maka-agent 0.2.0-dev.48.20260923 → 0.2.0-dev.49.20260924

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

@@ -10,6 +10,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "claude-opus-4-7": { "displayName": "Claude Opus 4.7", "description": "Stronger Opus tier for advanced software work and high-stakes reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "structuredOutput": true, "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "claude-opus-4-8": { "displayName": "Claude Opus 4.8", "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01", "structuredOutput": true, "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "claude-opus-5": { "displayName": "Claude Opus 5", "description": "Strongest Claude Opus model for coding, agents, and professional work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-07-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "claude-opus-5-5": { "displayName": "Claude Opus 5.5", "description": "Claude model for long-running agentic coding and knowledge work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "claude-sonnet-4-5": { "displayName": "Claude Sonnet 4.5 (latest)", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-07-31", "structuredOutput": true, "lastUpdated": "2025-09-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "claude-sonnet-4-5-20250929": { "displayName": "Claude Sonnet 4.5", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-07-31", "structuredOutput": true, "lastUpdated": "2025-09-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "claude-sonnet-4-6": { "displayName": "Claude Sonnet 4.6", "description": "Claude workhorse for coding agents, careful analysis, and production cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
@@ -18,6 +19,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
     "alibaba": {
         "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"] } },
         "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": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text"], "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": 1048576, "structuredOutput": true, "lastUpdated": "2026-07-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "qvq-max": { "displayName": "QVQ Max", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-04", "lastUpdated": "2025-03-25", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "qwen-flash": { "displayName": "Qwen Flash", "description": "Efficient Qwen model for fast chat, extraction, and high-volume workloads", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 32768, "knowledgeCutoff": "2024-04", "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen-max": { "displayName": "Qwen Max", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-04", "lastUpdated": "2025-01-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -66,8 +68,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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-max-preview": { "displayName": "Qwen3.6 Max Preview", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-20", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "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", "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": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-04", "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, "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": 131072, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-06-04", "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"] } },
         "qwq-plus": { "displayName": "QwQ Plus", "description": "Qwen reasoning model for deliberate problem solving, math, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-04", "lastUpdated": "2025-03-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -86,12 +88,15 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "deepseek-v3-2-exp": { "displayName": "DeepSeek V3.2 Exp", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "lastUpdated": "2025-01-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": 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-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-v4.1-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": "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"] } },
         "glm-5.1": { "displayName": "GLM-5.1", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-04-14", "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": 128000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "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"] } },
         "kimi-k2-thinking": { "displayName": "Moonshot Kimi K2 Thinking", "description": "Kimi reasoning model for long-horizon research, planning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2025-11-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "kimi-k2.5": { "displayName": "Moonshot Kimi K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "structuredOutput": false, "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": "Moonshot Kimi K2.6", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-01", "structuredOutput": false, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": 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": 1048576, "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/kimi-k2.5": { "displayName": "kimi/kimi-k2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "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/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"] } },
@@ -112,7 +117,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "qwen-plus-character": { "displayName": "Qwen Plus Character", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-04", "lastUpdated": "2024-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen-turbo": { "displayName": "Qwen Turbo", "description": "Efficient Qwen model for fast chat, extraction, and high-volume workloads", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-04", "lastUpdated": "2025-07-15", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen-vl-max": { "displayName": "Qwen-VL Max", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-04", "lastUpdated": "2025-08-13", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "qwen-vl-ocr": { "displayName": "Qwen-VL OCR", "description": "OCR model for extracting structured text from documents and screenshots", "lifecycle": "active", "contextWindow": 34096, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-04", "lastUpdated": "2025-04-13", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "qwen-vl-ocr": { "displayName": "Qwen-VL OCR", "description": "OCR model for extracting structured text from documents and screenshots", "lifecycle": "active", "contextWindow": 34096, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-04", "lastUpdated": "2026-09-11", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "qwen-vl-plus": { "displayName": "Qwen-VL Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-04", "lastUpdated": "2025-08-15", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "qwen2-5-14b-instruct": { "displayName": "Qwen2.5 14B Instruct", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen2-5-32b-instruct": { "displayName": "Qwen2.5 32B Instruct", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-04", "lastUpdated": "2024-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -133,8 +138,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "qwen3-coder-30b-a3b-instruct": { "displayName": "Qwen3-Coder 30B-A3B Instruct", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen3-coder-flash": { "displayName": "Qwen3 Coder Flash", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3-coder-plus": { "displayName": "Qwen3 Coder Plus", "description": "Hosted Qwen coder for software agents, repo edits, and long-context code", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen3-max": { "displayName": "Qwen3 Max", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen3-coder-plus": { "displayName": "Qwen3 Coder Plus", "description": "Hosted Qwen coder for software agents, repo edits, and long-context code", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-09-11", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen3-max": { "displayName": "Qwen3 Max", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen3-next-80b-a3b-thinking": { "displayName": "Qwen3-Next 80B-A3B (Thinking)", "description": "Qwen reasoning model for deliberate problem solving, math, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen3-omni-flash": { "displayName": "Qwen3-Omni Flash", "description": "Qwen omni model for text, vision, audio, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-04", "lastUpdated": "2025-09-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text", "audio"] } },
@@ -143,8 +148,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "qwen3-vl-30b-a3b": { "displayName": "Qwen3-VL 30B-A3B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "qwen3-vl-plus": { "displayName": "Qwen3-VL Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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": 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"] } },
-        "qwen3.5-flash": { "displayName": "Qwen3.5 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "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"] } },
+        "qwen3.5-flash": { "displayName": "Qwen3.5 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "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", "structuredOutput": true, "lastUpdated": "2026-09-22", "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-max-preview": { "displayName": "Qwen3.6 Max Preview", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 245800, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "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"] } },
@@ -199,6 +204,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
+        "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"] } },
         "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"] } },
@@ -224,9 +230,11 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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": false, "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"] } },
+        "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"] } },
         "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"] } },
@@ -267,12 +275,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
+        "@cf/aisingapore/gemma-sea-lion-v4-27b-it": { "displayName": "Gemma Sea Lion V4 27B It", "description": "Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "structuredOutput": false, "lastUpdated": "2025-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b": { "displayName": "Deepseek R1 Distill Qwen 32B", "description": "Classic open reasoning model for transparent math, coding, and deliberate problem solving", "lifecycle": "active", "contextWindow": 80000, "maxOutputTokens": 80000, "knowledgeCutoff": "2024-07", "structuredOutput": false, "lastUpdated": "2025-05-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "@cf/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": 1310720, "maxOutputTokens": 1048576, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "@cf/deepseek-ai/deepseek-v4-pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "@cf/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": 256000, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "@cf/ibm-granite/granite-4.0-h-micro": { "displayName": "Granite 4.0 H Micro", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 131000, "structuredOutput": false, "lastUpdated": "2025-10-07", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "@cf/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": 1310720, "maxOutputTokens": 1048576, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "@cf/deepseek-ai/deepseek-v4-pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "@cf/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": 256000, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "@cf/ibm-granite/granite-4.0-h-micro": { "displayName": "Granite 4.0 H Micro", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 131000, "structuredOutput": false, "lastUpdated": "2025-10-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "@cf/meta/llama-3.1-8b-instruct-fp8": { "displayName": "Llama 3.1 8B Instruct fp8", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 32000, "maxOutputTokens": 32000, "knowledgeCutoff": "2023-12", "structuredOutput": false, "lastUpdated": "2024-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "@cf/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": 128000, "knowledgeCutoff": "2023-12", "structuredOutput": false, "lastUpdated": "2024-09-25", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "@cf/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": 60000, "maxOutputTokens": 60000, "knowledgeCutoff": "2023-12", "structuredOutput": false, "lastUpdated": "2024-09-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -280,20 +288,20 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "@cf/meta/llama-3.3-70b-instruct-fp8-fast": { "displayName": "Llama 3.3 70B Instruct fp8 Fast", "description": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting", "lifecycle": "active", "contextWindow": 24000, "maxOutputTokens": 24000, "knowledgeCutoff": "2023-12", "structuredOutput": false, "lastUpdated": "2024-12-06", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "@cf/meta/llama-4-scout-17b-16e-instruct": { "displayName": "Llama 4 Scout 17B 16E Instruct", "description": "Open Llama with long-context vision for efficient multimodal agents", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-08", "structuredOutput": false, "lastUpdated": "2025-04-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "@cf/meta/llama-guard-3-8b": { "displayName": "Llama Guard 3 8B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2023-12", "structuredOutput": false, "lastUpdated": "2024-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "@cf/mistralai/mistral-small-3.1-24b-instruct": { "displayName": "Mistral Small 3.1 24B Instruct", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "structuredOutput": false, "lastUpdated": "2025-03-18", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "@cf/moonshotai/kimi-k2.6": { "displayName": "Kimi K2.6", "description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "@cf/moonshotai/kimi-k2.7-code": { "displayName": "Kimi K2.7 Code", "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "@cf/mistralai/mistral-small-3.1-24b-instruct": { "displayName": "Mistral Small 3.1 24B Instruct", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-06", "structuredOutput": false, "lastUpdated": "2025-03-17", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "@cf/moonshotai/kimi-k2.6": { "displayName": "Kimi K2.6", "description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "@cf/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"], "output": ["text"] } },
         "@cf/nvidia/nemotron-3-120b-a12b": { "displayName": "Nemotron 3 Super 120B", "description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "structuredOutput": true, "lastUpdated": "2026-03-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "@cf/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": 16384, "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "@cf/openai/gpt-oss-20b": { "displayName": "GPT OSS 20B", "description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "@cf/openai/gpt-oss-20b": { "displayName": "GPT OSS 20B", "description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "@cf/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": 32768, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2024-11-12", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "@cf/qwen/qwen3-30b-a3b-fp8": { "displayName": "Qwen3 30B A3b fp8", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2025-04-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "@cf/qwen/qwen3.8-27b": { "displayName": "Qwen3.8 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "@cf/qwen/qwq-32b": { "displayName": "Qwq 32B", "description": "Qwen reasoning model for deliberate problem solving, math, and coding", "lifecycle": "active", "contextWindow": 24000, "maxOutputTokens": 24000, "knowledgeCutoff": "2024-04", "structuredOutput": false, "lastUpdated": "2025-03-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "@cf/zai-org/glm-4.7-flash": { "displayName": "GLM-4.7-Flash", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "@cf/zai-org/glm-5.2": { "displayName": "Glm 5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "@cf/zai-org/glm-5.3": { "displayName": "Glm 5.3", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 1310720, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "@cf/zai-org/glm-5.3-flash": { "displayName": "Glm 5.3 Flash", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "@cf/zai-org/glm-4.7-flash": { "displayName": "GLM-4.7-Flash", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "@cf/zai-org/glm-5.2": { "displayName": "Glm 5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "@cf/zai-org/glm-5.3": { "displayName": "Glm 5.3", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "@cf/zai-org/glm-5.3-flash": { "displayName": "Glm 5.3 Flash", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
