maka-agent 0.2.0-dev.43.20260919 → 0.2.0-dev.45.20260921

package/node_modules/@maka/core/dist/model-metadata.generated.js

@@ -76,8 +76,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "deepseek-r1": { "displayName": "DeepSeek R1", "description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2025-01-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-r1-0528": { "displayName": "DeepSeek R1 0528", "description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2025-05-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-r1-distill-llama-70b": { "displayName": "DeepSeek R1 Distill Llama 70B", "description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2025-01-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek-r1-distill-llama-8b": { "displayName": "DeepSeek R1 Distill Llama 8B", "description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2025-01-01", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek-r1-distill-qwen-1-5b": { "displayName": "DeepSeek R1 Distill Qwen 1.5B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2025-01-01", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "deepseek-r1-distill-llama-8b": { "displayName": "DeepSeek R1 Distill Llama 8B", "description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2025-01-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "deepseek-r1-distill-qwen-1-5b": { "displayName": "DeepSeek R1 Distill Qwen 1.5B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2025-01-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-r1-distill-qwen-14b": { "displayName": "DeepSeek R1 Distill Qwen 14B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2025-01-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-r1-distill-qwen-32b": { "displayName": "DeepSeek R1 Distill Qwen 32B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2025-01-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-r1-distill-qwen-7b": { "displayName": "DeepSeek R1 Distill Qwen 7B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2025-01-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -162,89 +162,89 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "tongyi-intent-detect-v3": { "displayName": "Tongyi Intent Detect V3", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1024, "knowledgeCutoff": "2024-04", "lastUpdated": "2024-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
     },
     "alibaba-coding-plan-cn": {
-        "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", "lastUpdated": "2025-12-22", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "glm-5": { "displayName": "GLM-5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 16384, "lastUpdated": "2026-02-11", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "kimi-k2.5": { "displayName": "Kimi K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "MiniMax-M2.5": { "displayName": "MiniMax-M2.5", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 196608, "maxOutputTokens": 24576, "lastUpdated": "2026-02-12", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3-coder-next": { "displayName": "Qwen3 Coder Next", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-03", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3-coder-plus": { "displayName": "Qwen3 Coder Plus", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3-max-2026-01-23": { "displayName": "Qwen3 Max", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-23", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3.5-plus": { "displayName": "Qwen3.5 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "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", "lastUpdated": "2025-12-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "glm-5": { "displayName": "GLM-5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 16384, "lastUpdated": "2026-02-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "kimi-k2.5": { "displayName": "Kimi K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "MiniMax-M2.5": { "displayName": "MiniMax-M2.5", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 196608, "maxOutputTokens": 24576, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen3-coder-next": { "displayName": "Qwen3 Coder Next", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-03", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen3-coder-plus": { "displayName": "Qwen3 Coder Plus", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen3-max-2026-01-23": { "displayName": "Qwen3 Max", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen3.5-plus": { "displayName": "Qwen3.5 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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"] } },
-        "qwen3.6-plus": { "displayName": "Qwen3.6 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "qwen3.6-plus": { "displayName": "Qwen3.6 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "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"] } },
         "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": 65536, "lastUpdated": "2026-05-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3.7-plus": { "displayName": "Qwen3.7 Plus", "description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "qwen3.7-plus": { "displayName": "Qwen3.7 Plus", "description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
     },
     "alibaba-coding-plan": {
-        "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", "lastUpdated": "2025-12-22", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "glm-5": { "displayName": "GLM-5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 16384, "lastUpdated": "2026-02-11", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "kimi-k2.5": { "displayName": "Kimi K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "MiniMax-M2.5": { "displayName": "MiniMax-M2.5", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 196608, "inputLimit": 196601, "maxOutputTokens": 24576, "lastUpdated": "2026-02-12", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3-coder-next": { "displayName": "Qwen3 Coder Next", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-03", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3-coder-plus": { "displayName": "Qwen3 Coder Plus", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3-max-2026-01-23": { "displayName": "Qwen3 Max", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-23", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3.5-plus": { "displayName": "Qwen3.5 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "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", "lastUpdated": "2025-12-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "glm-5": { "displayName": "GLM-5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 16384, "lastUpdated": "2026-02-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "kimi-k2.5": { "displayName": "Kimi K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "MiniMax-M2.5": { "displayName": "MiniMax-M2.5", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 196608, "inputLimit": 196601, "maxOutputTokens": 24576, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen3-coder-next": { "displayName": "Qwen3 Coder Next", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-03", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen3-coder-plus": { "displayName": "Qwen3 Coder Plus", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen3-max-2026-01-23": { "displayName": "Qwen3 Max", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen3.5-plus": { "displayName": "Qwen3.5 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "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"] } },
         "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"] } },
-        "qwen3.6-plus": { "displayName": "Qwen3.6 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "qwen3.6-plus": { "displayName": "Qwen3.6 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "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"] } },
         "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": 65536, "lastUpdated": "2026-05-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3.7-plus": { "displayName": "Qwen3.7 Plus", "description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "qwen3.7-plus": { "displayName": "Qwen3.7 Plus", "description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
     },
     "alibaba-token-plan-cn": {
-        "deepseek-v3.2": { "displayName": "DeepSeek V3.2", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-12-05", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "happyhorse-1.1-i2v": { "displayName": "HappyHorse 1.1 Image-to-Video", "description": "Video model for image-to-video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["video"] } },
-        "happyhorse-1.1-r2v": { "displayName": "HappyHorse 1.1 Reference-to-Video", "description": "Video model for reference-guided video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["video"] } },
-        "happyhorse-1.1-t2v": { "displayName": "HappyHorse 1.1 Text-to-Video", "description": "Video model for prompt-driven text-to-video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
-        "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": 98304, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-01", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "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", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "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", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "MiniMax-M2.5": { "displayName": "MiniMax-M2.5", "description": "Prior MiniMax coding model for agent workflows, office edits, and automation", "lifecycle": "active", "contextWindow": 196608, "inputLimit": 196601, "maxOutputTokens": 32768, "lastUpdated": "2026-02-12", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen-image-2.0": { "displayName": "Qwen Image 2.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-03-03", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
-        "qwen-image-2.0-pro": { "displayName": "Qwen Image 2.0 Pro", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-03-03", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
-        "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", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "qwen3.6-plus": { "displayName": "Qwen3.6 Plus", "description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-04-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "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", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "wan2.7-image": { "displayName": "Wan2.7 Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-05-29", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
-        "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, "lastUpdated": "2026-05-29", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
+        "deepseek-v3.2": { "displayName": "DeepSeek V3.2", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-12-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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"] } },
+        "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"] } },
+        "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"] } },
+        "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"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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"] } },
+        "happyhorse-1.1-i2v": { "displayName": "HappyHorse 1.1 Image-to-Video", "description": "Video model for image-to-video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["video"] } },
+        "happyhorse-1.1-r2v": { "displayName": "HappyHorse 1.1 Reference-to-Video", "description": "Video model for reference-guided video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["video"] } },
+        "happyhorse-1.1-t2v": { "displayName": "HappyHorse 1.1 Text-to-Video", "description": "Video model for prompt-driven text-to-video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
+        "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": 98304, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "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"] } },
+        "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"] } },
+        "MiniMax-M2.5": { "displayName": "MiniMax-M2.5", "description": "Prior MiniMax coding model for agent workflows, office edits, and automation", "lifecycle": "active", "contextWindow": 196608, "inputLimit": 196601, "maxOutputTokens": 32768, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen-image-2.0": { "displayName": "Qwen Image 2.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-03-03", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
+        "qwen-image-2.0-pro": { "displayName": "Qwen Image 2.0 Pro", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-03-03", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
+        "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"] } },
+        "qwen3.6-plus": { "displayName": "Qwen3.6 Plus", "description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "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": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "wan2.7-image": { "displayName": "Wan2.7 Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-05-29", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
+        "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, "lastUpdated": "2026-05-29", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
     },
     "alibaba-token-plan": {
-        "deepseek-v3.2": { "displayName": "DeepSeek V3.2", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-12-05", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "happyhorse-1.1-i2v": { "displayName": "HappyHorse 1.1 Image-to-Video", "description": "Video model for image-to-video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["video"] } },
-        "happyhorse-1.1-r2v": { "displayName": "HappyHorse 1.1 Reference-to-Video", "description": "Video model for reference-guided video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["video"] } },
-        "happyhorse-1.1-t2v": { "displayName": "HappyHorse 1.1 Text-to-Video", "description": "Video model for prompt-driven text-to-video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
