-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gpt-5": { "adapter": { "kind": "openai" } }, "gpt-5-codex": { "adapter": { "kind": "openai" } }, "gpt-5-nano": { "adapter": { "kind": "openai" } }, "gpt-5.1": { "adapter": { "kind": "openai" } }, "gpt-5.1-codex": { "adapter": { "kind": "openai" } }, "gpt-5.1-codex-max": { "adapter": { "kind": "openai" } }, "gpt-5.1-codex-mini": { "adapter": { "kind": "openai" } }, "gpt-5.2": { "adapter": { "kind": "openai" } }, "gpt-5.2-codex": { "adapter": { "kind": "openai" } }, "gpt-5.3-codex": { "adapter": { "kind": "openai" } }, "gpt-5.3-codex-spark": { "adapter": { "kind": "openai" } }, "gpt-5.4": { "adapter": { "kind": "openai" } }, "gpt-5.4-mini": { "adapter": { "kind": "openai" } }, "gpt-5.4-nano": { "adapter": { "kind": "openai" } }, "gpt-5.4-pro": { "adapter": { "kind": "openai" } }, "gpt-5.5": { "adapter": { "kind": "openai" } }, "gpt-5.5-pro": { "adapter": { "kind": "openai" } }, "gpt-5.6-luna": { "adapter": { "kind": "openai" } }, "gpt-5.6-sol": { "adapter": { "kind": "openai" } }, "gpt-5.6-terra": { "adapter": { "kind": "openai" } }, "grok-4.5": { "adapter": { "kind": "openai" } }, "grok-4.6": { "adapter": { "kind": "openai" } }, "grok-build-0.1": { "adapter": { "kind": "openai" } }, "minimax-m2.1-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m2.5-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m3-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "muse-spark-1.2": { "adapter": { "kind": "openai" } }, "muse-spark-1.2-contributor-free": { "adapter": { "kind": "openai" } }, "qwen3.5-plus": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "qwen3.6-plus": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "qwen3.6-plus-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } } },
|
|
2031
|
-
"opencode-go": { "gpt-5.6-luna": { "adapter": { "kind": "openai" } }, "grok-4.5": { "adapter": { "kind": "openai" } }, "grok-4.6": { "adapter": { "kind": "openai" } }, "minimax-m2.5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m2.7": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m3": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "muse-spark-1.2-contributor": { "adapter": { "kind": "openai" } }, "qwen3.8-flash": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } } },
|
|
2088
|
+
"opencode": { "claude-3-5-haiku": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-fable-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-fable-5-1": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-haiku-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-1": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-6": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-7": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-8": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4-6": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "gemini-3-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3-pro": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.1-pro": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.5-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.5-flash-lite": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.6-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.7-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.8-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gpt-5": { "adapter": { "kind": "openai" } }, "gpt-5-codex": { "adapter": { "kind": "openai" } }, "gpt-5-nano": { "adapter": { "kind": "openai" } }, "gpt-5.1": { "adapter": { "kind": "openai" } }, "gpt-5.1-codex": { "adapter": { "kind": "openai" } }, "gpt-5.1-codex-max": { "adapter": { "kind": "openai" } }, "gpt-5.1-codex-mini": { "adapter": { "kind": "openai" } }, "gpt-5.2": { "adapter": { "kind": "openai" } }, "gpt-5.2-codex": { "adapter": { "kind": "openai" } }, "gpt-5.3-codex": { "adapter": { "kind": "openai" } }, "gpt-5.3-codex-spark": { "adapter": { "kind": "openai" } }, "gpt-5.4": { "adapter": { "kind": "openai" } }, "gpt-5.4-mini": { "adapter": { "kind": "openai" } }, "gpt-5.4-nano": { "adapter": { "kind": "openai" } }, "gpt-5.4-pro": { "adapter": { "kind": "openai" } }, "gpt-5.5": { "adapter": { "kind": "openai" } }, "gpt-5.5-pro": { "adapter": { "kind": "openai" } }, "gpt-5.6-luna": { "adapter": { "kind": "openai" } }, "gpt-5.6-sol": { "adapter": { "kind": "openai" } }, "gpt-5.6-terra": { "adapter": { "kind": "openai" } }, "gpt-6-astra": { "adapter": { "kind": "openai" } }, "grok-4.5": { "adapter": { "kind": "openai" } }, "grok-4.6": { "adapter": { "kind": "openai" } }, "grok-build-0.1": { "adapter": { "kind": "openai" } }, "minimax-m2.1-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m2.5-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m3-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "muse-spark-1.2": { "adapter": { "kind": "openai" } }, "muse-spark-1.2-contributor-free": { "adapter": { "kind": "openai" } }, "muse-spark-1.3": { "adapter": { "kind": "openai" } }, "muse-spark-1.3-contributor-free": { "adapter": { "kind": "openai" } }, "qwen3.5-plus": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "qwen3.6-plus": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "qwen3.6-plus-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } } },
|
|
2089
|
+
"opencode-go": { "gpt-5.6-luna": { "adapter": { "kind": "openai" } }, "grok-4.5": { "adapter": { "kind": "openai" } }, "grok-4.6": { "adapter": { "kind": "openai" } }, "minimax-m2.5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m2.7": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m3": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "muse-spark-1.2-contributor": { "adapter": { "kind": "openai" } }, "muse-spark-1.3-contributor": { "adapter": { "kind": "openai" } }, "qwen3.8-flash": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } } },
|
|
2032
2090
|
"openrouter": {},
|
|
2033
2091
|
"siliconflow": {},
|
|
2034
2092
|
"stepfun": {},
|
|
@@ -2067,12 +2125,13 @@ export const GENERATED_MODELS_DEV_PROVIDER_FACTS = {
|
|
|
2067
2125
|
"google": { "id": "google", "name": "Google", "doc": "https://ai.google.dev/gemini-api/docs/models" },
|
|
2068
2126
|
"groq": { "id": "groq", "name": "Groq", "doc": "https://console.groq.com/docs/models" },
|
|
2069
2127
|
"huggingface": { "id": "huggingface", "name": "Hugging Face", "api": "https://router.huggingface.co/v1", "doc": "https://huggingface.co/docs/inference-providers" },
|
|
2070
|
-
"kimi-coding-plan": { "id": "kimi-for-coding", "name": "Kimi For Coding", "api": "https://api.kimi.com/coding/v1", "doc": "https://www.kimi.com/code/docs/en/
|
|
2128
|
+
"kimi-coding-plan": { "id": "kimi-for-coding", "name": "Kimi For Coding", "api": "https://api.kimi.com/coding/v1", "doc": "https://www.kimi.com/code/docs/en/kimi-code/models.html" },
|
|
2071
2129
|
"MiniMax": { "id": "minimax", "name": "MiniMax (minimax.io)", "api": "https://api.minimax.io/anthropic/v1", "doc": "https://platform.minimax.io/docs/guides/quickstart" },
|
|
2072
2130
|
"MiniMax-cn": { "id": "minimax-cn", "name": "MiniMax (minimaxi.com)", "api": "https://api.minimaxi.com/anthropic/v1", "doc": "https://platform.minimaxi.com/docs/guides/quickstart" },
|
|
2073
2131
|
"minimax-coding-plan": { "id": "minimax-coding-plan", "name": "MiniMax Token Plan (minimax.io)", "api": "https://api.minimax.io/anthropic/v1", "doc": "https://platform.minimax.io/docs/token-plan/intro" },
|
|
2074
2132
|
"mistral": { "id": "mistral", "name": "Mistral", "doc": "https://docs.mistral.ai/getting-started/models/" },
|
|
2075
2133
|
"moonshot": { "id": "moonshotai-cn", "name": "Moonshot AI (China)", "api": "https://api.moonshot.cn/v1", "doc": "https://platform.moonshot.cn/docs/api/chat" },
|
|
2134
|
+
"moonshot-global": { "id": "moonshotai", "name": "Moonshot AI", "api": "https://api.moonshot.ai/v1", "doc": "https://platform.moonshot.ai/docs/api/chat" },
|
|
2076
2135
|
"nvidia": { "id": "nvidia", "name": "Nvidia", "api": "https://integrate.api.nvidia.com/v1", "doc": "https://docs.api.nvidia.com/nim/" },
|
|
2077
2136
|
"ollama-cloud": { "id": "ollama-cloud", "name": "Ollama Cloud", "api": "https://ollama.com/v1", "doc": "https://docs.ollama.com/cloud" },
|
|
2078
2137
|
"openai": { "id": "openai", "name": "OpenAI", "doc": "https://platform.openai.com/docs/models" },
|