     },
     "deepinfra": {
         "ByteDance/Seed-2.0-code": { "displayName": "Seed 2.0 Code", "description": "ByteDance Seed coding model for multimodal software engineering and long-running agents", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-02-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
@@ -306,7 +314,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "deepseek-ai/DeepSeek-V3.2": { "displayName": "DeepSeek-V3.2", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 64000, "knowledgeCutoff": "2024-12", "structuredOutput": true, "lastUpdated": "2025-12-02", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V4-Flash": { "displayName": "DeepSeek V4 Flash", "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V4-Flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high", "max"] }, "modalities": { "input": ["text", "image"], "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": 16384, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V4-Pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V4.1-Flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
@@ -352,10 +360,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "Qwen/Qwen3.8-Max": { "displayName": "Qwen3.8 Max", "description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-03", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
         "stepfun-ai/Step-3.7-Flash": { "displayName": "Step 3.7 Flash", "description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "knowledgeCutoff": "2026-03-01", "lastUpdated": "2026-05-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "tencent/Hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "inputLimit": 192000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-07-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "thinkingmachines/Inkling": { "displayName": "Inkling", "description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 1048576, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
+        "thinkingmachines/Inkling": { "displayName": "Inkling", "description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
         "thinkingmachines/Inkling-Small": { "displayName": "Inkling Small", "description": "Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-07-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
         "XiaomiMiMo/MiMo-V2.5": { "displayName": "MiMo-V2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-12", "structuredOutput": true, "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
         "XiaomiMiMo/MiMo-V2.5-Pro": { "displayName": "MiMo-V2.5-Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-12", "structuredOutput": true, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "audio"], "output": ["text"] } },
+        "XiaomiMiMo/MiMo-V2.6-Flash": { "displayName": "MiMo-V2.6-Flash", "description": "MiMo Flash model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "XiaomiMiMo/MiMo-V2.6-Pro": { "displayName": "MiMo-V2.6-Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
         "zai-org/GLM-4.6": { "displayName": "GLM-4.6", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09-30", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai-org/GLM-4.7": { "displayName": "GLM-4.7", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-12-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai-org/GLM-4.7-Flash": { "displayName": "GLM-4.7-Flash", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "deprecated", "contextWindow": 202752, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -366,35 +376,46 @@ 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": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
     },
     "deepseek": {
-        "deepseek-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "deepseek-v4-flash": { "displayName": "DeepSeek V4 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "deepseek-v4-pro": { "displayName": "DeepSeek V4 Pro", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "deepseek-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 393216, "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"] } },
+        "deepseek-v4-flash": { "displayName": "DeepSeek V4 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "deprecated", "contextWindow": 1000000, "maxOutputTokens": 393216, "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"] } },
+        "deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "deprecated", "contextWindow": 1000000, "maxOutputTokens": 393216, "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"] } },
+        "deepseek-v4-pro": { "displayName": "DeepSeek V4 Pro", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 393216, "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"] } },
     },
     "fireworks-ai": {
-        "accounts/fireworks/models/deepseek-v4-flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "accounts/fireworks/models/deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "accounts/fireworks/models/deepseek-v4-pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "accounts/fireworks/models/deepseek-v4-flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "deprecated", "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"] } },
+        "accounts/fireworks/models/deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "deprecated", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "accounts/fireworks/models/deepseek-v4-pro": { "displayName": "DeepSeek V4 Pro", "description": "Open MoE flagship with million-token context for coding and long agent runs", "lifecycle": "deprecated", "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"] } },
+        "accounts/fireworks/models/deepseek-v4-pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "deprecated", "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"] } },
         "accounts/fireworks/models/deepseek-v4p1-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "accounts/fireworks/models/glm-5p2": { "displayName": "GLM 5.2", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1048575, "maxOutputTokens": 131072, "lastUpdated": "2026-06-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "accounts/fireworks/models/ember-1": { "displayName": "Ember-1", "description": "Specialized model from Fireworks built on Kimi K3, producing shorter reasoning traces with approximately 40% fewer tokens while maintaining comparable quality", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "accounts/fireworks/models/glm-5p2": { "displayName": "GLM 5.2", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "deprecated", "contextWindow": 1048575, "maxOutputTokens": 131072, "lastUpdated": "2026-06-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "accounts/fireworks/models/glm-5p3": { "displayName": "GLM 5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1048573, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-09-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "accounts/fireworks/models/glm-5p3-flash": { "displayName": "GLM 5.3 Flash", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow": 1048573, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
+        "accounts/fireworks/models/glm-5p3-flash": { "displayName": "GLM 5.3 Flash", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow": 1048573, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "accounts/fireworks/models/gpt-oss-120b": { "displayName": "GPT OSS 120B", "description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "lastUpdated": "2026-06-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "accounts/fireworks/models/inkling": { "displayName": "Inkling", "description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
-        "accounts/fireworks/models/kimi-k2p6": { "displayName": "Kimi K2.6", "description": "Kimi reasoning model for long-horizon research, planning, and tool use", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "lastUpdated": "2026-04-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "accounts/fireworks/models/kimi-k2p7-code": { "displayName": "Kimi K2.7 Code", "description": "Kimi coding model for software agents, refactors, and repository reasoning", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "lastUpdated": "2026-06-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "accounts/fireworks/models/kimi-k2p6": { "displayName": "Kimi K2.6", "description": "Kimi reasoning model for long-horizon research, planning, and tool use", "lifecycle": "deprecated", "contextWindow": 262000, "maxOutputTokens": 262000, "lastUpdated": "2026-04-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "accounts/fireworks/models/kimi-k2p7-code": { "displayName": "Kimi K2.7 Code", "description": "Kimi coding model for software agents, refactors, and repository reasoning", "lifecycle": "deprecated", "contextWindow": 262000, "maxOutputTokens": 262000, "lastUpdated": "2026-06-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "accounts/fireworks/models/kimi-k3": { "displayName": "Kimi K3", "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "accounts/fireworks/models/minimax-m3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 512000, "maxOutputTokens": 512000, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "accounts/fireworks/models/mistral-large-3-fp8": { "displayName": "Mistral Large 3 675B Instruct 2512", "description": "Mistral's largest general model for enterprise agents, coding, and multilingual reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2024-11", "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "accounts/fireworks/models/muse-glimmer-30b": { "displayName": "Muse Glimmer 30B", "description": "Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2026-01-04", "structuredOutput": true, "lastUpdated": "2026-08-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "accounts/fireworks/models/minimax-m2p7": { "displayName": "MiniMax-M2.7", "description": "Open MiniMax flagship for coding agents, office automation, and complex environments", "lifecycle": "deprecated", "contextWindow": 196608, "maxOutputTokens": 131072, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "accounts/fireworks/models/minimax-m3": { "displayName": "MiniMax-M3", "description": "Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 512000, "maxOutputTokens": 512000, "lastUpdated": "2026-06-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "accounts/fireworks/models/muse-glimmer-30b": { "displayName": "Muse Glimmer 30B", "description": "Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.", "lifecycle": "deprecated", "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"] } },
         "accounts/fireworks/models/nemotron-3-ultra-nvfp4": { "displayName": "Nemotron 3 Ultra 550B A55B", "description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 128000, "lastUpdated": "2026-06-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": { "displayName": "Nemotron 3.5 Lightning 30B A3B", "description": "Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-08-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "accounts/fireworks/models/qwen3p7-plus": { "displayName": "Qwen 3.7 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "accounts/fireworks/models/qwen3p8-2p4t-a95b": { "displayName": "Qwen3.8 2.4T A95B", "description": "Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "accounts/fireworks/models/qwen3p8-max": { "displayName": "Qwen3.8 Max", "description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 131072, "lastUpdated": "2026-08-03", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "accounts/fireworks/models/qwen3p8-max": { "displayName": "Qwen3.8 Max", "description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 131072, "lastUpdated": "2026-08-03", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "accounts/fireworks/routers/deepseek-flash-latest": { "displayName": "DeepSeek Flash Latest", "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"] } },
+        "accounts/fireworks/routers/deepseek-pro-latest": { "displayName": "DeepSeek Pro Latest", "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"] } },
         "accounts/fireworks/routers/glm-5p2-fast": { "displayName": "GLM 5.2 Fast", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 1048575, "maxOutputTokens": 131072, "lastUpdated": "2026-06-26", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "accounts/fireworks/routers/glm-5p3-fast": { "displayName": "GLM 5.3 Fast", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1048572, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-09-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "accounts/fireworks/routers/glm-fast-latest": { "displayName": "GLM 5.3 Fast (Latest)", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1048572, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-09-15", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "accounts/fireworks/routers/glm-flash-latest": { "displayName": "GLM Flash Latest (GLM 5.3 Flash)", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow": 1048573, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "accounts/fireworks/routers/glm-latest": { "displayName": "GLM Latest", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1048573, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-09-15", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "accounts/fireworks/routers/kimi-fast-latest": { "displayName": "Kimi Fast Latest", "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": "2026-09-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "accounts/fireworks/routers/kimi-k3-fast": { "displayName": "Kimi K3 Fast", "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "accounts/fireworks/routers/kimi-latest": { "displayName": "Kimi Latest", "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": "2026-09-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "accounts/fireworks/routers/minimax-latest": { "displayName": "MiniMax Latest", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 512000, "maxOutputTokens": 512000, "lastUpdated": "2026-09-15", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "accounts/fireworks/routers/qwen-max-latest": { "displayName": "Qwen Max Latest (Qwen3.8 Max)", "description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 131072, "lastUpdated": "2026-09-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
     },
     "github-copilot": {
         "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"] } },
@@ -403,6 +424,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "claude-opus-4.7": { "displayName": "Claude Opus 4.7", "description": "Stronger Opus tier for advanced software work and high-stakes reasoning", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 168000, "maxOutputTokens": 32000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "claude-opus-4.8": { "displayName": "Claude Opus 4.8", "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 168000, "maxOutputTokens": 64000, "knowledgeCutoff": "2026-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "claude-opus-5": { "displayName": "Claude Opus 5", "description": "Strongest Claude Opus model for coding, agents, and professional work", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 936000, "maxOutputTokens": 64000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-07-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "claude-opus-5.5": { "displayName": "Claude Opus 5.5", "description": "Claude model for long-running agentic coding and knowledge work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "claude-sonnet-4.6": { "displayName": "Claude Sonnet 4.6", "description": "Claude workhorse for coding agents, careful analysis, and production cost control", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 168000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "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"] } },
         "gemini-3.5-flash": { "displayName": "Gemini 3.5 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 200000, "inputLimit": 128000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-05-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