-        "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": 98304, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-01", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "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", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "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", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "MiniMax-M2.5": { "displayName": "MiniMax-M2.5", "description": "Prior MiniMax coding model for agent workflows, office edits, and automation", "lifecycle": "active", "contextWindow": 196608, "inputLimit": 196601, "maxOutputTokens": 32768, "lastUpdated": "2026-02-12", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen-image-2.0": { "displayName": "Qwen Image 2.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-03-03", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
-        "qwen-image-2.0-pro": { "displayName": "Qwen Image 2.0 Pro", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-03-03", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
-        "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", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "qwen3.6-plus": { "displayName": "Qwen3.6 Plus", "description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-04-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "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", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "wan2.7-image": { "displayName": "Wan2.7 Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-05-29", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
-        "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, "lastUpdated": "2026-05-29", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
+        "deepseek-v3.2": { "displayName": "DeepSeek V3.2", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-12-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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"] } },
+        "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"] } },
+        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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"] } },
+        "happyhorse-1.1-i2v": { "displayName": "HappyHorse 1.1 Image-to-Video", "description": "Video model for image-to-video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["video"] } },
+        "happyhorse-1.1-r2v": { "displayName": "HappyHorse 1.1 Reference-to-Video", "description": "Video model for reference-guided video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["video"] } },
+        "happyhorse-1.1-t2v": { "displayName": "HappyHorse 1.1 Text-to-Video", "description": "Video model for prompt-driven text-to-video generation", "lifecycle": "active", "lastUpdated": "2026-07-17", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
+        "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": 98304, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "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"] } },
+        "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"] } },
+        "MiniMax-M2.5": { "displayName": "MiniMax-M2.5", "description": "Prior MiniMax coding model for agent workflows, office edits, and automation", "lifecycle": "active", "contextWindow": 196608, "inputLimit": 196601, "maxOutputTokens": 32768, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen-image-2.0": { "displayName": "Qwen Image 2.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-03-03", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
+        "qwen-image-2.0-pro": { "displayName": "Qwen Image 2.0 Pro", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-03-03", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
+        "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"] } },
+        "qwen3.6-plus": { "displayName": "Qwen3.6 Plus", "description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "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": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "wan2.7-image": { "displayName": "Wan2.7 Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 8192, "lastUpdated": "2026-05-29", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
+        "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, "lastUpdated": "2026-05-29", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
     },
     "cerebras": {
         "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"] } },
@@ -264,7 +264,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "command-r-plus-08-2024": { "displayName": "Command R+", "description": "Cohere's RAG workhorse for long-context enterprise search and tool use", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4000, "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-08-30", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "command-r7b-12-2024": { "displayName": "Command R7B", "description": "Cohere retrieval model for long-context chat and enterprise RAG workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4000, "knowledgeCutoff": "2024-06-01", "lastUpdated": "2024-12-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "command-r7b-arabic-02-2025": { "displayName": "Command R7B Arabic", "description": "Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4000, "knowledgeCutoff": "2024-06-01", "lastUpdated": "2025-02-27", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "north-mini-code-1-0": { "displayName": "North Mini Code", "description": "Cohere coding model for practical software engineering and agentic edits", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-09-23", "structuredOutput": true, "lastUpdated": "2026-06-09", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "north-mini-code-1-0": { "displayName": "North Mini Code", "description": "Cohere coding model for practical software engineering and agentic edits", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-09-23", "structuredOutput": true, "lastUpdated": "2026-06-09", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
     },
     "cloudflare-workers-ai": {
         "@cf/aisingapore/gemma-sea-lion-v4-27b-it": { "displayName": "Gemma Sea Lion V4 27B It", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "structuredOutput": false, "lastUpdated": "2025-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -461,14 +461,14 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "gemini-omni-flash-preview": { "displayName": "Gemini Omni Flash Preview", "description": "Video generation and editing model for fast, conversational text- and image-to-video workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text", "image", "video"], "output": ["video"] } },
         "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"] } },
         "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"], "output": ["text"] } },
-        "lyria-3-clip-preview": { "displayName": "Lyria 3 Clip Preview", "description": "Music generation model for short 30-second clips, loops, and previews from text or image prompts", "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"] } },
-        "lyria-3-pro-preview": { "displayName": "Lyria 3 Pro Preview", "description": "Music generation model for full-length songs from text or images with vocals and structure", "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"] } },
+        "lyria-3-clip-preview": { "displayName": "Lyria 3 Clip Preview", "description": "Music generation model for short 30-second clips, loops, and previews from text or image prompts", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "structuredOutput": false, "lastUpdated": "2026-03-25", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "audio"] } },
+        "lyria-3-pro-preview": { "displayName": "Lyria 3 Pro Preview", "description": "Music generation model for full-length songs from text or images with vocals and structure", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "structuredOutput": false, "lastUpdated": "2026-03-25", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "audio"] } },
         "veo-3.1-fast-generate-preview": { "displayName": "Veo 3.1 fast", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 480, "maxOutputTokens": 8192, "lastUpdated": "2026-01-01", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "video"], "output": ["video"] } },
         "veo-3.1-generate-preview": { "displayName": "Veo 3.1", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "beta", "contextWindow": 480, "maxOutputTokens": 8192, "lastUpdated": "2026-01", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
         "veo-3.1-lite-generate-preview": { "displayName": "Veo 3.1 lite", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "contextWindow": 480, "maxOutputTokens": 8192, "lastUpdated": "2026-03-31", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
     },
     "groq": {
-        "allam-2-7b": { "displayName": "ALLaM-2-7b", "description": "ALLaM-2-7b instruction tuned model by SDAIA", "lifecycle": "active", "contextWindow": 4096, "maxOutputTokens": 4096, "lastUpdated": "2025-01-23", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "allam-2-7b": { "displayName": "ALLaM-2-7b", "description": "ALLaM-2-7b instruction tuned model by SDAIA", "lifecycle": "active", "contextWindow": 4096, "maxOutputTokens": 4096, "lastUpdated": "2025-01-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "canopylabs/orpheus-arabic-saudi": { "displayName": "Canopy Labs Orpheus Arabic Saudi", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "beta", "contextWindow": 4000, "maxOutputTokens": 50000, "lastUpdated": "2025-12-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
         "canopylabs/orpheus-v1-english": { "displayName": "Canopy Labs Orpheus V1 English", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "beta", "contextWindow": 4000, "maxOutputTokens": 50000, "lastUpdated": "2025-12-19", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
         "groq/compound": { "displayName": "Compound", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 8192, "lastUpdated": "2025-09-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -557,7 +557,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "zai-org/GLM-4.6": { "displayName": "GLM-4.6", "description": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-30", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai-org/GLM-4.6V-Flash": { "displayName": "GLM-4.6V-Flash", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "lastUpdated": "2025-12-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "zai-org/GLM-4.7": { "displayName": "GLM-4.7", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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": 200000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-08", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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": 200000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-08", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai-org/GLM-5": { "displayName": "GLM-5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 131072, "lastUpdated": "2026-02-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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": 131072, "lastUpdated": "2026-04-03", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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": 131072, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -565,10 +565,10 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "zai-org/GLM-5.3-Flash": { "displayName": "GLM-5.3-Flash", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "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"], "output": ["text"] } },
     },
     "kimi-coding-plan": {
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
+        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
     },
     "MiniMax": {
         "MiniMax-M2": { "displayName": "MiniMax-M2", "description": "Efficient open MiniMax model built for coding agents and tool-heavy workflows", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2025-10-27", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -589,13 +589,13 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "MiniMax-M3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 512000, "lastUpdated": "2026-06-25", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
     },
     "minimax-coding-plan": {
-        "MiniMax-M2": { "displayName": "MiniMax-M2", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2025-10-27", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "MiniMax-M2.1": { "displayName": "MiniMax-M2.1", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2025-12-23", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "MiniMax-M2.5": { "displayName": "MiniMax-M2.5", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-02-12", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "MiniMax-M2.5-highspeed": { "displayName": "MiniMax-M2.5-highspeed", "description": "High-speed MiniMax model for low-latency coding and agent workflows", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-02-13", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "MiniMax-M2.7": { "displayName": "MiniMax-M2.7", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "MiniMax-M2.7-highspeed": { "displayName": "MiniMax-M2.7-highspeed", "description": "High-speed MiniMax model for low-latency coding and agent workflows", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "MiniMax-M3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 512000, "lastUpdated": "2026-06-25", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "MiniMax-M2": { "displayName": "MiniMax-M2", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2025-10-27", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "MiniMax-M2.1": { "displayName": "MiniMax-M2.1", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2025-12-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "MiniMax-M2.5": { "displayName": "MiniMax-M2.5", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "MiniMax-M2.5-highspeed": { "displayName": "MiniMax-M2.5-highspeed", "description": "High-speed MiniMax model for low-latency coding and agent workflows", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-02-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "MiniMax-M2.7": { "displayName": "MiniMax-M2.7", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "MiniMax-M2.7-highspeed": { "displayName": "MiniMax-M2.7-highspeed", "description": "High-speed MiniMax model for low-latency coding and agent workflows", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "MiniMax-M3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 512000, "lastUpdated": "2026-06-25", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
     },
     "mistral": {
         "codestral-latest": { "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"] } },
@@ -605,7 +605,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "devstral-medium-latest": { "displayName": "Devstral 2 (latest)", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "devstral-small-2505": { "displayName": "Devstral Small 2505", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 128000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-07", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "devstral-small-2507": { "displayName": "Devstral Small", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 128000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-05", "lastUpdated": "2025-07-10", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "labs-devstral-small-2512": { "displayName": "Devstral Small 2", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-09", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "labs-devstral-small-2512": { "displayName": "Devstral Small 2", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-12", "lastUpdated": "2025-12-09", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "magistral-medium-latest": { "displayName": "Magistral Medium (latest)", "description": "Mistral reasoning model for transparent analysis, math, and complex decisions", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-06", "lastUpdated": "2025-03-20", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "magistral-small": { "displayName": "Magistral Small", "description": "Mistral reasoning model for transparent analysis, math, and complex decisions", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-06", "lastUpdated": "2025-03-17", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "ministral-3b-latest": { "displayName": "Ministral 3B (latest)", "description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-10", "lastUpdated": "2024-10-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -646,110 +646,110 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
     },
     "nvidia": {
-        "abacusai/dracarys-llama-3.1-70b-instruct": { "displayName": "dracarys-llama-3.1-70b-instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-05-22", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "baai/bge-m3": { "displayName": "BGE M3", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1024, "lastUpdated": "2026-04-30", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "black-forest-labs/flux_1-kontext-dev": { "displayName": "FLUX.1-Kontext-dev", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 40960, "maxOutputTokens": 40960, "lastUpdated": "2025-08-12", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["image"] } },
-        "black-forest-labs/flux_1-schnell": { "displayName": "FLUX.1-schnell", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 77, "inputLimit": 77, "knowledgeCutoff": "2024-07", "structuredOutput": false, "lastUpdated": "2026-02-04", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
-        "black-forest-labs/flux_2-klein-4b": { "displayName": "FLUX.2 Klein 4B", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 40960, "maxOutputTokens": 40960, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-01-31", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["image"] } },
-        "black-forest-labs/flux.1-dev": { "displayName": "FLUX.1-dev", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 4096, "knowledgeCutoff": "2024-08", "lastUpdated": "2025-09-05", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
-        "bytedance/seed-oss-36b-instruct": { "displayName": "ByteDance-Seed/Seed-OSS-36B-Instruct", "description": "Tool-capable chat model for instruction following and agentic application workflows", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2025-11-25", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "abacusai/dracarys-llama-3.1-70b-instruct": { "displayName": "dracarys-llama-3.1-70b-instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-05-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "baai/bge-m3": { "displayName": "BGE M3", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1024, "lastUpdated": "2026-04-30", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "black-forest-labs/flux_1-kontext-dev": { "displayName": "FLUX.1-Kontext-dev", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 40960, "maxOutputTokens": 40960, "lastUpdated": "2025-08-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["image"] } },
+        "black-forest-labs/flux_1-schnell": { "displayName": "FLUX.1-schnell", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 77, "inputLimit": 77, "knowledgeCutoff": "2024-07", "structuredOutput": false, "lastUpdated": "2026-02-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
+        "black-forest-labs/flux_2-klein-4b": { "displayName": "FLUX.2 Klein 4B", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 40960, "maxOutputTokens": 40960, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-01-31", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["image"] } },
+        "black-forest-labs/flux.1-dev": { "displayName": "FLUX.1-dev", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 4096, "knowledgeCutoff": "2024-08", "lastUpdated": "2025-09-05", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
+        "bytedance/seed-oss-36b-instruct": { "displayName": "ByteDance-Seed/Seed-OSS-36B-Instruct", "description": "Tool-capable chat model for instruction following and agentic application workflows", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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": 393216, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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": ["none", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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": ["none", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "google/gemma-2-2b-it": { "displayName": "Gemma 2 2b It", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2024-07-16", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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, "lastUpdated": "2025-03-12", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "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, "lastUpdated": "2025-03-12", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "google/gemma-3n-e2b-it": { "displayName": "Gemma 3n E2b It", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-06", "structuredOutput": true, "lastUpdated": "2025-06-12", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "google/gemma-3n-e4b-it": { "displayName": "Gemma 3n E4b It", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-06", "structuredOutput": true, "lastUpdated": "2025-06-03", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "google/gemma-4-31b-it": { "displayName": "Gemma-4-31B-IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "google/google-paligemma": { "displayName": "paligemma", "description": "Gemini multimodal model for text, image, audio, video, and document tasks", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2024-08-26", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "meta/esm2-650m": { "displayName": "esm2-650m", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-03-10", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "meta/esmfold": { "displayName": "esmfold", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-06-12", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "meta/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": 128000, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2024-07-16", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "meta/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": 16000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-12", "lastUpdated": "2025-01-01", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "meta/llama-3.2-11b-vision-instruct": { "displayName": "Llama 3.2 11b Vision Instruct", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-12", "structuredOutput": true, "lastUpdated": "2024-09-18", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "meta/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": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-12", "structuredOutput": true, "lastUpdated": "2024-09-18", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "meta/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": 32768, "maxOutputTokens": 32000, "structuredOutput": true, "lastUpdated": "2024-09-18", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "meta/llama-3.2-90b-vision-instruct": { "displayName": "Llama-3.2-90B-Vision-Instruct", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "meta/llama-3.3-70b-instruct": { "displayName": "Llama 3.3 70b Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2024-11-26", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "meta/llama-4-maverick-17b-128e-instruct": { "displayName": "Llama 4 Maverick 17b 128e Instruct", "description": "Open multimodal Llama model for strong reasoning and fast responses", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-02", "structuredOutput": true, "lastUpdated": "2025-04-01", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "meta/llama-guard-4-12b": { "displayName": "Llama Guard 4 12B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 16384, "lastUpdated": "2026-04-30", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "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": 131072, "knowledgeCutoff": "2026-01-04", "structuredOutput": true, "lastUpdated": "2026-08-10", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "microsoft/phi-4-mini-instruct": { "displayName": "Phi-4-Mini", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-12", "lastUpdated": "2025-09-05", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "microsoft/phi-4-multimodal-instruct": { "displayName": "Phi 4 Multimodal", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 128000, "inputLimit": 128000, "maxOutputTokens": 16384, "structuredOutput": false, "lastUpdated": "2025-07-26", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "minimaxai/minimax-m2.7": { "displayName": "MiniMax-M2.7", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-04-11", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "minimaxai/minimax-m3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 16384, "lastUpdated": "2026-06-01", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "mistralai/magistral-small-2506": { "displayName": "Magistral Small 2506", "description": "Mistral reasoning model for transparent analysis, math, and complex decisions", "lifecycle": "active", "contextWindow": 32768, "inputLimit": 32768, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2025-09-25", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mistralai/ministral-14b-instruct-2512": { "displayName": "Ministral 3 14B Instruct 2512", "description": "Compact Mistral VLM for chat and instruction-based workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "lastUpdated": "2025-12-02", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistralai/mistral-7b-instruct-v0.3": { "displayName": "Mistral-7B-Instruct-v0.3", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2025-04-01", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mistralai/mistral-large-3-675b-instruct-2512": { "displayName": "Mistral Large 3 675B Instruct 2512", "description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-12-02", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistralai/mistral-medium-3-instruct": { "displayName": "Mistral Medium 3", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 131072, "inputLimit": 131072, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2025-09-25", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistralai/mistral-medium-3.5-128b": { "displayName": "Mistral Medium 3.5", "description": "Balanced Mistral model for enterprise assistants, multilingual work, and tools", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-04-29", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistralai/mistral-nemotron": { "displayName": "mistral-nemotron", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-06-12", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mistralai/mistral-small-4-119b-2603": { "displayName": "mistral-small-4-119b-2603", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "structuredOutput": true, "lastUpdated": "2026-03-16", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistralai/mixtral-8x22b-instruct": { "displayName": "Mistral: Mixtral 8x22B Instruct", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 13108, "lastUpdated": "2024-04-17", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mistralai/mixtral-8x7b-instruct": { "displayName": "Mistral: Mixtral 8x7B Instruct", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2026-03-15", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "moonshotai/kimi-k2-instruct-0905": { "displayName": "Kimi K2 0905", "description": "Kimi model for long-context chat, coding, and agentic reasoning", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09-05", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "moonshotai/kimi-k2.6": { "displayName": "Kimi K2.6", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-04-21", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "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", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "nvidia/active-speaker-detection": { "displayName": "Active Speaker Detection", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2026-04-16", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["video"], "output": ["text"] } },
-        "nvidia/bevformer": { "displayName": "bevformer", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-07-20", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["video"], "output": ["text"] } },
-        "nvidia/cosmos-predict1-5b": { "displayName": "cosmos-predict1-5b", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2025-03-18", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "video"], "output": ["video"] } },