@@ -419,8 +441,11 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "gpt-5.6-sol": { "displayName": "GPT-5.6 Sol", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "gpt-5.6-terra": { "displayName": "GPT-5.6 Terra", "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "gpt-6-astra": { "displayName": "GPT-6 Astra", "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-30", "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "gpt-6-luna": { "displayName": "GPT-6 Luna", "description": "OpenAI's most efficient model for focused, high-volume tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05-18", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "gpt-6-sol": { "displayName": "GPT-6 Sol", "description": "OpenAI model for complex coding and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-20", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "grok-4.5": { "displayName": "Grok 4.5", "description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk", "lifecycle": "active", "contextWindow": 500000, "inputLimit": 372000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "grok-4.6": { "displayName": "Grok 4.6", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "lifecycle": "active", "contextWindow": 500000, "inputLimit": 372000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-01", "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "grok-4.7": { "displayName": "Grok 4.7", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "lifecycle": "active", "contextWindow": 500000, "inputLimit": 372000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-09-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "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": 256000, "inputLimit": 224000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "kimi-k3": { "displayName": "Kimi K3", "description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "mai-code-1-flash-picker": { "displayName": "MAI-Code-1-Flash", "description": "Microsoft coding model built for fast, efficient assistance in everyday developer workflows", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 128000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12", "structuredOutput": true, "lastUpdated": "2026-06-08", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -429,7 +454,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
     "google": {
         "deep-research-max-preview-04-2026": { "displayName": "Deep Research Max Preview (Apr-21-2026)", "description": "Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text", "image"] } },
         "deep-research-preview-04-2026": { "displayName": "Deep Research Preview (Apr-21-2026)", "description": "Agentic model for autonomous multi-step research, synthesis, and cited reports", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text", "image"] } },
-        "gemini-2.5-computer-use-preview-10-2025": { "displayName": "Gemini 2.5 Computer Use Preview 10-2025", "description": "Specialized Gemini 2.5 model for browser-control agents that automate UI tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "lastUpdated": "2025-10-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "gemini-2.5-computer-use-preview-10-2025": { "displayName": "Gemini 2.5 Computer Use Preview 10-2025", "description": "Specialized Gemini 2.5 model for browser-control agents that automate UI tasks", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01", "lastUpdated": "2025-10-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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": 65536, "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"] } },
         "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": 32768, "knowledgeCutoff": "2024-06", "lastUpdated": "2025-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
         "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": 65536, "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"] } },
@@ -437,12 +462,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "gemini-2.5-pro": { "displayName": "Gemini 2.5 Pro", "description": "Google's proven reasoning model for coding, math, and multimodal analysis", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-06-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio", "video", "pdf"], "output": ["text"] } },
         "gemini-2.5-pro-preview-tts": { "displayName": "Gemini 2.5 Pro Preview TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-01", "lastUpdated": "2025-05-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
         "gemini-3-flash-preview": { "displayName": "Gemini 3 Flash Preview", "description": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-12-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
-        "gemini-3-pro-image": { "displayName": "Nano Banana Pro", "description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
+        "gemini-3-pro-image": { "displayName": "Nano Banana Pro", "description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
         "gemini-3-pro-image-preview": { "displayName": "Nano Banana Pro", "description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2025-11-20", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
-        "gemini-3.1-flash-image": { "displayName": "Nano Banana 2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["minimal", "high"] }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text", "image"] } },
+        "gemini-3.1-flash-image": { "displayName": "Nano Banana 2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["minimal", "high"] }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text", "image"] } },
         "gemini-3.1-flash-image-preview": { "displayName": "Nano Banana 2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["minimal", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text", "image"] } },
         "gemini-3.1-flash-lite": { "displayName": "Gemini 3.1 Flash Lite", "description": "Low-latency Gemini model for high-volume multimodal and agent workloads", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-05-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
-        "gemini-3.1-flash-lite-image": { "displayName": "Nano Banana 2 Lite", "description": "Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": false, "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
+        "gemini-3.1-flash-lite-image": { "displayName": "Nano Banana 2 Lite", "description": "Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 4096, "knowledgeCutoff": "2025-01", "structuredOutput": false, "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
         "gemini-3.1-flash-lite-preview": { "displayName": "Gemini 3.1 Flash Lite Preview", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-03-03", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
         "gemini-3.1-flash-live-preview": { "displayName": "Gemini 3.1 Flash Live Preview", "description": "High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": false, "lastUpdated": "2026-03-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio"], "output": ["text", "audio"] } },
         "gemini-3.1-flash-tts-preview": { "displayName": "Gemini 3.1 Flash TTS Preview", "description": "Low-latency speech generation with steerable prompts and expressive audio tags", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-15", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
@@ -494,7 +519,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "deepseek-ai/DeepSeek-V3.2": { "displayName": "DeepSeek-V3.2", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 65536, "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V4-Flash": { "displayName": "DeepSeek V4 Flash", "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V4-Flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "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": ["high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V4-Pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V4.1-Flash": { "displayName": "DeepSeek V4.1 Flash", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
@@ -546,6 +571,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "stepfun-ai/Step-3.5-Flash": { "displayName": "Step 3.5 Flash", "description": "StepFun flash lane for quick multimodal reasoning and coding assistance", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "stepfun-ai/Step-3.7-Flash": { "displayName": "Step 3.7 Flash", "description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "knowledgeCutoff": "2026-03-01", "lastUpdated": "2026-05-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "tencent/Hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "inputLimit": 192000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-07-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "tencent/Hy4-preview": { "displayName": "Hy4 preview", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-08-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "thinkingmachines/Inkling": { "displayName": "Inkling", "description": "Multimodal model for analyzing text, images, documents, and rich media", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "thinkingmachines/Inkling-Small": { "displayName": "Inkling Small", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 1048576, "lastUpdated": "2026-07-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "XiaomiMiMo/MiMo-V2-Flash": { "displayName": "MiMo-V2-Flash", "description": "MiMo flash model for fast multimodal assistance and agent workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-12", "lastUpdated": "2025-12-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -577,7 +603,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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": "Open MiniMax flagship for coding agents, office automation, and complex environments", "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": "Low-latency M2.7 variant for interactive coding plans and agent loops", "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 model for long-context coding, perception, and agent planning", "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-M3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 512000, "lastUpdated": "2026-06-25", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
     },
     "MiniMax-cn": {
         "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"] } },
@@ -586,7 +612,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
+        "MiniMax-M3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -631,19 +657,20 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "voxtral-mini-latest": { "displayName": "Voxtral Mini (latest)", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "lifecycle": "active", "lastUpdated": "2026-02-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["text"] } },
         "voxtral-mini-tts-latest": { "displayName": "Voxtral Mini TTS (latest)", "description": "Multilingual text-to-speech model with zero-shot voice cloning", "lifecycle": "active", "lastUpdated": "2026-03-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
         "voxtral-small-latest": { "displayName": "Voxtral Small (latest)", "description": "Instruct model with native audio input for speech understanding and tool use", "lifecycle": "active", "contextWindow": 32000, "maxOutputTokens": 32000, "lastUpdated": "2025-07-15", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "audio"], "output": ["text"] } },
-        "zai-glm-5-2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "beta", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "zai-glm-5-2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "beta", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "zai-glm-5-3": { "displayName": "GLM-5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
     },
     "moonshot": {
         "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 }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "kimi-k2.7-code-highspeed": { "displayName": "Kimi K2.7 Code HighSpeed", "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "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"] } },
+        "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": 1048576, "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"] } },
     },
     "moonshot-global": {
         "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 }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "kimi-k2.7-code-highspeed": { "displayName": "Kimi K2.7 Code HighSpeed", "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "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"] } },
+        "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": 1048576, "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", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -749,6 +776,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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": { "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"] } },
         "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": {
@@ -812,6 +840,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "gpt-5.6-sol": { "displayName": "GPT-5.6 Sol", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "gpt-5.6-terra": { "displayName": "GPT-5.6 Terra", "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "gpt-6-astra": { "displayName": "GPT-6 Astra", "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-30", "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "gpt-6-luna": { "displayName": "GPT-6 Luna", "description": "OpenAI's most efficient model for focused, high-volume tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05-18", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "gpt-6-sol": { "displayName": "GPT-6 Sol", "description": "OpenAI model for complex coding and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-20", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "gpt-image-1": { "displayName": "gpt-image-1", "description": "OpenAI image model for production generation, edits, and brand-safe visual workflows", "lifecycle": "deprecated", "lastUpdated": "2025-04-24", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["image"] } },
         "gpt-image-1-mini": { "displayName": "gpt-image-1-mini", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2025-09-26", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
         "gpt-image-1.5": { "displayName": "gpt-image-1.5", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2025-11-25", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
@@ -839,14 +869,16 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "claude-opus-4-7": { "displayName": "Claude Opus 4.7", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "claude-opus-4-8": { "displayName": "Claude Opus 4.8", "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "claude-opus-5": { "displayName": "Claude Opus 5", "description": "Strongest Claude Opus model for coding, agents, and professional work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05", "lastUpdated": "2026-07-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "claude-opus-5-5": { "displayName": "Claude Opus 5.5", "description": "Claude model for long-running agentic coding and knowledge work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "claude-sonnet-4": { "displayName": "Claude Sonnet 4", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "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": "2025-07-31", "lastUpdated": "2025-09-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "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", "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-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": "2026-09-01", "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"] } },
+        "deepseek-v4.1-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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"] } },
         "gemini-3-pro": { "displayName": "Gemini 3 Pro", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-11-18", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
         "gemini-3.1-pro": { "displayName": "Gemini 3.1 Pro Preview", "description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-02-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "audio", "pdf"], "output": ["text"] } },
@@ -882,11 +914,14 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "gpt-5.5": { "displayName": "GPT-5.5", "description": "Default frontier GPT for coding, computer use, research, and knowledge work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12-01", "structuredOutput": true, "lastUpdated": "2026-04-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "gpt-5.5-pro": { "displayName": "GPT-5.5 Pro", "description": "Frontier GPT model for professional reasoning, coding, and multimodal work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12-01", "structuredOutput": false, "lastUpdated": "2026-04-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "gpt-5.6-luna": { "displayName": "GPT-5.6 Luna", "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "gpt-5.6-sol": { "displayName": "GPT-5.6 Sol (50% Off)", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "gpt-5.6-sol": { "displayName": "GPT-5.6 Sol", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "gpt-5.6-terra": { "displayName": "GPT-5.6 Terra", "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "gpt-6-astra": { "displayName": "GPT-6 Astra", "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-30", "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "gpt-6-luna": { "displayName": "GPT-6 Luna", "description": "OpenAI's most efficient model for focused, high-volume tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05-18", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "gpt-6-sol": { "displayName": "GPT-6 Sol", "description": "OpenAI model for complex coding and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-20", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "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-4.7": { "displayName": "Grok 4.7 (30% Off)", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-09-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "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", "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"] } },
@@ -907,7 +942,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
+        "mimo-v2.5-free": { "displayName": "MiMo V2.5 Free", "description": "MiMo omni model for text, image, video, audio, and agents", "lifecycle": "deprecated", "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"] } },
+        "mimo-v2.6-flash-free": { "displayName": "MiMo-V2.6-Flash Free", "description": "MiMo Flash model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 32000, "lastUpdated": "2026-09-22", "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", "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"] } },
@@ -917,7 +953,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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", "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": { "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"] }, "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", "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"] } },
@@ -927,13 +963,15 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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", "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"] } },
         "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"] } },
+        "space-bunny-free": { "displayName": "Space Bunny Free", "description": "Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input", "lifecycle": "active", "contextWindow": 1048576, "inputLimit": 524288, "maxOutputTokens": 524288, "lastUpdated": "2026-09-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "video"], "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"] } },
-        "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-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": "2026-09-01", "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 (New)", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-v4.1-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "glm-5": { "displayName": "GLM-5", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 202752, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -942,8 +980,10 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
         "gpt-5.6-luna": { "displayName": "GPT-5.6 Luna", "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "gpt-6-luna": { "displayName": "GPT-6 Luna", "description": "OpenAI's most efficient model for focused, high-volume tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05-18", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "grok-4.5": { "displayName": "Grok 4.5", "description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk", "lifecycle": "deprecated", "contextWindow": 500000, "maxOutputTokens": 500000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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-4.7": { "displayName": "Grok 4.7", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-09-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "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", "low", "high"] }, "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"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "kimi-k2.5": { "displayName": "Kimi K2.5", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2024-10", "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
@@ -955,6 +995,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "mimo-v2-pro": { "displayName": "MiMo V2 Pro", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 1048576, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "mimo-v2.5": { "displayName": "MiMo V2.5", "description": "MiMo omni model for text, image, video, audio, and agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
         "mimo-v2.5-pro": { "displayName": "MiMo V2.5 Pro", "description": "MiMo pro model for strong multimodal reasoning and agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mimo-v2.6-flash": { "displayName": "MiMo-V2.6-Flash", "description": "MiMo Flash model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "mimo-v2.6-pro": { "displayName": "MiMo-V2.6-Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
         "minimax-m2.5": { "displayName": "MiniMax-M2.5", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 65536, "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 coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-31", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
@@ -968,15 +1010,16 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "qwen3.7-plus": { "displayName": "Qwen3.7 Plus", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "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 multimodal flagship for coding, professional work, 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"], "output": ["text"] } },
+        "space-bunny-free": { "displayName": "Space Bunny Free", "description": "Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input", "lifecycle": "active", "contextWindow": 1048576, "inputLimit": 524288, "maxOutputTokens": 524288, "lastUpdated": "2026-09-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
     },
     "openrouter": {
         "~anthropic/claude-fable-latest": { "displayName": "Claude Fable Latest", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "~anthropic/claude-haiku-latest": { "displayName": "Claude Haiku Latest", "description": "Fast Claude model for responsive assistance, classification, and lightweight agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "~anthropic/claude-opus-latest": { "displayName": "Claude Opus Latest", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "~anthropic/claude-opus-latest": { "displayName": "Claude Opus Latest", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "~anthropic/claude-sonnet-latest": { "displayName": "Claude Sonnet Latest", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "~deepseek/deepseek-flash-latest": { "displayName": "DeepSeek Flash Latest", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-09-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "~deepseek/deepseek-pro-latest": { "displayName": "DeepSeek Pro Latest", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-09-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "~deepseek/deepseek-v4-flash-latest": { "displayName": "DeepSeek V4 Flash Latest", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 393216, "structuredOutput": true, "lastUpdated": "2026-08-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "~deepseek/deepseek-v4-flash-latest": { "displayName": "DeepSeek V4 Flash Latest", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-08-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "~google/gemini-flash-latest": { "displayName": "Gemini Flash Latest", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01-01", "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
         "~google/gemini-pro-latest": { "displayName": "Gemini Pro Latest", "description": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["audio", "pdf", "image", "text", "video"], "output": ["text"] } },
         "~moonshotai/kimi-latest": { "displayName": "Kimi Latest", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
@@ -986,11 +1029,13 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "~openai/gpt-sol-latest": { "displayName": "GPT Sol Latest", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-09-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
         "~openai/gpt-terra-latest": { "displayName": "GPT Terra Latest", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-09-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
         "~x-ai/grok-latest": { "displayName": "Grok Latest", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 450000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "~z-ai/glm-flash-latest": { "displayName": "GLM Flash Latest", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "~z-ai/glm-flash-latest": { "displayName": "GLM Flash Latest", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-08-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "~z-ai/glm-latest": { "displayName": "GLM Latest", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "aion-labs/aion-2.0": { "displayName": "Aion-2.0", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-02-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "aion-labs/aion-3.0": { "displayName": "Aion-3.0", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "aion-labs/aion-3.0-mini": { "displayName": "Aion-3.0-Mini", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-07-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "aion-labs/aion-3.5": { "displayName": "Aion 3.5", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-09-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "aion-labs/aion-3.5-mini": { "displayName": "Aion 3.5 Mini", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": false, "lastUpdated": "2026-09-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "aion-labs/aion-rp-llama-3.1-8b": { "displayName": "Aion-RP 1.0 (8B)", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 29491, "knowledgeCutoff": "2023-12-31", "structuredOutput": false, "lastUpdated": "2025-02-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "amazon/nova-2-lite-v1": { "displayName": "Nova 2 Lite", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65535, "structuredOutput": false, "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
         "amazon/nova-lite-v1": { "displayName": "Nova Lite 1.0", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 300000, "maxOutputTokens": 5120, "knowledgeCutoff": "2024-10-31", "structuredOutput": false, "lastUpdated": "2024-12-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
@@ -1002,14 +1047,14 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "anthropic/claude-fable-5": { "displayName": "Claude Fable 5", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "structuredOutput": true, "lastUpdated": "2026-06-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "anthropic/claude-fable-5.1": { "displayName": "Claude Fable 5.1", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "structuredOutput": true, "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "anthropic/claude-haiku-4.5": { "displayName": "Claude Haiku 4.5 (latest)", "description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-02-28", "structuredOutput": true, "lastUpdated": "2025-10-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-opus-4": { "displayName": "Claude Opus 4", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-01-31", "structuredOutput": false, "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "pdf"], "output": ["text"] } },
         "anthropic/claude-opus-4.1": { "displayName": "Claude Opus 4.1 (latest)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-03-31", "structuredOutput": false, "lastUpdated": "2025-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "anthropic/claude-opus-4.5": { "displayName": "Claude Opus 4.5 (latest)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2025-11-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "anthropic/claude-opus-4.6": { "displayName": "Claude Opus 4.6", "description": "High-end Claude for difficult coding, planning, and slower expert reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-05-31", "structuredOutput": true, "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "anthropic/claude-opus-4.7": { "displayName": "Claude Opus 4.7", "description": "Stronger Opus tier for advanced software work and high-stakes reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "structuredOutput": true, "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "anthropic/claude-opus-4.8": { "displayName": "Claude Opus 4.8", "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01", "structuredOutput": true, "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "anthropic/claude-opus-5": { "displayName": "Claude Opus 5", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-07-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-sonnet-4": { "displayName": "Claude Sonnet 4", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-31", "structuredOutput": false, "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "pdf"], "output": ["text"] } },
+        "anthropic/claude-opus-5.5": { "displayName": "Claude Opus 5.5", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-sonnet-4": { "displayName": "Claude Sonnet 4", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-31", "structuredOutput": false, "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "pdf"], "output": ["text"] } },
         "anthropic/claude-sonnet-4.5": { "displayName": "Claude Sonnet 4.5 (latest)", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-07-31", "structuredOutput": true, "lastUpdated": "2025-09-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "anthropic/claude-sonnet-4.6": { "displayName": "Claude Sonnet 4.6", "description": "Claude workhorse for coding agents, careful analysis, and production cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "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", "structuredOutput": true, "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
@@ -1024,11 +1069,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "bytedance/ui-tars-1.5-7b": { "displayName": "UI-TARS 7B ", "description": "Multimodal model for analyzing text, images, documents, and rich media", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 2048, "knowledgeCutoff": "2025-01-31", "structuredOutput": true, "lastUpdated": "2025-07-22", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
         "cognitivecomputations/dolphin-mistral-24b-venice-edition": { "displayName": "Uncensored", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-04-30", "structuredOutput": false, "lastUpdated": "2025-07-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "cohere/command-a": { "displayName": "Command A", "description": "Cohere command model for multilingual enterprise agents, tools, and chat", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-08-31", "structuredOutput": true, "lastUpdated": "2025-03-13", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "cohere/command-a-plus": { "displayName": "Command A+", "description": "Cohere command model for multilingual enterprise agents, tools, and chat", "lifecycle": "active", "contextWindow": 192000, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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", "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": { "displayName": "DeepSeek Chat", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 16384, "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"] } },
         "deepseek/deepseek-r1": { "displayName": "DeepSeek-R1", "description": "Classic open reasoning model for transparent math, coding, and deliberate problem solving", "lifecycle": "active", "contextWindow": 64000, "maxOutputTokens": 16000, "knowledgeCutoff": "2024-07", "structuredOutput": false, "lastUpdated": "2025-05-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1039,10 +1085,10 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "deepseek/deepseek-v3.2-exp": { "displayName": "DeepSeek V3.2 Exp", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-07-31", "structuredOutput": true, "lastUpdated": "2025-09-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek/deepseek-v4-flash": { "displayName": "DeepSeek V4 Flash", "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek/deepseek-v4-flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 943718, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek/deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "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-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Fast DeepSeek model for efficient chat, coding help, and agent loops", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "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": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
+        "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": 131072, "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", "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"] } },
@@ -1083,11 +1129,9 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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", "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", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "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": 262144, "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"] } },
         "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", "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"] } },