-        "nvidia/cosmos-reason2-8b": { "displayName": "Cosmos Reason2 8B", "description": "Vision language model for physical-world understanding with structured reasoning on video and images", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2025-12-01", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "nvidia/cosmos-transfer1-7b": { "displayName": "cosmos-transfer1-7b", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2025-06-30", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "video"], "output": ["video"] } },
-        "nvidia/cosmos-transfer2_5-2b": { "displayName": "cosmos-transfer2.5-2b", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2026-02-26", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "video"], "output": ["video"] } },
-        "nvidia/gliner-pii": { "displayName": "gliner-pii", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2026-03-03", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/llama-3_2-nemoretriever-300m-embed-v1": { "displayName": "llama-3_2-nemoretriever-300m-embed-v1", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 2048, "lastUpdated": "2025-07-24", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/llama-3.1-nemotron-70b-instruct": { "displayName": "Llama 3.1 Nemotron 70B Instruct", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-04-15", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/llama-3.1-nemotron-nano-8b-v1": { "displayName": "Llama 3.1 Nemotron Nano 8B v1", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2025-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/llama-3.1-nemotron-nano-vl-8b-v1": { "displayName": "Llama 3.1 Nemotron Nano VL 8B v1", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2025-04-10", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "nvidia/llama-3.1-nemotron-safety-guard-8b-v3": { "displayName": "llama-3.1-nemotron-safety-guard-8b-v3", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2025-10-28", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/llama-3.1-nemotron-ultra-253b-v1": { "displayName": "Llama 3.1 Nemotron Ultra 253B", "description": "Flagship Nemotron model for high-throughput reasoning and complex agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 16384, "lastUpdated": "2025-04-07", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/llama-3.3-nemotron-super-49b-v1": { "displayName": "Llama 3.3 Nemotron Super 49B v1", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "lastUpdated": "2025-04-07", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/llama-3.3-nemotron-super-49b-v1.5": { "displayName": "Llama 3.3 Nemotron Super 49B v1.5", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "lastUpdated": "2025-07-25", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/llama-nemotron-embed-vl-1b-v2": { "displayName": "llama-nemotron-embed-vl-1b-v2", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 2048, "lastUpdated": "2026-02-10", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "nvidia/llama-nemotron-rerank-vl-1b-v2": { "displayName": "llama-nemotron-rerank-vl-1b-v2", "description": "Reranking model for improving retrieval quality in search and recommendation systems", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2026-03-31", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "nvidia/magpie-tts-zeroshot": { "displayName": "magpie-tts-zeroshot", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2025-06-12", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "audio"], "output": ["audio"] } },
-        "nvidia/nemotron-3-content-safety": { "displayName": "nemotron-3-content-safety", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2026-04-16", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-09", "lastUpdated": "2024-12", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": { "displayName": "Nemotron 3 Nano Omni", "description": "Open Nemotron omni model combining reasoning with text, vision, and audio", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-04-28", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video", "audio"], "output": ["text"] } },
+        "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": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "google/gemma-2-2b-it": { "displayName": "Gemma 2 2b It", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2024-07-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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, "lastUpdated": "2025-03-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "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, "lastUpdated": "2025-03-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "google/gemma-3n-e2b-it": { "displayName": "Gemma 3n E2b It", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-06", "structuredOutput": true, "lastUpdated": "2025-06-12", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "google/gemma-3n-e4b-it": { "displayName": "Gemma 3n E4b It", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-06", "structuredOutput": true, "lastUpdated": "2025-06-03", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "google/gemma-4-31b-it": { "displayName": "Gemma-4-31B-IT", "description": "Open Gemma instruction model for efficient chat and self-hosted deployments", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "google/google-paligemma": { "displayName": "paligemma", "description": "Gemini multimodal model for text, image, audio, video, and document tasks", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2024-08-26", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "meta/esm2-650m": { "displayName": "esm2-650m", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-03-10", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "meta/esmfold": { "displayName": "esmfold", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-06-12", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "meta/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": 128000, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2024-07-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "meta/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": 16000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-12", "lastUpdated": "2025-01-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "meta/llama-3.2-11b-vision-instruct": { "displayName": "Llama 3.2 11b Vision Instruct", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-12", "structuredOutput": true, "lastUpdated": "2024-09-18", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "meta/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": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-12", "structuredOutput": true, "lastUpdated": "2024-09-18", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "meta/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": 32768, "maxOutputTokens": 32000, "structuredOutput": true, "lastUpdated": "2024-09-18", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "meta/llama-3.2-90b-vision-instruct": { "displayName": "Llama-3.2-90B-Vision-Instruct", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "knowledgeCutoff": "2023-12", "lastUpdated": "2024-09-25", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "meta/llama-3.3-70b-instruct": { "displayName": "Llama 3.3 70b Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2024-11-26", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "meta/llama-4-maverick-17b-128e-instruct": { "displayName": "Llama 4 Maverick 17b 128e Instruct", "description": "Open multimodal Llama model for strong reasoning and fast responses", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-02", "structuredOutput": true, "lastUpdated": "2025-04-01", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "meta/llama-guard-4-12b": { "displayName": "Llama Guard 4 12B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 16384, "lastUpdated": "2026-04-30", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "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": 131072, "knowledgeCutoff": "2026-01-04", "structuredOutput": true, "lastUpdated": "2026-08-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "microsoft/phi-4-mini-instruct": { "displayName": "Phi-4-Mini", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-12", "lastUpdated": "2025-09-05", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "microsoft/phi-4-multimodal-instruct": { "displayName": "Phi 4 Multimodal", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 128000, "inputLimit": 128000, "maxOutputTokens": 16384, "structuredOutput": false, "lastUpdated": "2025-07-26", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "minimaxai/minimax-m2.7": { "displayName": "MiniMax-M2.7", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-04-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "minimaxai/minimax-m3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 16384, "lastUpdated": "2026-06-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "mistralai/magistral-small-2506": { "displayName": "Magistral Small 2506", "description": "Mistral reasoning model for transparent analysis, math, and complex decisions", "lifecycle": "active", "contextWindow": 32768, "inputLimit": 32768, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2025-09-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mistralai/ministral-14b-instruct-2512": { "displayName": "Ministral 3 14B Instruct 2512", "description": "Compact Mistral VLM for chat and instruction-based workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "mistralai/mistral-7b-instruct-v0.3": { "displayName": "Mistral-7B-Instruct-v0.3", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2025-04-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mistralai/mistral-large-3-675b-instruct-2512": { "displayName": "Mistral Large 3 675B Instruct 2512", "description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "mistralai/mistral-medium-3-instruct": { "displayName": "Mistral Medium 3", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 131072, "inputLimit": 131072, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2025-09-25", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "mistralai/mistral-medium-3.5-128b": { "displayName": "Mistral Medium 3.5", "description": "Balanced Mistral model for enterprise assistants, multilingual work, and tools", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-04-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "mistralai/mistral-nemotron": { "displayName": "mistral-nemotron", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-06-12", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mistralai/mistral-small-4-119b-2603": { "displayName": "mistral-small-4-119b-2603", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "structuredOutput": true, "lastUpdated": "2026-03-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "mistralai/mixtral-8x22b-instruct": { "displayName": "Mistral: Mixtral 8x22B Instruct", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 13108, "lastUpdated": "2024-04-17", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mistralai/mixtral-8x7b-instruct": { "displayName": "Mistral: Mixtral 8x7B Instruct", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2026-03-15", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "moonshotai/kimi-k2-instruct-0905": { "displayName": "Kimi K2 0905", "description": "Kimi model for long-context chat, coding, and agentic reasoning", "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"] } },
+        "moonshotai/kimi-k2.6": { "displayName": "Kimi K2.6", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "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"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "nvidia/active-speaker-detection": { "displayName": "Active Speaker Detection", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2026-04-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["video"], "output": ["text"] } },
+        "nvidia/bevformer": { "displayName": "bevformer", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-07-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["video"], "output": ["text"] } },
+        "nvidia/cosmos-predict1-5b": { "displayName": "cosmos-predict1-5b", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2025-03-18", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "video"], "output": ["video"] } },
+        "nvidia/cosmos-reason2-8b": { "displayName": "Cosmos Reason2 8B", "description": "Vision language model for physical-world understanding with structured reasoning on video and images", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2025-12-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "nvidia/cosmos-transfer1-7b": { "displayName": "cosmos-transfer1-7b", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2025-06-30", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "video"], "output": ["video"] } },
+        "nvidia/cosmos-transfer2_5-2b": { "displayName": "cosmos-transfer2.5-2b", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2026-02-26", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "video"], "output": ["video"] } },
+        "nvidia/gliner-pii": { "displayName": "gliner-pii", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2026-03-03", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/llama-3_2-nemoretriever-300m-embed-v1": { "displayName": "llama-3_2-nemoretriever-300m-embed-v1", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 2048, "lastUpdated": "2025-07-24", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/llama-3.1-nemotron-70b-instruct": { "displayName": "Llama 3.1 Nemotron 70B Instruct", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-04-15", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/llama-3.1-nemotron-nano-8b-v1": { "displayName": "Llama 3.1 Nemotron Nano 8B v1", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2025-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/llama-3.1-nemotron-nano-vl-8b-v1": { "displayName": "Llama 3.1 Nemotron Nano VL 8B v1", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "lastUpdated": "2025-04-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "nvidia/llama-3.1-nemotron-safety-guard-8b-v3": { "displayName": "llama-3.1-nemotron-safety-guard-8b-v3", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2025-10-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/llama-3.1-nemotron-ultra-253b-v1": { "displayName": "Llama 3.1 Nemotron Ultra 253B", "description": "Flagship Nemotron model for high-throughput reasoning and complex agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 16384, "lastUpdated": "2025-04-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/llama-3.3-nemotron-super-49b-v1": { "displayName": "Llama 3.3 Nemotron Super 49B v1", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "lastUpdated": "2025-04-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/llama-3.3-nemotron-super-49b-v1.5": { "displayName": "Llama 3.3 Nemotron Super 49B v1.5", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "lastUpdated": "2025-07-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/llama-nemotron-embed-vl-1b-v2": { "displayName": "llama-nemotron-embed-vl-1b-v2", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 2048, "lastUpdated": "2026-02-10", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "nvidia/llama-nemotron-rerank-vl-1b-v2": { "displayName": "llama-nemotron-rerank-vl-1b-v2", "description": "Reranking model for improving retrieval quality in search and recommendation systems", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2026-03-31", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "nvidia/magpie-tts-zeroshot": { "displayName": "magpie-tts-zeroshot", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2025-06-12", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "audio"], "output": ["audio"] } },