@@ -1100,7 +1144,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "meta-llama/llama-4-maverick": { "displayName": "Llama 4 Maverick", "description": "Open multimodal Llama model for strong reasoning and fast responses", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-08-31", "structuredOutput": true, "lastUpdated": "2025-04-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "meta-llama/llama-4-scout": { "displayName": "Llama 4 Scout", "description": "Open multimodal Llama model for long-context analysis and efficient agents", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-08-31", "structuredOutput": true, "lastUpdated": "2025-04-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "meta-llama/llama-guard-4-12b": { "displayName": "Llama Guard 4 12B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 16384, "knowledgeCutoff": "2024-08-31", "structuredOutput": false, "lastUpdated": "2025-04-30", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
-        "meta/muse-glimmer-30b": { "displayName": "Muse Glimmer 30B", "description": "Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "knowledgeCutoff": "2026-01-04", "structuredOutput": true, "lastUpdated": "2026-08-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "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": 16384, "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-spark-1.1": { "displayName": "Muse Spark 1.1", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
         "meta/muse-spark-1.2": { "displayName": "Muse Spark 1.2", "description": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
         "meta/muse-spark-1.2-contributor": { "displayName": "Muse Spark 1.2 Contributor", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 943718, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video", "pdf", "audio"], "output": ["text"] } },
@@ -1110,20 +1154,18 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "microsoft/wizardlm-2-8x22b": { "displayName": "WizardLM-2 8x22B", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 65535, "maxOutputTokens": 8000, "knowledgeCutoff": "2024-04-30", "structuredOutput": false, "lastUpdated": "2024-04-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-01": { "displayName": "MiniMax-01", "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 1000192, "maxOutputTokens": 900172, "knowledgeCutoff": "2024-03-31", "structuredOutput": false, "lastUpdated": "2025-01-15", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "minimax/minimax-m1": { "displayName": "MiniMax M1", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 40000, "knowledgeCutoff": "2024-06-30", "structuredOutput": false, "lastUpdated": "2025-06-17", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "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, "structuredOutput": true, "lastUpdated": "2025-10-27", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "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": 176947, "structuredOutput": true, "lastUpdated": "2025-10-27", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-m2-her": { "displayName": "MiniMax-M2 Her", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 2048, "structuredOutput": false, "lastUpdated": "2026-01-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-m2.1": { "displayName": "MiniMax-M2.1", "description": "Earlier MiniMax agent model for practical coding and productivity tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "structuredOutput": false, "lastUpdated": "2025-12-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-m2.5": { "displayName": "MiniMax-M2.5", "description": "Prior MiniMax coding model for agent workflows, office edits, and automation", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-m2.7": { "displayName": "MiniMax-M2.7", "description": "Open MiniMax flagship for coding agents, office automation, and complex environments", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-m3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 512000, "structuredOutput": true, "lastUpdated": "2026-06-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "mistralai/codestral-2508": { "displayName": "Codestral 2508", "description": "Mistral coding model for code completion, generation, and developer workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 204800, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-08-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "pdf"], "output": ["text"] } },
-        "mistralai/devstral-2512": { "displayName": "Devstral 2", "description": "Mistral coding agent model for repository tasks and software engineering workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 209715, "knowledgeCutoff": "2025-12", "structuredOutput": true, "lastUpdated": "2025-12-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "pdf"], "output": ["text"] } },
         "mistralai/ministral-14b-2512": { "displayName": "Ministral 3 14B 2512", "description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 209715, "structuredOutput": true, "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "mistralai/ministral-3b-2512": { "displayName": "Ministral 3 3B 2512", "description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 104857, "structuredOutput": true, "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "mistralai/ministral-8b-2512": { "displayName": "Ministral 3 8B 2512", "description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 209715, "structuredOutput": true, "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "mistralai/mistral-large": { "displayName": "Mistral Large", "description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 102400, "knowledgeCutoff": "2024-11-30", "structuredOutput": true, "lastUpdated": "2024-02-26", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "pdf"], "output": ["text"] } },
         "mistralai/mistral-large-2407": { "displayName": "Mistral Large 2407", "description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 104857, "knowledgeCutoff": "2024-03-31", "structuredOutput": true, "lastUpdated": "2024-11-19", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "pdf"], "output": ["text"] } },
-        "mistralai/mistral-large-2512": { "displayName": "Mistral Large 3", "description": "Mistral's largest general model for enterprise agents, coding, and multilingual reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 209715, "knowledgeCutoff": "2024-11", "structuredOutput": true, "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "mistralai/mistral-medium-3": { "displayName": "Mistral Medium 3", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 104857, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-05-07", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "mistralai/mistral-medium-3-5": { "displayName": "Mistral Medium 3.5", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 209715, "structuredOutput": true, "lastUpdated": "2026-04-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "mistralai/mistral-medium-3.1": { "displayName": "Mistral Medium 3.1", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 104857, "knowledgeCutoff": "2025-06-30", "structuredOutput": true, "lastUpdated": "2025-08-13", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
@@ -1131,7 +1173,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "mistralai/mistral-saba": { "displayName": "Saba", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 26214, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-02-17", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "pdf"], "output": ["text"] } },
         "mistralai/mistral-small-24b-instruct-2501": { "displayName": "Mistral Small 3", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 16384, "knowledgeCutoff": "2023-10-31", "structuredOutput": true, "lastUpdated": "2025-01-30", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "mistralai/mistral-small-2603": { "displayName": "Mistral Small 4", "description": "Fast Mistral production model for chat, extraction, and cost-sensitive agents", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 209715, "knowledgeCutoff": "2025-06", "structuredOutput": true, "lastUpdated": "2026-03-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistralai/mistral-small-3.1-24b-instruct": { "displayName": "Mistral Small 3.1 24B", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 102400, "knowledgeCutoff": "2023-10-31", "structuredOutput": false, "lastUpdated": "2025-03-17", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "mistralai/mistral-small-3.1-24b-instruct": { "displayName": "Mistral Small 3.1 24B", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 102400, "knowledgeCutoff": "2023-10-31", "structuredOutput": false, "lastUpdated": "2025-03-17", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "mistralai/mistral-small-3.2-24b-instruct": { "displayName": "Mistral Small 3.2 24B", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 16384, "knowledgeCutoff": "2023-10-31", "structuredOutput": true, "lastUpdated": "2025-06-20", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
         "mistralai/mixtral-8x22b-instruct": { "displayName": "Mixtral 8x22B Instruct", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 52428, "knowledgeCutoff": "2024-01-31", "structuredOutput": true, "lastUpdated": "2024-04-17", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "pdf"], "output": ["text"] } },
         "mistralai/voxtral-small-24b-2507": { "displayName": "Voxtral Small 24B 2507", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 26214, "structuredOutput": true, "lastUpdated": "2025-07-15", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "audio", "pdf"], "output": ["text"] } },
@@ -1204,11 +1246,15 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "openai/gpt-5.6-terra-pro": { "displayName": "GPT-5.6 Terra Pro", "description": "Frontier GPT model for professional reasoning, coding, and multimodal work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/gpt-6-astra": { "displayName": "GPT-6 Astra", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-30", "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/gpt-6-astra-pro": { "displayName": "GPT-6 Astra Pro", "description": "Frontier GPT model for professional reasoning, coding, and multimodal work", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
+        "openai/gpt-6-luna": { "displayName": "GPT-6 Luna", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05-18", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-6-luna-pro": { "displayName": "GPT-6 Luna Pro", "description": "Frontier GPT model for professional reasoning, coding, and multimodal work", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
+        "openai/gpt-6-sol": { "displayName": "GPT-6 Sol", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-20", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-6-sol-pro": { "displayName": "GPT-6 Sol Pro", "description": "Frontier GPT model for professional reasoning, coding, and multimodal work", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["pdf", "image", "text"], "output": ["text"] } },
         "openai/gpt-audio": { "displayName": "GPT Audio", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
         "openai/gpt-audio-mini": { "displayName": "GPT Audio Mini", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
         "openai/gpt-chat-latest": { "displayName": "GPT Chat Latest", "description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "lifecycle": "active", "contextWindow": 400000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-05-05", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-oss-120b": { "displayName": "GPT OSS 120B", "description": "Open GPT reasoning model for self-hosted agents and controllable deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "openai/gpt-oss-20b": { "displayName": "GPT OSS 20B", "description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "openai/gpt-oss-120b": { "displayName": "GPT OSS 120B", "description": "Open GPT reasoning model for self-hosted agents and controllable deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2025-08-05", "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/gpt-oss-safeguard-20b": { "displayName": "GPT OSS Safeguard 20B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2025-10-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "openai/o1": { "displayName": "o1", "description": "O-series reasoning model for hard analysis, math, coding, and planning", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 100000, "knowledgeCutoff": "2023-09", "structuredOutput": true, "lastUpdated": "2024-12-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/o1-pro": { "displayName": "o1-pro", "description": "O-series reasoning model for hard analysis, math, coding, and planning", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 100000, "knowledgeCutoff": "2023-09", "structuredOutput": true, "lastUpdated": "2025-03-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
@@ -1233,6 +1279,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "prism-ml/ternary-bonsai-2-27b": { "displayName": "Ternary Bonsai 2 27B", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-09-18", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image"], "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"] } },
@@ -1255,24 +1302,24 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "qwen/qwen3-coder-plus": { "displayName": "Qwen3 Coder Plus", "description": "Hosted Qwen coder for software agents, repo edits, and long-context code", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-07-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen/qwen3-max": { "displayName": "Qwen3 Max", "description": "Flagship Qwen3 model for coding agents, complex reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen/qwen3-max-thinking": { "displayName": "Qwen3 Max Thinking", "description": "Qwen reasoning model for deliberate problem solving, math, and coding", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-09", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen/qwen3-next-80b-a3b-instruct": { "displayName": "Qwen3-Next 80B-A3B Instruct", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "qwen/qwen3-next-80b-a3b-thinking": { "displayName": "Qwen3-Next 80B-A3B (Thinking)", "description": "Efficient Qwen thinking model for local reasoning, math, and coding agents", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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": 235929, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "qwen/qwen3-next-80b-a3b-thinking": { "displayName": "Qwen3-Next 80B-A3B (Thinking)", "description": "Efficient Qwen thinking model for local reasoning, math, and coding agents", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen/qwen3-vl-235b-a22b-instruct": { "displayName": "Qwen3 VL 235B A22B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-09-23", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "qwen/qwen3-vl-235b-a22b-thinking": { "displayName": "Qwen3 VL 235B A22B Thinking", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-09-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "qwen/qwen3-vl-30b-a3b-instruct": { "displayName": "Qwen3 VL 30B A3B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-10-06", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "qwen/qwen3-vl-30b-a3b-instruct": { "displayName": "Qwen3 VL 30B A3B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-10-06", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "qwen/qwen3-vl-30b-a3b-thinking": { "displayName": "Qwen3 VL 30B A3B Thinking", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-10-06", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "qwen/qwen3-vl-32b-instruct": { "displayName": "Qwen3 VL 32B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2025-10-23", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "qwen/qwen3-vl-8b-instruct": { "displayName": "Qwen3 VL 8B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2025-10-14", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
         "qwen/qwen3-vl-8b-thinking": { "displayName": "Qwen3 VL 8B Thinking", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2025-10-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