+        "nvidia/nemotron-3-content-safety": { "displayName": "nemotron-3-content-safety", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2026-04-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-09", "lastUpdated": "2024-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": { "displayName": "Nemotron 3 Nano Omni", "description": "Open Nemotron omni model combining reasoning with text, vision, and audio", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-04-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video", "audio"], "output": ["text"] } },
         "nvidia/nemotron-3-super-120b-a12b": { "displayName": "Nemotron 3 Super", "description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2024-04", "lastUpdated": "2026-03-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-06-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/nemotron-3.5-lightning-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", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/nemotron-content-safety-reasoning-4b": { "displayName": "nemotron-content-safety-reasoning-4b", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2026-01-22", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/nemotron-mini-4b-instruct": { "displayName": "nemotron-mini-4b-instruct", "description": "Compact Nemotron model for efficient reasoning and deployable AI agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2024-08-26", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/nemotron-nano-12b-v2-vl": { "displayName": "Nemotron Nano 12B v2 VL", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "lastUpdated": "2025-10-28", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "nvidia/nemotron-voicechat": { "displayName": "nemotron-voicechat", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2026-03-16", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "audio"], "output": ["text"] } },
-        "nvidia/nv-embed-v1": { "displayName": "nv-embed-v1", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 2048, "lastUpdated": "2025-07-22", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/nv-embedcode-7b-v1": { "displayName": "nv-embedcode-7b-v1", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 2048, "lastUpdated": "2025-05-29", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/nvidia-nemotron-nano-9b-v2": { "displayName": "nvidia-nemotron-nano-9b-v2", "description": "Compact Nemotron model for efficient reasoning and deployable AI agents", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-09", "lastUpdated": "2025-08-18", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/rerank-qa-mistral-4b": { "displayName": "rerank-qa-mistral-4b", "description": "Reranking model for improving retrieval quality in search and recommendation systems", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2025-01-17", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/riva-translate-4b-instruct-v1.1": { "displayName": "riva-translate-4b-instruct-v1_1", "description": "Translation model for multilingual conversion, localization, and cross-language workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2025-12-12", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/sparsedrive": { "displayName": "sparsedrive", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-07-20", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["video"], "output": ["text"] } },
-        "nvidia/streampetr": { "displayName": "streampetr", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-11-13", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["video"], "output": ["text"] } },
-        "nvidia/studiovoice": { "displayName": "studiovoice", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-06-13", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/synthetic-video-detector": { "displayName": "synthetic-video-detector", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2026-04-16", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["video"], "output": ["text"] } },
-        "nvidia/usdcode": { "displayName": "usdcode", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2026-01-01", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/usdvalidate": { "displayName": "usdvalidate", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2025-01-08", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "openai/gpt-oss-120b": { "displayName": "GPT-OSS-120B", "description": "Open GPT reasoning model for self-hosted agents and controllable deployments", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "knowledgeCutoff": "2025-08", "structuredOutput": true, "lastUpdated": "2025-08-14", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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": 32768, "structuredOutput": true, "lastUpdated": "2025-08-05", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "openai/whisper-large-v3": { "displayName": "Whisper Large v3", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "lifecycle": "active", "maxOutputTokens": 4096, "knowledgeCutoff": "2023-09", "lastUpdated": "2025-09-05", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["text"] } },
-        "poolside/laguna-xs-2.1": { "displayName": "Laguna XS 2.1", "description": "Agentic coding model from Poolside in the XS size class for local deployment", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "structuredOutput": false, "lastUpdated": "2026-07-02", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen/qwen-image": { "displayName": "Qwen Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "structuredOutput": false, "lastUpdated": "2025-08-07", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["image"] } },
-        "qwen/qwen-image-edit": { "displayName": "Qwen Image Edit", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "structuredOutput": false, "lastUpdated": "2025-08-19", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["image"] } },
-        "qwen/qwen2.5-coder-32b-instruct": { "displayName": "Qwen2.5 Coder 32b Instruct", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2024-11-06", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen/qwen3-coder-480b-a35b-instruct": { "displayName": "Qwen3 Coder 480B A35B Instruct", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 66536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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": "2024-12", "lastUpdated": "2025-09-05", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video", "audio"], "output": ["text"] } },
-        "qwen/qwen3.5-397b-a17b": { "displayName": "Qwen3.5-397B-A17B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 8192, "knowledgeCutoff": "2026-01", "structuredOutput": true, "lastUpdated": "2026-02-16", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "sarvamai/sarvam-m": { "displayName": "sarvam-m", "description": "Efficient Indian-language reasoning model for chat, coding, and multilingual work", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-07-25", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "stepfun-ai/step-3.5-flash": { "displayName": "Step 3.5 Flash", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 16384, "lastUpdated": "2026-02-02", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "stepfun-ai/step-3.7-flash": { "displayName": "Step 3.7 Flash", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 16384, "lastUpdated": "2026-05-28", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
+        "nvidia/nemotron-3.5-lightning-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"] } },
+        "nvidia/nemotron-content-safety-reasoning-4b": { "displayName": "nemotron-content-safety-reasoning-4b", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2026-01-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/nemotron-mini-4b-instruct": { "displayName": "nemotron-mini-4b-instruct", "description": "Compact Nemotron model for efficient reasoning and deployable AI agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2024-08-26", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/nemotron-nano-12b-v2-vl": { "displayName": "Nemotron Nano 12B v2 VL", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "lastUpdated": "2025-10-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "nvidia/nemotron-voicechat": { "displayName": "nemotron-voicechat", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2026-03-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "audio"], "output": ["text"] } },
+        "nvidia/nv-embed-v1": { "displayName": "nv-embed-v1", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 2048, "lastUpdated": "2025-07-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/nv-embedcode-7b-v1": { "displayName": "nv-embedcode-7b-v1", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 2048, "lastUpdated": "2025-05-29", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/nvidia-nemotron-nano-9b-v2": { "displayName": "nvidia-nemotron-nano-9b-v2", "description": "Compact Nemotron model for efficient reasoning and deployable AI agents", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-09", "lastUpdated": "2025-08-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/rerank-qa-mistral-4b": { "displayName": "rerank-qa-mistral-4b", "description": "Reranking model for improving retrieval quality in search and recommendation systems", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2025-01-17", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/riva-translate-4b-instruct-v1.1": { "displayName": "riva-translate-4b-instruct-v1_1", "description": "Translation model for multilingual conversion, localization, and cross-language workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2025-12-12", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/sparsedrive": { "displayName": "sparsedrive", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-07-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["video"], "output": ["text"] } },
+        "nvidia/streampetr": { "displayName": "streampetr", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-11-13", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["video"], "output": ["text"] } },
+        "nvidia/studiovoice": { "displayName": "studiovoice", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-06-13", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/synthetic-video-detector": { "displayName": "synthetic-video-detector", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2026-04-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["video"], "output": ["text"] } },
+        "nvidia/usdcode": { "displayName": "usdcode", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "lastUpdated": "2026-01-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/usdvalidate": { "displayName": "usdvalidate", "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "lifecycle": "active", "maxOutputTokens": 4096, "lastUpdated": "2025-01-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "openai/gpt-oss-120b": { "displayName": "GPT-OSS-120B", "description": "Open GPT reasoning model for self-hosted agents and controllable deployments", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "knowledgeCutoff": "2025-08", "structuredOutput": true, "lastUpdated": "2025-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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": 32768, "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "openai/whisper-large-v3": { "displayName": "Whisper Large v3", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "lifecycle": "active", "maxOutputTokens": 4096, "knowledgeCutoff": "2023-09", "lastUpdated": "2025-09-05", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["text"] } },
+        "poolside/laguna-xs-2.1": { "displayName": "Laguna XS 2.1", "description": "Agentic coding model from Poolside in the XS size class for local deployment", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "structuredOutput": false, "lastUpdated": "2026-07-02", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen/qwen-image": { "displayName": "Qwen Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "structuredOutput": false, "lastUpdated": "2025-08-07", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["image"] } },
+        "qwen/qwen-image-edit": { "displayName": "Qwen Image Edit", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "structuredOutput": false, "lastUpdated": "2025-08-19", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["image"] } },
+        "qwen/qwen2.5-coder-32b-instruct": { "displayName": "Qwen2.5 Coder 32b Instruct", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2024-11-06", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen/qwen3-coder-480b-a35b-instruct": { "displayName": "Qwen3 Coder 480B A35B Instruct", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 66536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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": "2024-12", "lastUpdated": "2025-09-05", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "audio"], "output": ["text"] } },
+        "qwen/qwen3.5-397b-a17b": { "displayName": "Qwen3.5-397B-A17B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 8192, "knowledgeCutoff": "2026-01", "structuredOutput": true, "lastUpdated": "2026-02-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "sarvamai/sarvam-m": { "displayName": "sarvam-m", "description": "Efficient Indian-language reasoning model for chat, coding, and multilingual work", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "lastUpdated": "2025-07-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "stepfun-ai/step-3.5-flash": { "displayName": "Step 3.5 Flash", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 16384, "lastUpdated": "2026-02-02", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "stepfun-ai/step-3.7-flash": { "displayName": "Step 3.7 Flash", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 16384, "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
     },
     "ollama-cloud": {
         "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"] } },
@@ -828,7 +828,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "text-embedding-ada-002": { "displayName": "text-embedding-ada-002", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1536, "knowledgeCutoff": "2022-12", "lastUpdated": "2022-12-15", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
     },
     "opencode": {
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "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"] } },
@@ -844,7 +844,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "claude-sonnet-4-6": { "displayName": "Claude Sonnet 4.6", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "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"] } },
@@ -857,9 +857,9 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "glm-5": { "displayName": "GLM-5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "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"] } },
@@ -888,48 +888,48 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "kimi-k2.5": { "displayName": "Kimi K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2024-10", "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "kimi-k2.5-free": { "displayName": "Kimi K2.5 Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2024-10", "lastUpdated": "2026-01-27", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "kimi-k2.5-free": { "displayName": "Kimi K2.5 Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2024-10", "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "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 }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "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"] } },
         "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": ["max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "laguna-s-2.1-free": { "displayName": "Laguna S 2.1 Free", "description": "Agentic coding model from Poolside in the XS size class for local deployment", "lifecycle": "deprecated", "contextWindow": 256000, "maxOutputTokens": 32000, "structuredOutput": false, "lastUpdated": "2026-07-21", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "ling-2.6-flash-free": { "displayName": "Ling 2.6 Flash Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262100, "maxOutputTokens": 32800, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-04-21", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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": 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"] } },
-        "ling-3.0-flash-free": { "displayName": "Ling-3.0-flash Free", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-23", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "ling-3.0-tiny-free": { "displayName": "Ling-3.0-tiny Free", "description": "Compact MoE model for responsive agents, instruction following, and multi-turn conversations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-08-06", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "longcat-2.0-free": { "displayName": "LongCat-2.0 Free", "description": "Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window", "lifecycle": "deprecated", "contextWindow": 1000000, "maxOutputTokens": 131072, "lastUpdated": "2026-06-30", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mimo-v2-flash-free": { "displayName": "MiMo V2 Flash Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-16", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mimo-v2-omni-free": { "displayName": "MiMo V2 Omni Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 64000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio", "pdf"], "output": ["text"] } },
-        "mimo-v2-pro-free": { "displayName": "MiMo V2 Pro Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 64000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mimo-v2.5-free": { "displayName": "MiMo V2.5 Free", "description": "MiMo omni model for text, image, video, audio, and agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 32000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-24", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "laguna-s-2.1-free": { "displayName": "Laguna S 2.1 Free", "description": "Agentic coding model from Poolside in the XS size class for local deployment", "lifecycle": "deprecated", "contextWindow": 256000, "maxOutputTokens": 32000, "structuredOutput": false, "lastUpdated": "2026-07-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "ling-2.6-flash-free": { "displayName": "Ling 2.6 Flash Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262100, "maxOutputTokens": 32800, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-04-21", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-08-27", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "ling-3.0-flash-free": { "displayName": "Ling-3.0-flash Free", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "ling-3.0-tiny-free": { "displayName": "Ling-3.0-tiny Free", "description": "Compact MoE model for responsive agents, instruction following, and multi-turn conversations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-08-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "longcat-2.0-free": { "displayName": "LongCat-2.0 Free", "description": "Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window", "lifecycle": "deprecated", "contextWindow": 1000000, "maxOutputTokens": 131072, "lastUpdated": "2026-06-30", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mimo-v2-flash-free": { "displayName": "MiMo V2 Flash Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mimo-v2-omni-free": { "displayName": "MiMo V2 Omni Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 64000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio", "pdf"], "output": ["text"] } },
+        "mimo-v2-pro-free": { "displayName": "MiMo V2 Pro Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 64000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mimo-v2.5-free": { "displayName": "MiMo V2.5 Free", "description": "MiMo omni model for text, image, video, audio, and agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 32000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
         "minimax-m2.1": { "displayName": "MiniMax-M2.1", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "minimax-m2.1-free": { "displayName": "MiniMax-M2.1 Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-23", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "minimax-m2.1-free": { "displayName": "MiniMax-M2.1 Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-01", "lastUpdated": "2025-12-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax-m2.5": { "displayName": "MiniMax-M2.5", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "minimax-m2.5-free": { "displayName": "MiniMax-M2.5 Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-12", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "minimax-m2.5-free": { "displayName": "MiniMax-M2.5 Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
         "minimax-m3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 512000, "maxOutputTokens": 128000, "lastUpdated": "2026-06-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
         "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "north-mini-code-free": { "displayName": "North Mini Code Free", "description": "Cohere coding model for practical software engineering and agentic edits", "lifecycle": "deprecated", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-09-23", "structuredOutput": true, "lastUpdated": "2026-06-09", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "north-mini-code-free": { "displayName": "North Mini Code Free", "description": "Cohere coding model for practical software engineering and agentic edits", "lifecycle": "deprecated", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-09-23", "structuredOutput": true, "lastUpdated": "2026-06-09", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen3-coder": { "displayName": "Qwen3 Coder", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen3.5-plus": { "displayName": "Qwen3.5 Plus", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "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"] } },
         "qwen3.6-plus": { "displayName": "Qwen3.6 Plus", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 262144, "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"] } },
-        "qwen3.6-plus-free": { "displayName": "Qwen3.6 Plus Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "ring-2.6-1t-free": { "displayName": "Ring 2.6 1T Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262000, "maxOutputTokens": 66000, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-05-08", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "trinity-large-preview-free": { "displayName": "Trinity Large Preview", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-01-28", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "x-preview-f-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"] } },
+        "qwen3.6-plus-free": { "displayName": "Qwen3.6 Plus Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "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"] } },
+        "ring-2.6-1t-free": { "displayName": "Ring 2.6 1T Free", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262000, "maxOutputTokens": 66000, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-05-08", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "trinity-large-preview-free": { "displayName": "Trinity Large Preview", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-01-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "x-preview-f-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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
     },
     "opencode-go": {
         "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"] } },
@@ -961,7 +961,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "qwen3.7-max": { "displayName": "Qwen3.7 Max", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "lastUpdated": "2026-05-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1027,7 +1027,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "cohere/command-r-08-2024": { "displayName": "Command R", "description": "Cohere retrieval model for long-context chat and enterprise RAG workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4000, "knowledgeCutoff": "2024-06-01", "structuredOutput": true, "lastUpdated": "2024-08-30", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "cohere/command-r-plus-08-2024": { "displayName": "Command R+", "description": "Cohere's RAG workhorse for long-context enterprise search and tool use", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4000, "knowledgeCutoff": "2024-06-01", "structuredOutput": true, "lastUpdated": "2024-08-30", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "cohere/command-r7b-12-2024": { "displayName": "Command R7B", "description": "Cohere retrieval model for long-context chat and enterprise RAG workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4000, "knowledgeCutoff": "2024-06-01", "structuredOutput": true, "lastUpdated": "2024-12-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "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"] } },
@@ -1043,7 +1043,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "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"] } },
@@ -1069,11 +1069,11 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "video"], "output": ["text"] } },
         "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"] } },
-        "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"] } },
-        "google/lyria-3-clip-preview": { "displayName": "Lyria 3 Clip 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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "video"], "output": ["text"] } },
+        "google/lyria-3-clip-preview": { "displayName": "Lyria 3 Clip Preview", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "structuredOutput": false, "lastUpdated": "2026-03-25", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "audio"] } },
+        "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", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "audio"] } },
         "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"] } },
         "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"] } },
         "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"] } },
@@ -1081,15 +1081,15 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "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"] } },
@@ -1144,21 +1144,21 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video", "audio"], "output": ["text"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "openai/gpt-3.5-turbo": { "displayName": "GPT-3.5-turbo", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 16385, "maxOutputTokens": 4096, "knowledgeCutoff": "2021-09-01", "structuredOutput": true, "lastUpdated": "2023-11-06", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "openai/gpt-3.5-turbo-0613": { "displayName": "GPT-3.5 Turbo (older v0613)", "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": "2024-01-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "openai/gpt-3.5-turbo-16k": { "displayName": "GPT-3.5 Turbo 16k", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 16385, "maxOutputTokens": 4096, "knowledgeCutoff": "2021-09-30", "structuredOutput": true, "lastUpdated": "2023-08-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1220,7 +1220,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "openai/o4-mini-high": { "displayName": "o4 Mini High", "description": "O-series reasoning model for hard analysis, math, coding, and planning", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 100000, "knowledgeCutoff": "2024-06-30", "structuredOutput": true, "lastUpdated": "2025-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high"] }, "modalities": { "input": ["image", "text", "pdf"], "output": ["text"] } },