         "qwen/qwen3.5-122b-a10b": { "displayName": "Qwen3.5 122B-A10B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "qwen/qwen3.5-27b": { "displayName": "Qwen3.5 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "qwen/qwen3.5-35b-a3b": { "displayName": "Qwen3.5 35B-A3B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "qwen/qwen3.5-35b-a3b": { "displayName": "Qwen3.5 35B-A3B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "qwen/qwen3.5-397b-a17b": { "displayName": "Qwen3.5 397B-A17B", "description": "Large open Qwen multimodal MoE for visual agents and long technical tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-02-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "qwen/qwen3.5-9b": { "displayName": "Qwen3.5 9B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "qwen/qwen3.5-9b": { "displayName": "Qwen3.5 9B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "qwen/qwen3.5-flash-02-23": { "displayName": "Qwen3.5-Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-02-25", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "qwen/qwen3.5-plus-02-15": { "displayName": "Qwen3.5 Plus 2026-02-15", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-02-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "qwen/qwen3.5-plus-20260420": { "displayName": "Qwen3.5 Plus 2026-04-20", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "qwen/qwen3.6-27b": { "displayName": "Qwen3.6 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "qwen/qwen3.6-27b": { "displayName": "Qwen3.6 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262140, "structuredOutput": true, "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "qwen/qwen3.6-35b-a3b": { "displayName": "Qwen3.6 35B-A3B", "description": "Open multimodal Qwen MoE for local agents that need vision, audio, and code", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-04-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "qwen/qwen3.6-flash": { "displayName": "Qwen3.6 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-04-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "qwen/qwen3.6-max-preview": { "displayName": "Qwen3.6 Max Preview", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-04-20", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1282,8 +1329,11 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "qwen/qwen3.7-plus": { "displayName": "Qwen3.7 Plus", "description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2026-06-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "qwen/qwen3.8-2.4t-a95b": { "displayName": "Qwen3.8 2.4T A95B", "description": "Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "qwen/qwen3.8-27b": { "displayName": "Qwen3.8 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "qwen/qwen3.8-27b:free": { "displayName": "Qwen3.8 27B (free)", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "qwen/qwen3.8-flash": { "displayName": "Qwen3.8 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "qwen/qwen3.8-max-0902": { "displayName": "Qwen3.8 Max 0902", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "qwen/qwen3.8-max-prime": { "displayName": "Qwen 3.8 Max Prime", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "qwen/qwen3.8-omni-flash": { "displayName": "Qwen3.8 Omni Flash", "description": "Qwen omni model for text, vision, audio, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
         "rekaai/reka-edge": { "displayName": "Reka Edge", "description": "Multimodal model for analyzing text, images, documents, and rich media", "lifecycle": "active", "contextWindow": 16384, "maxOutputTokens": 14745, "structuredOutput": true, "lastUpdated": "2026-03-20", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["image", "text", "video"], "output": ["text"] } },
         "rekaai/reka-flash-3": { "displayName": "Reka Flash 3", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 58982, "knowledgeCutoff": "2025-01-31", "structuredOutput": true, "lastUpdated": "2025-03-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "relace/relace-apply-3": { "displayName": "Relace Apply 3", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 128000, "structuredOutput": false, "lastUpdated": "2025-09-26", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1295,34 +1345,41 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "sao10k/l3-lunaris-8b": { "displayName": "Llama 3 8B Lunaris", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 7372, "knowledgeCutoff": "2023-12-31", "structuredOutput": true, "lastUpdated": "2024-08-13", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "sao10k/l3.1-euryale-70b": { "displayName": "Llama 3.1 Euryale 70B v2.2", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2023-12-31", "structuredOutput": true, "lastUpdated": "2024-08-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "sao10k/l3.3-euryale-70b": { "displayName": "Llama 3.3 Euryale 70B", "description": "Open Llama instruction model for multilingual chat, reasoning, and coding", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 16384, "knowledgeCutoff": "2023-12-31", "structuredOutput": true, "lastUpdated": "2024-12-18", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "stealth/space-bunny-alpha": { "displayName": "Space Bunny Alpha", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 524288, "structuredOutput": false, "lastUpdated": "2026-09-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "stepfun/step-3.5-flash": { "displayName": "Step 3.5 Flash", "description": "StepFun flash lane for quick multimodal reasoning and coding assistance", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": false, "lastUpdated": "2026-02-13", "capabilities": { "vision": false, "reasoning": true, "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": 262144, "inputLimit": 256000, "maxOutputTokens": 230400, "knowledgeCutoff": "2026-03-01", "structuredOutput": true, "lastUpdated": "2026-05-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "tencent/hunyuan-a13b-instruct": { "displayName": "Hunyuan A13B Instruct", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-07-08", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "tencent/hy-mt2-1.8b": { "displayName": "Hy-MT2-1.8B", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 4096, "structuredOutput": false, "lastUpdated": "2026-08-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "tencent/hy-mt2-30b-a3b": { "displayName": "Hy-MT2-30B-A3B", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2026-08-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "tencent/hy-mt2-30b-a3b": { "displayName": "Hy-MT2-30B-A3B", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2026-08-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "tencent/hy-mt2-7b": { "displayName": "Hy-MT2-7B", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 4096, "structuredOutput": true, "lastUpdated": "2026-08-19", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "tencent/hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "inputLimit": 192000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-07-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "tencent/hy3-preview": { "displayName": "Hy3 preview", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 235929, "structuredOutput": false, "lastUpdated": "2026-04-20", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "tencent/hy4-preview": { "displayName": "Hy4 preview", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-08-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "thedrummer/cydonia-24b-v4.1": { "displayName": "Cydonia 24B V4.1", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 117964, "knowledgeCutoff": "2024-04-30", "structuredOutput": true, "lastUpdated": "2025-09-27", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "thedrummer/skyfall-36b-v2": { "displayName": "Skyfall 36B V2", "description": "Open-weight instruction model for adaptable chat and self-hosted production workloads", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 29491, "knowledgeCutoff": "2024-06-30", "structuredOutput": true, "lastUpdated": "2025-03-10", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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"] } },
+        "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": false }, "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", "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"] } },
+        "unbiased/pareto": { "displayName": "Pareto", "description": "Blended multimodal model that runs multiple language models in parallel and returns a synthesized answer", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 131072, "structuredOutput": false, "lastUpdated": "2026-09-17", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "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"] } },
+        "upstage/solar-mini4": { "displayName": "Solar Mini 4", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "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": { "efforts": ["none", "minimal", "low", "medium", "high"] }, "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": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "writer/palmyra-x5": { "displayName": "Palmyra X5", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 1040000, "maxOutputTokens": 8192, "structuredOutput": false, "lastUpdated": "2026-01-21", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "x-ai/grok-4.20": { "displayName": "Grok 4.20", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 1800000, "knowledgeCutoff": "2025-09-01", "structuredOutput": true, "lastUpdated": "2026-03-31", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "x-ai/grok-4.20-multi-agent": { "displayName": "Grok 4.20 Multi-Agent", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 1800000, "knowledgeCutoff": "2025-09-01", "structuredOutput": true, "lastUpdated": "2026-03-31", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "x-ai/grok-4.3": { "displayName": "Grok 4.3", "description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 900000, "structuredOutput": true, "lastUpdated": "2026-04-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "x-ai/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": 450000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "x-ai/grok-4.6": { "displayName": "Grok 4.6", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 450000, "knowledgeCutoff": "2026-02-01", "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "x-ai/grok-4.7": { "displayName": "Grok 4.7", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 450000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-09-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "x-ai/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": 230400, "structuredOutput": true, "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "xiaomi/mimo-v2.5": { "displayName": "MiMo-V2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "structuredOutput": true, "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
         "xiaomi/mimo-v2.5-pro": { "displayName": "MiMo-V2.5-Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-12", "structuredOutput": true, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "xiaomi/mimo-v2.6-flash": { "displayName": "MiMo-V2.6-Flash", "description": "MiMo flash model for fast multimodal assistance and agent workflows", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "xiaomi/mimo-v2.6-pro": { "displayName": "MiMo-V2.6-Pro", "description": "MiMo pro model for strong multimodal reasoning and agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "xiaomi/mimo-v2.6-pro-ultraspeed": { "displayName": "MiMo-V2.6-Pro-UltraSpeed", "description": "MiMo pro model for strong multimodal reasoning and agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
         "z-ai/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", "structuredOutput": false, "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "z-ai/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", "structuredOutput": false, "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "z-ai/glm-4.5v": { "displayName": "GLM-4.5V", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "structuredOutput": false, "lastUpdated": "2025-08-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
@@ -1333,13 +1390,15 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "z-ai/glm-5": { "displayName": "GLM-5", "description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "z-ai/glm-5-turbo": { "displayName": "GLM-5-Turbo", "description": "Faster GLM-5 lane for coding agents that need lower latency", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 131072, "structuredOutput": false, "lastUpdated": "2026-03-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "z-ai/glm-5.1": { "displayName": "GLM-5.1", "description": "Strong GLM coding model for agentic engineering, terminals, and repository generation", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-04-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "z-ai/glm-5.2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "z-ai/glm-5.3": { "displayName": "GLM-5.3", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 943717, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "z-ai/glm-5.3-flash": { "displayName": "GLM-5.3-Flash", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "z-ai/glm-5.2": { "displayName": "GLM-5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "z-ai/glm-5.2:free": { "displayName": "GLM 5.2 (free)", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 29491, "structuredOutput": false, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "z-ai/glm-5.3": { "displayName": "GLM-5.3", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "z-ai/glm-5.3-flash": { "displayName": "GLM-5.3-Flash", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 1310720, "maxOutputTokens": 943718, "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"] } },
+        "z-ai/glm-5.3-flashx": { "displayName": "GLM 5.3 FlashX", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "structuredOutput": false, "lastUpdated": "2026-09-18", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "z-ai/glm-5.3-prime": { "displayName": "GLM 5.3 Prime", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": false, "lastUpdated": "2026-09-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "z-ai/glm-5v-turbo": { "displayName": "GLM-5V-Turbo", "description": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 202752, "maxOutputTokens": 131072, "structuredOutput": false, "lastUpdated": "2026-04-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["image", "text", "video"], "output": ["text"] } },
     },
     "siliconflow": {
-        "baidu/ERNIE-4.5-300B-A47B": { "displayName": "baidu/ERNIE-4.5-300B-A47B", "description": "Tool-capable chat model for instruction following and agentic application workflows", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 131000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "ByteDance-Seed/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-R1": { "displayName": "deepseek-ai/DeepSeek-R1", "description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools", "lifecycle": "active", "contextWindow": 164000, "maxOutputTokens": 164000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V3": { "displayName": "deepseek-ai/DeepSeek-V3", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 164000, "maxOutputTokens": 164000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1348,26 +1407,32 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "deepseek-ai/DeepSeek-V3.2": { "displayName": "deepseek-ai/DeepSeek-V3.2", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 164000, "maxOutputTokens": 164000, "structuredOutput": true, "lastUpdated": "2025-12-03", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V3.2-Exp": { "displayName": "deepseek-ai/DeepSeek-V3.2-Exp", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 164000, "maxOutputTokens": 164000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": 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": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "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 }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "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": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "google/gemma-4-12B-it": { "displayName": "Gemma 4 12B IT", "description": "Compact Gemma 4 instruction model for open, self-hosted chat and reasoning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-06-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "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": 262144, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "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": 262144, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "inclusionAI/Ling-flash-2.0": { "displayName": "inclusionAI/Ling-flash-2.0", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 131000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "meituan-longcat/LongCat-2.0": { "displayName": "LongCat-2.0", "description": "Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window", "lifecycle": "active", "contextWindow": 1049000, "maxOutputTokens": 131072, "lastUpdated": "2026-06-30", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "MiniMaxAI/MiniMax-M2.5": { "displayName": "MiniMaxAI/MiniMax-M2.5", "description": "MiniMax model for chat, coding, office work, and agentic tasks", "lifecycle": "active", "contextWindow": 197000, "maxOutputTokens": 131000, "structuredOutput": false, "lastUpdated": "2026-06-15", "capabilities": { "vision": false, "reasoning": false, "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": 1048576, "maxOutputTokens": 131000, "lastUpdated": "2026-06-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "moonshotai/Kimi-K2.5": { "displayName": "moonshotai/Kimi-K2.5", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "moonshotai/Kimi-K2.6": { "displayName": "moonshotai/Kimi-K2.6", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2026-06-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "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"], "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": 262000, "structuredOutput": true, "lastUpdated": "2026-07-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "nex-agi/Nex-N2-Pro": { "displayName": "Nex-N2-Pro", "description": "Open