         "openrouter/auto": { "displayName": "Auto Router", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "structuredOutput": true, "lastUpdated": "2023-11-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio", "pdf", "video"], "output": ["text", "image"] } },
         "openrouter/bodybuilder": { "displayName": "Body Builder (beta)", "description": "Preview model for early access evaluation, prototyping, and compatibility testing", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "structuredOutput": false, "lastUpdated": "2025-12-05", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "openrouter/free": { "displayName": "Free Models Router", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 200000, "maxOutputTokens": 8000, "structuredOutput": true, "lastUpdated": "2026-02-01", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "openrouter/free": { "displayName": "Free Models Router", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 200000, "maxOutputTokens": 8000, "structuredOutput": true, "lastUpdated": "2026-02-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "openrouter/fusion": { "displayName": "Fusion", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": false, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "openrouter/pareto-code": { "displayName": "Pareto Code Router", "description": "Coding model for repository understanding, refactors, and agentic engineering tasks", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 200000, "structuredOutput": false, "lastUpdated": "2026-04-21", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "perceptron/perceptron-mk1": { "displayName": "Perceptron Mk1", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 8192, "structuredOutput": true, "lastUpdated": "2026-05-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
@@ -1230,9 +1230,9 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "perplexity/sonar-pro-search": { "displayName": "Sonar Pro Search", "description": "Advanced Sonar search model for deeper research and cited synthesis", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 8000, "structuredOutput": true, "lastUpdated": "2025-10-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "perplexity/sonar-reasoning-pro": { "displayName": "Sonar Reasoning Pro", "description": "Web-grounded reasoning model for multi-step research and cited answers", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 115200, "structuredOutput": false, "lastUpdated": "2025-03-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "poolside/laguna-s-2.1": { "displayName": "Laguna S 2.1", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": false, "lastUpdated": "2026-07-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "poolside/laguna-s-2.1:free": { "displayName": "Laguna S 2.1 (free)", "description": "Free provider route for experiments, demos, and cost-sensitive chat workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-21", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "poolside/laguna-s-2.1:free": { "displayName": "Laguna S 2.1 (free)", "description": "Free provider route for experiments, demos, and cost-sensitive chat workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "poolside/laguna-xs-2.1": { "displayName": "Laguna XS 2.1", "description": "Agentic coding model from Poolside in the XS size class for local deployment", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-02", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "poolside/laguna-xs-2.1:free": { "displayName": "Laguna XS 2.1 (free)", "description": "Free provider route for experiments, demos, and cost-sensitive chat workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-02", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "poolside/laguna-xs-2.1:free": { "displayName": "Laguna XS 2.1 (free)", "description": "Free provider route for experiments, demos, and cost-sensitive chat workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-02", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen/qwen-2.5-72b-instruct": { "displayName": "Qwen2.5 72B Instruct", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-06-30", "structuredOutput": true, "lastUpdated": "2024-09-19", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen/qwen-2.5-7b-instruct": { "displayName": "Qwen2.5 7B Instruct", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 29491, "knowledgeCutoff": "2024-06-30", "structuredOutput": true, "lastUpdated": "2024-10-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
@@ -1309,8 +1309,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "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"] } },
@@ -1462,22 +1462,22 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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": 1048575, "maxOutputTokens": 400000, "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"] } },
     },
     "tencent-coding-plan": {
-        "glm-5": { "displayName": "GLM-5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 16384, "lastUpdated": "2026-02-11", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "hunyuan-2.0-instruct": { "displayName": "Tencent HY 2.0 Instruct", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2026-03-08", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "hunyuan-2.0-thinking": { "displayName": "Tencent HY 2.0 Think", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2026-03-08", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "hunyuan-t1": { "displayName": "Hunyuan-T1", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2026-03-08", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "hunyuan-turbos": { "displayName": "Hunyuan-TurboS", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2026-03-08", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "kimi-k2.5": { "displayName": "Kimi-K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "minimax-m2.5": { "displayName": "MiniMax-M2.5", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 32768, "lastUpdated": "2026-02-12", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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"] } },
+        "glm-5": { "displayName": "GLM-5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 16384, "lastUpdated": "2026-02-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "hunyuan-2.0-instruct": { "displayName": "Tencent HY 2.0 Instruct", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2026-03-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "hunyuan-2.0-thinking": { "displayName": "Tencent HY 2.0 Think", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2026-03-08", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "hunyuan-t1": { "displayName": "Hunyuan-T1", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2026-03-08", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "hunyuan-turbos": { "displayName": "Hunyuan-TurboS", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "lastUpdated": "2026-03-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "kimi-k2.5": { "displayName": "Kimi-K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "minimax-m2.5": { "displayName": "MiniMax-M2.5", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 32768, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
     },
     "tencent-token-plan": {
-        "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"] } },
+        "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", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
     },
     "tencent-tokenhub": {
-        "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"] } },
-        "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"] } },
+        "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", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
     },
     "vercel": {
@@ -1629,12 +1629,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
         "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"] } },
         "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
-        "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"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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"] } },
         "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", "lastUpdated": "2025-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
         "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", "lastUpdated": "2025-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
@@ -1650,9 +1650,9 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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": 256000, "maxOutputTokens": 80000, "lastUpdated": "2026-07-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "meta/llama-3.1-70b": { "displayName": "Llama 3.1 70B Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "meta/llama-3.1-8b": { "displayName": "Llama 3.1 8B Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "knowledgeCutoff": "2023-12", "lastUpdated": "2024-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "meta/llama-3.3-70b": { "displayName": "Llama-3.3-70B-Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "meta/llama-4-maverick": { "displayName": "Llama-4-Maverick-17B-128E-Instruct-FP8", "description": "Open multimodal Llama model for strong reasoning and fast responses", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "meta/llama-4-scout": { "displayName": "Llama-4-Scout-17B-16E-Instruct-FP8", "description": "Open multimodal Llama model for long-context analysis and efficient agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "isFree": true, "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "meta/llama-3.3-70b": { "displayName": "Llama-3.3-70B-Instruct", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-12", "lastUpdated": "2024-12-06", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "meta/llama-4-maverick": { "displayName": "Llama-4-Maverick-17B-128E-Instruct-FP8", "description": "Open multimodal Llama model for strong reasoning and fast responses", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "meta/llama-4-scout": { "displayName": "Llama-4-Scout-17B-16E-Instruct-FP8", "description": "Open multimodal Llama model for long-context analysis and efficient agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-08", "lastUpdated": "2025-04-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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": 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"] } },
         "meta/muse-image-1.0": { "displayName": "Muse Image 1.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["image"] } },
         "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"] } },
@@ -1783,7 +1783,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "perplexity/sonar-pro": { "displayName": "Sonar Pro", "description": "Advanced Sonar search model for deeper research and cited synthesis", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 8000, "knowledgeCutoff": "2025-09", "lastUpdated": "2025-02-19", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "perplexity/sonar-reasoning-pro": { "displayName": "Sonar Reasoning Pro", "description": "Web-grounded reasoning model for multi-step research and cited answers", "lifecycle": "active", "contextWindow": 127000, "maxOutputTokens": 8000, "knowledgeCutoff": "2025-09", "lastUpdated": "2025-02-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "poolside/laguna-s-2.1": { "displayName": "Laguna S 2.1", "description": "Agentic coding model from Poolside in the XS size class for local deployment", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": false, "lastUpdated": "2026-07-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "poolside/laguna-s-2.1-free": { "displayName": "Laguna S 2.1 Free", "description": "Free provider route for experiments, demos, and cost-sensitive chat workloads", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-21", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "poolside/laguna-s-2.1-free": { "displayName": "Laguna S 2.1 Free", "description": "Free provider route for experiments, demos, and cost-sensitive chat workloads", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "prodia/flux-fast-schnell": { "displayName": "Flux Schnell", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 512, "lastUpdated": "2026-06-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "quiverai/arrow-1.1": { "displayName": "Arrow 1.1", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "lastUpdated": "2026-04-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "recraft/recraft-v2": { "displayName": "Recraft V2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 512, "lastUpdated": "2024-03", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
@@ -1881,41 +1881,41 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "mimo-v2.5-pro-ultraspeed": { "displayName": "MiMo-V2.5-Pro-UltraSpeed", "description": "MiMo pro model for strong multimodal reasoning and agent execution", "lifecycle": "beta", "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"] } },
     },
     "xiaomi-token-plan-cn": {
-        "mimo-v2-pro": { "displayName": "MiMo-V2-Pro", "description": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mimo-v2-tts": { "displayName": "MiMo-V2-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "mimo-v2.5": { "displayName": "MiMo-V2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
-        "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": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mimo-v2.5-tts": { "displayName": "MiMo-V2.5-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "mimo-v2.5-tts-voiceclone": { "displayName": "MiMo-V2.5-TTS-VoiceClone", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "mimo-v2.5-tts-voicedesign": { "displayName": "MiMo-V2.5-TTS-VoiceDesign", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2-pro": { "displayName": "MiMo-V2-Pro", "description": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mimo-v2-tts": { "displayName": "MiMo-V2-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2.5": { "displayName": "MiMo-V2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "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": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mimo-v2.5-tts": { "displayName": "MiMo-V2.5-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2.5-tts-voiceclone": { "displayName": "MiMo-V2.5-TTS-VoiceClone", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2.5-tts-voicedesign": { "displayName": "MiMo-V2.5-TTS-VoiceDesign", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