agentic MoE model (397B total, 17B active) for coding, tool use, and research workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "structuredOutput": true, "lastUpdated": "2026-06-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "openai/gpt-oss-120b": { "displayName": "openai/gpt-oss-120b", "description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 8000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "openai/gpt-oss-20b": { "displayName": "openai/gpt-oss-20b", "description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 8000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "Qwen/Qwen2.5-72B-Instruct": { "displayName": "Qwen/Qwen2.5-72B-Instruct", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 33000, "maxOutputTokens": 4000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "Qwen/Qwen2.5-7B-Instruct": { "displayName": "Qwen/Qwen2.5-7B-Instruct", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 33000, "maxOutputTokens": 4000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "Qwen/Qwen3-14B": { "displayName": "Qwen/Qwen3-14B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 131000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "Qwen/Qwen3-235B-A22B-Thinking-2507": { "displayName": "Qwen/Qwen3-235B-A22B-Thinking-2507", "description": "Qwen reasoning model for deliberate problem solving, math, and coding", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "Qwen/Qwen3-30B-A3B-Instruct-2507": { "displayName": "Qwen/Qwen3-30B-A3B-Instruct-2507", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "Qwen/Qwen3-32B": { "displayName": "Qwen/Qwen3-32B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 131000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "Qwen/Qwen3-8B": { "displayName": "Qwen/Qwen3-8B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 131000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "Qwen/Qwen3-Coder-30B-A3B-Instruct": { "displayName": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "Qwen/Qwen3-Coder-480B-A35B-Instruct": { "displayName": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "description": "Qwen coding model for software agents, repository edits, and code reasoning", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "Qwen/Qwen3-VL-235B-A22B-Instruct": { "displayName": "Qwen/Qwen3-VL-235B-A22B-Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "Qwen/Qwen3-VL-235B-A22B-Thinking": { "displayName": "Qwen/Qwen3-VL-235B-A22B-Thinking", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "Qwen/Qwen3-VL-30B-A3B-Instruct": { "displayName": "Qwen/Qwen3-VL-30B-A3B-Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "Qwen/Qwen3-VL-30B-A3B-Thinking": { "displayName": "Qwen/Qwen3-VL-30B-A3B-Thinking", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "Qwen/Qwen3-VL-32B-Instruct": { "displayName": "Qwen/Qwen3-VL-32B-Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
@@ -1380,13 +1445,16 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "Qwen/Qwen3.5-9B": { "displayName": "Qwen/Qwen3.5-9B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "Qwen/Qwen3.6-27B": { "displayName": "Qwen3.6 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "Qwen/Qwen3.6-35B-A3B": { "displayName": "Qwen3.6 35B-A3B", "description": "Open multimodal Qwen MoE for local agents that need vision, audio, and code", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-04-17", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "Qwen/Qwen3.8-2.4T-A95B": { "displayName": "Qwen3.8 2.4T A95B", "description": "Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows", "lifecycle": "active", "contextWindow": 1049000, "maxOutputTokens": 131000, "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "stepfun-ai/Step-3.5-Flash": { "displayName": "stepfun-ai/Step-3.5-Flash", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2026-02-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "tencent/Hunyuan-A13B-Instruct": { "displayName": "tencent/Hunyuan-A13B-Instruct", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 131000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "tencent/Hy3-preview": { "displayName": "Hy3 preview", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "lastUpdated": "2026-04-20", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "tencent/Hy3": { "displayName": "Hy3", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 262144, "inputLimit": 192000, "maxOutputTokens": 262144, "lastUpdated": "2026-07-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai-org/GLM-4.5-Air": { "displayName": "zai-org/GLM-4.5-Air", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 131000, "structuredOutput": true, "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai-org/GLM-5": { "displayName": "zai-org/GLM-5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 205000, "maxOutputTokens": 205000, "structuredOutput": true, "lastUpdated": "2026-06-15", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "zai-org/GLM-5.1": { "displayName": "zai-org/GLM-5.1", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 205000, "maxOutputTokens": 205000, "structuredOutput": true, "lastUpdated": "2026-04-08", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "zai-org/GLM-5.1": { "displayName": "zai-org/GLM-5.1", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 205000, "maxOutputTokens": 131000, "structuredOutput": true, "lastUpdated": "2026-04-08", "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": 1049000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "zai-org/GLM-5.3": { "displayName": "GLM-5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1049000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "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": 1049000, "maxOutputTokens": 262000, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "zai-org/GLM-5V-Turbo": { "displayName": "zai-org/GLM-5V-Turbo", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 131072, "lastUpdated": "2026-04-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
     },
     "stepfun": {
@@ -1395,6 +1463,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "step-3.5-flash": { "displayName": "Step 3.5 Flash", "description": "StepFun flash lane for quick multimodal reasoning and coding assistance", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-15", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "step-3.5-flash-2603": { "displayName": "Step 3.5 Flash 2603", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-02", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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": "2026-06-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "step-5-preview": { "displayName": "Step 5 Preview", "description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-09-20", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "step-tts-2": { "displayName": "Step TTS 2", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-07-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
         "stepaudio-2.5-asr": { "displayName": "StepAudio 2.5 ASR", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "lifecycle": "active", "lastUpdated": "2026-07-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["text"] } },
         "stepaudio-2.5-tts": { "displayName": "StepAudio 2.5 TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-07-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
@@ -1405,6 +1474,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "step-3.5-flash": { "displayName": "Step 3.5 Flash", "description": "StepFun flash lane for quick multimodal reasoning and coding assistance", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-06-15", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "step-3.5-flash-2603": { "displayName": "Step 3.5 Flash 2603", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-02", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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": "2026-06-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "step-5-preview": { "displayName": "Step 5 Preview", "description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window", "lifecycle": "active", "contextWindow": 1024000, "inputLimit": 1024000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-09-20", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "step-tts-2": { "displayName": "Step TTS 2", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-07-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
         "stepaudio-2.5-asr": { "displayName": "StepAudio 2.5 ASR", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "lifecycle": "active", "lastUpdated": "2026-07-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["text"] } },
         "stepaudio-2.5-tts": { "displayName": "StepAudio 2.5 TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-07-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
@@ -1413,11 +1483,13 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "step-3.5-flash": { "displayName": "Step 3.5 Flash", "description": "StepFun flash lane for quick multimodal reasoning and coding assistance", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "step-3.5-flash-2603": { "displayName": "Step 3.5 Flash 2603", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-02", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
+        "step-5-preview": { "displayName": "Step 5 Preview", "description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-09-20", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
     },
     "stepfun-step-plan": {
         "step-3.5-flash": { "displayName": "Step 3.5 Flash", "description": "StepFun flash lane for quick multimodal reasoning and coding assistance", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "step-3.5-flash-2603": { "displayName": "Step 3.5 Flash 2603", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-04-02", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
+        "step-5-preview": { "displayName": "Step 5 Preview", "description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-09-20", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "step-router-v1": { "displayName": "Step Router v1", "description": "StepFun routing model that dispatches requests to the appropriate Step model.", "lifecycle": "active", "contextWindow": 256000, "inputLimit": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-29", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
     },
     "togetherai": {
@@ -1425,7 +1497,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "deepseek-ai/DeepSeek-R1": { "displayName": "DeepSeek-R1", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 163839, "maxOutputTokens": 163839, "knowledgeCutoff": "2024-07", "lastUpdated": "2025-03-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V3": { "displayName": "DeepSeek-V3", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V3-1": { "displayName": "DeepSeek V3.1", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "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": ["high", "max"], "toggle": true }, "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": 1048576, "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-ai/DeepSeek-V4-Pro": { "displayName": "DeepSeek V4 Pro", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 512000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V4-Pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek-ai/DeepSeek-V4.1-Flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
@@ -1436,7 +1508,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "meta-llama/Llama-3.3-70B-Instruct-Turbo": { "displayName": "Llama 3.3 70B", "description": "Compact Llama instruction model for fast chat and local deployment", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2023-12", "lastUpdated": "2026-07-02", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "meta-llama/Meta-Llama-3-8B-Instruct-Lite": { "displayName": "Meta Llama 3 8B Instruct Lite", "description": "Compact Llama instruction model for fast chat and local deployment", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 8192, "lastUpdated": "2024-04-18", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "MiniMaxAI/MiniMax-M2.5": { "displayName": "MiniMax-M2.5", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "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": 202752, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "MiniMaxAI/MiniMax-M2.7": { "displayName": "MiniMax-M2.7", "description": "Open MiniMax flagship for coding agents, office automation, and complex environments", "lifecycle": "active", "contextWindow": 196608, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "MiniMaxAI/MiniMax-M3": { "displayName": "MiniMax-M3", "description": "MiniMax multimodal coding model for long-context reasoning and agent tasks", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 250000, "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "moonshotai/Kimi-K2.5": { "displayName": "Kimi K2.5", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "deprecated", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2026-01", "lastUpdated": "2026-01-27", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "moonshotai/Kimi-K2.6": { "displayName": "Kimi K2.6", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 131000, "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"] } },
@@ -1457,7 +1529,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "thinkingmachines/Inkling": { "displayName": "Inkling", "description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio", "lifecycle": "active", "contextWindow": 524288, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["max", "xhigh", "high", "medium", "low", "none"] }, "modalities": { "input": ["text", "image", "audio"], "output": ["text"] } },
         "zai-org/GLM-5": { "displayName": "GLM-5", "description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows", "lifecycle": "deprecated", "contextWindow": 202752, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-02-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": 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": "deprecated", "contextWindow": 202752, "maxOutputTokens": 131072, "knowledgeCutoff": "2025-11", "structuredOutput": true, "lastUpdated": "2026-07-02", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": 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": 512000, "maxOutputTokens": 164000, "structuredOutput": true, "lastUpdated": "2026-06-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": 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": 1048575, "maxOutputTokens": 164000, "structuredOutput": true, "lastUpdated": "2026-06-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "max"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai-org/GLM-5.3": { "displayName": "GLM-5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
     },
@@ -1482,7 +1554,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
     },
     "vercel": {