     },
     "xiaomi-token-plan-sgp": {
-        "mimo-v2-pro": { "displayName": "MiMo-V2-Pro", "description": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mimo-v2-tts": { "displayName": "MiMo-V2-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "mimo-v2.5": { "displayName": "MiMo-V2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
-        "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": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mimo-v2.5-tts": { "displayName": "MiMo-V2.5-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "mimo-v2.5-tts-voiceclone": { "displayName": "MiMo-V2.5-TTS-VoiceClone", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "mimo-v2.5-tts-voicedesign": { "displayName": "MiMo-V2.5-TTS-VoiceDesign", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2-pro": { "displayName": "MiMo-V2-Pro", "description": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mimo-v2-tts": { "displayName": "MiMo-V2-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2.5": { "displayName": "MiMo-V2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "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": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mimo-v2.5-tts": { "displayName": "MiMo-V2.5-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2.5-tts-voiceclone": { "displayName": "MiMo-V2.5-TTS-VoiceClone", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2.5-tts-voicedesign": { "displayName": "MiMo-V2.5-TTS-VoiceDesign", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
     },
     "xiaomi-token-plan-ams": {
-        "mimo-v2-pro": { "displayName": "MiMo-V2-Pro", "description": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mimo-v2-tts": { "displayName": "MiMo-V2-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-03-18", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "mimo-v2.5": { "displayName": "MiMo-V2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
-        "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": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mimo-v2.5-tts": { "displayName": "MiMo-V2.5-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "mimo-v2.5-tts-voiceclone": { "displayName": "MiMo-V2.5-TTS-VoiceClone", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "mimo-v2.5-tts-voicedesign": { "displayName": "MiMo-V2.5-TTS-VoiceDesign", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "isFree": true, "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2-pro": { "displayName": "MiMo-V2-Pro", "description": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mimo-v2-tts": { "displayName": "MiMo-V2-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2.5": { "displayName": "MiMo-V2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "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": 131072, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mimo-v2.5-tts": { "displayName": "MiMo-V2.5-TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2.5-tts-voiceclone": { "displayName": "MiMo-V2.5-TTS-VoiceClone", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "mimo-v2.5-tts-voicedesign": { "displayName": "MiMo-V2.5-TTS-VoiceDesign", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
     },
     "zai": {
         "glm-4.5": { "displayName": "GLM-4.5", "description": "Hybrid-reasoning GLM release that made the 4.5 line broadly useful", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 98304, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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": 131072, "maxOutputTokens": 98304, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "glm-4.5-flash": { "displayName": "GLM-4.5-Flash", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 98304, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "glm-4.5-flash": { "displayName": "GLM-4.5-Flash", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 98304, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "glm-4.5v": { "displayName": "GLM-4.5V", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 64000, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-08-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "glm-4.6": { "displayName": "GLM-4.6", "description": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks", "lifecycle": "active", "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"] } },
         "glm-4.6v": { "displayName": "GLM-4.6V", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "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", "lastUpdated": "2025-12-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "glm-4.7-flashx": { "displayName": "GLM-4.7-FlashX", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "glm-5": { "displayName": "GLM-5", "description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "glm-5-turbo": { "displayName": "GLM-5-Turbo", "description": "Faster GLM-5 lane for coding agents that need lower latency", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-03-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1926,13 +1926,13 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "glm-5v-turbo": { "displayName": "GLM-5V-Turbo", "description": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 131072, "lastUpdated": "2026-04-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
     },
     "zai-coding-plan": {
-        "glm-4.7": { "displayName": "GLM-4.7", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "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"] } },
-        "glm-5-turbo": { "displayName": "GLM-5-Turbo", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-03-16", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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"] } },
-        "glm-5.2-highspeed": { "displayName": "GLM-5.2 Highspeed", "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"] } },
-        "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", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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"] } },
-        "glm-5.3-highspeed": { "displayName": "GLM-5.3 Highspeed", "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", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "glm-4.7": { "displayName": "GLM-4.7", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "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"] } },
+        "glm-5-turbo": { "displayName": "GLM-5-Turbo", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-03-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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"] } },
+        "glm-5.2-highspeed": { "displayName": "GLM-5.2 Highspeed", "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"] } },
+        "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"] } },
+        "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"] } },
+        "glm-5.3-highspeed": { "displayName": "GLM-5.3 Highspeed", "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"] } },
     },
     "zenmux": {
         "anthropic/claude-3.5-haiku": { "displayName": "Claude 3.5 Haiku", "description": "Fast Claude model for responsive assistance, classification, and lightweight agents", "lifecycle": "deprecated", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2024-11-04", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
@@ -1949,7 +1949,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "anthropic/claude-sonnet-4.5": { "displayName": "Claude Sonnet 4.5", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-09-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "anthropic/claude-sonnet-4.6": { "displayName": "Claude Sonnet 4.6", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-02-18", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "anthropic/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"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-sonnet-5-free": { "displayName": "Claude Sonnet 5 (Free)", "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", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-sonnet-5-free": { "displayName": "Claude Sonnet 5 (Free)", "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"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "baidu/ernie-5.0-thinking-preview": { "displayName": "ERNIE 5.0", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-01-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "deepseek/deepseek-chat": { "displayName": "DeepSeek-V3.2 (Non-thinking Mode)", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "deprecated", "contextWindow": 128000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek/deepseek-v3.2": { "displayName": "DeepSeek V3.2", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1981,9 +1981,9 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "moonshotai/kimi-k2.5": { "displayName": "Kimi K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "moonshotai/kimi-k2.6": { "displayName": "Kimi K2.6", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262140, "maxOutputTokens": 262140, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-04-20", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "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 }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "moonshotai/kimi-k2.7-code-free": { "displayName": "Kimi K2.7 Code (Free)", "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", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "moonshotai/kimi-k2.7-code-free": { "displayName": "Kimi K2.7 Code (Free)", "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"] } },
         "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": ["max"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "moonshotai/kimi-k3-free": { "displayName": "Kimi K3 (Free)", "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": ["max"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "moonshotai/kimi-k3-free": { "displayName": "Kimi K3 (Free)", "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": ["max"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "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"] } },
         "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"] } },
         "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"] } },
@@ -2017,7 +2017,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "stepfun/step-3": { "displayName": "Step-3", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "deprecated", "contextWindow": 65536, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-07-31", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
         "stepfun/step-3.5-flash": { "displayName": "Step 3.5 Flash", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-02-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "stepfun/step-3.7-flash": { "displayName": "Step 3.7 Flash", "description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "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"] } },
-        "stepfun/step-3.7-flash-free": { "displayName": "Step 3.7 Flash (Free)", "description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2026-03-01", "lastUpdated": "2026-05-29", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "stepfun/step-3.7-flash-free": { "displayName": "Step 3.7 Flash (Free)", "description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "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"] } },
         "tencent/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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "volcengine/doubao-seed-1.8": { "displayName": "Doubao-Seed-1.8", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-18", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "volcengine/doubao-seed-2.0-code": { "displayName": "Doubao Seed 2.0 Code", "description": "Coding model for repository understanding, refactors, and agentic engineering tasks", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-03-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -2045,15 +2045,15 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "z-ai/glm-4.6": { "displayName": "GLM 4.6", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-09-30", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "z-ai/glm-4.6v": { "displayName": "GLM 4.6V", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "z-ai/glm-4.6v-flash": { "displayName": "GLM 4.6V FlashX", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "z-ai/glm-4.6v-flash-free": { "displayName": "GLM 4.6V Flash (Free)", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-08", "isFree": true, "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "z-ai/glm-4.6v-flash-free": { "displayName": "GLM 4.6V Flash (Free)", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "z-ai/glm-4.7": { "displayName": "GLM 4.7", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-12-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "z-ai/glm-4.7-flash-free": { "displayName": "GLM 4.7 Flash (Free)", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-01-19", "isFree": true, "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "z-ai/glm-4.7-flash-free": { "displayName": "GLM 4.7 Flash (Free)", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "z-ai/glm-4.7-flashx": { "displayName": "GLM 4.7 FlashX", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "z-ai/glm-5": { "displayName": "GLM 5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "z-ai/glm-5-turbo": { "displayName": "GLM 5 Turbo", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2026-03-20", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "z-ai/glm-5.1": { "displayName": "GLM-5.1", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-04-03", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "z-ai/glm-5.2-free": { "displayName": "GLM 5.2 (Free)", "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"] } },
+        "z-ai/glm-5.2-free": { "displayName": "GLM 5.2 (Free)", "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"] } },
         "z-ai/glm-5v-turbo": { "displayName": "GLM 5V Turbo", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "lastUpdated": "2026-04-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
     },
 };