         "alibaba/qwen-3-14b": { "displayName": "Qwen3-14B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 40960, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "alibaba/qwen-3-235b": { "displayName": "Qwen3 235B A22B Instruct 2507", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "alibaba/qwen-3-235b": { "displayName": "Qwen3 235B A22B Instruct 2507", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "alibaba/qwen-3-30b": { "displayName": "Qwen3-30B-A3B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 40960, "maxOutputTokens": 16384, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "alibaba/qwen-3-32b": { "displayName": "Qwen 3.32B", "description": "Qwen instruction model for multilingual chat, reasoning, and tool use", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8192, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "alibaba/qwen-3.6-max-preview": { "displayName": "Qwen 3.6 Max Preview", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 240000, "maxOutputTokens": 64000, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1497,23 +1569,25 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "alibaba/qwen3-max": { "displayName": "Qwen3 Max", "description": "Flagship Qwen3 model for coding agents, complex reasoning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "alibaba/qwen3-max-preview": { "displayName": "Qwen3 Max Preview", "description": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "alibaba/qwen3-max-thinking": { "displayName": "Qwen 3 Max Thinking", "description": "Qwen reasoning model for deliberate problem solving, math, and coding", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "lastUpdated": "2025-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "alibaba/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": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "alibaba/qwen3-next-80b-a3b-thinking": { "displayName": "Qwen3 Next 80B A3B Thinking", "description": "Efficient Qwen thinking model for local reasoning, math, and coding agents", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "alibaba/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": 262114, "maxOutputTokens": 262114, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "alibaba/qwen3-next-80b-a3b-thinking": { "displayName": "Qwen3 Next 80B A3B Thinking", "description": "Efficient Qwen thinking model for local reasoning, math, and coding agents", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "alibaba/qwen3-vl-235b-a22b-instruct": { "displayName": "Qwen3 VL 235B A22B Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 129024, "knowledgeCutoff": "2025-03-31", "structuredOutput": true, "lastUpdated": "2025-09-23", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "alibaba/qwen3-vl-instruct": { "displayName": "Qwen3 VL Instruct", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 129024, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-09-24", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "alibaba/qwen3-vl-thinking": { "displayName": "Qwen3 VL Thinking", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-09", "lastUpdated": "2025-09-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "alibaba/qwen3.5-flash": { "displayName": "Qwen 3.5 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "alibaba/qwen3.5-plus": { "displayName": "Qwen 3.5 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "alibaba/qwen3.5-flash": { "displayName": "Qwen 3.5 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-02-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "alibaba/qwen3.5-plus": { "displayName": "Qwen 3.5 Plus", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-02-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "alibaba/qwen3.6-27b": { "displayName": "Qwen 3.6 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "structuredOutput": true, "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "alibaba/qwen3.6-plus": { "displayName": "Qwen 3.6 Plus", "description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "alibaba/qwen3.7-flash": { "displayName": "Qwen 3.7 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 991000, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "alibaba/qwen3.7-max": { "displayName": "Qwen 3.7 Max", "description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks", "lifecycle": "active", "contextWindow": 991000, "maxOutputTokens": 64000, "lastUpdated": "2026-05-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "alibaba/qwen3.7-plus": { "displayName": "Qwen 3.7 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", "pdf"], "output": ["text"] } },
+        "alibaba/qwen3.6-plus": { "displayName": "Qwen 3.6 Plus", "description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "alibaba/qwen3.7-flash": { "displayName": "Qwen 3.7 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 991000, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-07-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "alibaba/qwen3.7-max": { "displayName": "Qwen 3.7 Max", "description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks", "lifecycle": "active", "contextWindow": 991000, "maxOutputTokens": 64000, "lastUpdated": "2026-05-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "alibaba/qwen3.7-plus": { "displayName": "Qwen 3.7 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": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "alibaba/qwen3.8-2.4t-a95b": { "displayName": "Qwen3.8 2.4T A95B", "description": "Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "alibaba/qwen3.8-27b": { "displayName": "Qwen3.8 27B", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "alibaba/qwen3.8-flash": { "displayName": "Qwen 3.8 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 991000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "alibaba/qwen3.8-max": { "displayName": "Qwen 3.8 Max", "description": "Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "lastUpdated": "2026-07-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "alibaba/qwen3.8-flash": { "displayName": "Qwen 3.8 Flash", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 991000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "alibaba/qwen3.8-max": { "displayName": "Qwen 3.8 Max", "description": "Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 128000, "lastUpdated": "2026-07-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "alibaba/qwen3.8-max-0902": { "displayName": "Qwen3.8 Max 0902", "description": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "lifecycle": "active", "contextWindow": 991000, "maxOutputTokens": 128000, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "alibaba/qwen3.8-max-prime": { "displayName": "Qwen 3.8 Max Prime", "description": "High-throughput edition of Qwen3.8 Max for coding, professional work, multimodal understanding, and long-running agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "alibaba/qwen3.8-omni-flash": { "displayName": "Qwen 3.8 Omni Flash", "description": "Qwen omni model for text, vision, audio, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "lastUpdated": "2026-09-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "alibaba/wan-v2.5-t2v-preview": { "displayName": "Wan v2.5 Text-to-Video Preview", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "lastUpdated": "2025-09-24", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
         "alibaba/wan-v2.6-i2v": { "displayName": "Wan v2.6 Image-to-Video", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2025-12-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
         "alibaba/wan-v2.6-i2v-flash": { "displayName": "Wan v2.6 Image-to-Video Flash", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2025-12-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
@@ -1530,22 +1604,24 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "amazon/nova-pro": { "displayName": "Nova Pro", "description": "Flagship model for demanding analysis, coding, and production agent workflows", "lifecycle": "active", "contextWindow": 300000, "maxOutputTokens": 10000, "knowledgeCutoff": "2024-10", "lastUpdated": "2024-12-03", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
         "amazon/titan-embed-text-v2": { "displayName": "Titan Text Embeddings V2", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1536, "lastUpdated": "2024-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "anthropic/claude-3-haiku": { "displayName": "Claude Haiku 3", "description": "Legacy model retained for compatibility with older integrations", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 4096, "knowledgeCutoff": "2023-08-31", "lastUpdated": "2024-03-13", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "anthropic/claude-fable-5": { "displayName": "Claude Fable 5", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-fable-5.1": { "displayName": "Claude Fable 5.1", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-fable-5": { "displayName": "Claude Fable 5", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-06-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-fable-5.1": { "displayName": "Claude Fable 5.1", "description": "Claude model for creative writing, analysis, and controlled agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "anthropic/claude-haiku-4.5": { "displayName": "Claude Haiku 4.5", "description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-02-28", "lastUpdated": "2025-10-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-opus-4": { "displayName": "Claude Opus 4", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 8192, "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-opus-4.5": { "displayName": "Claude Opus 4.5", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-05", "lastUpdated": "2025-11-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-opus-4.6": { "displayName": "Claude Opus 4.6", "description": "High-end Claude for difficult coding, planning, and slower expert reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-opus-4.7": { "displayName": "Claude Opus 4.7", "description": "Stronger Opus tier for advanced software work and high-stakes reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-opus-4.8": { "displayName": "Claude Opus 4.8", "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-opus-4.8-fast": { "displayName": "Claude Opus 4.8 (Fast)", "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-opus-5": { "displayName": "Claude Opus 5", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05", "lastUpdated": "2026-07-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-opus-5-fast": { "displayName": "Claude Opus 5 (Fast)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05", "lastUpdated": "2026-07-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-sonnet-4": { "displayName": "Claude Sonnet 4", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 8192, "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-opus-4": { "displayName": "Claude Opus 4", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 32000, "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-opus-4.5": { "displayName": "Claude Opus 4.5", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-05", "lastUpdated": "2025-11-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-opus-4.6": { "displayName": "Claude Opus 4.6", "description": "High-end Claude for difficult coding, planning, and slower expert reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-05-31", "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-opus-4.7": { "displayName": "Claude Opus 4.7", "description": "Stronger Opus tier for advanced software work and high-stakes reasoning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01-31", "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-opus-4.8": { "displayName": "Claude Opus 4.8", "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-opus-4.8-fast": { "displayName": "Claude Opus 4.8 (Fast)", "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-opus-5": { "displayName": "Claude Opus 5", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05", "lastUpdated": "2026-07-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-opus-5-fast": { "displayName": "Claude Opus 5 (Fast)", "description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05", "lastUpdated": "2026-07-24", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-opus-5.5": { "displayName": "Claude Opus 5.5", "description": "Claude model for long-running agentic coding and knowledge work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-opus-5.5-fast": { "displayName": "Claude Opus 5.5 (Fast)", "description": "Claude model for long-running agentic coding and knowledge work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-06", "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "anthropic/claude-sonnet-4": { "displayName": "Claude Sonnet 4", "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-03-31", "lastUpdated": "2025-05-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "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": "2025-07-31", "structuredOutput": true, "lastUpdated": "2025-09-29", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "anthropic/claude-sonnet-4.6": { "displayName": "Claude Sonnet 4.6", "description": "Claude workhorse for coding agents, careful analysis, and production cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "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", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "arcee-ai/trinity-large-thinking": { "displayName": "Trinity Large Thinking", "description": "Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use", "lifecycle": "active", "contextWindow": 262100, "maxOutputTokens": 80000, "lastUpdated": "2026-04-03", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "anthropic/claude-sonnet-4.6": { "displayName": "Claude Sonnet 4.6", "description": "Claude workhorse for coding agents, careful analysis, and production cost control", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "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": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "arcee-ai/trinity-large-thinking": { "displayName": "Trinity Large Thinking", "description": "Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use", "lifecycle": "active", "contextWindow": 262100, "maxOutputTokens": 80000, "lastUpdated": "2026-05-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "bfl/flux-2-flex": { "displayName": "FLUX.2 [flex]", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-06-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "bfl/flux-2-klein-4b": { "displayName": "FLUX.2 [klein] 4B", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-06-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "bfl/flux-2-klein-9b": { "displayName": "FLUX.2 [klein] 9B", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-06-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
@@ -1559,7 +1635,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "bfl/flux-pro-1.1-ultra": { "displayName": "FLUX1.1 [pro] Ultra", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 512, "lastUpdated": "2024-11", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "bytedance/seed-1.6": { "displayName": "Seed 1.6", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "bytedance/seed-1.8": { "displayName": "Seed 1.8", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "bytedance/seed-2.1-turbo": { "displayName": "Seed 2.1 Turbo", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "lastUpdated": "2026-06-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "bytedance/seed-2.1-turbo": { "displayName": "Seed 2.1 Turbo", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 262144, "lastUpdated": "2026-06-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "bytedance/seedance-2.0": { "displayName": "Seedance 2.0", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "lastUpdated": "2026-04-14", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
         "bytedance/seedance-2.0-fast": { "displayName": "Seedance 2.0 Fast", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "lastUpdated": "2026-04-14", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
         "bytedance/seedance-2.0-mini": { "displayName": "Seedance 2.0 Mini", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "lastUpdated": "2026-06-22", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
@@ -1577,45 +1653,45 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "cohere/rerank-v4-fast": { "displayName": "Cohere Rerank 4 Fast", "description": "Reranking model for improving retrieval quality in search and recommendation systems", "lifecycle": "active", "contextWindow": 32000, "maxOutputTokens": 32000, "lastUpdated": "2025-12-11", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "cohere/rerank-v4-pro": { "displayName": "Cohere Rerank 4 Pro", "description": "Reranking model for improving retrieval quality in search and recommendation systems", "lifecycle": "active", "contextWindow": 32000, "maxOutputTokens": 32000, "lastUpdated": "2025-12-11", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "deepseek/deepseek-r1": { "displayName": "DeepSeek-R1", "description": "Classic open reasoning model for transparent math, coding, and deliberate problem solving", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 32768, "knowledgeCutoff": "2024-07", "lastUpdated": "2025-05-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek/deepseek-v3.1": { "displayName": "DeepSeek-V3.1", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 128000, "lastUpdated": "2025-08-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek/deepseek-v3.1-terminus": { "displayName": "DeepSeek V3.1 Terminus", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-07", "lastUpdated": "2025-09-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "deepseek/deepseek-v3.1": { "displayName": "DeepSeek-V3.1", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 163840, "maxOutputTokens": 128000, "lastUpdated": "2025-08-21", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "deepseek/deepseek-v3.1-terminus": { "displayName": "DeepSeek V3.1 Terminus", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-07", "lastUpdated": "2025-09-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "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": 8000, "knowledgeCutoff": "2024-07", "structuredOutput": true, "lastUpdated": "2025-12-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek/deepseek-v3.2-thinking": { "displayName": "DeepSeek V3.2 Thinking", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8000, "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek/deepseek-v4-flash": { "displayName": "DeepSeek V4 Flash", "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek/deepseek-v4-flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek/deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "deepseek/deepseek-v4-pro": { "displayName": "DeepSeek V4 Pro", "description": "Open MoE flagship with million-token context for coding and long agent runs", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek/deepseek-v4-pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "deepseek/deepseek-v4.1-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "deepseek/deepseek-v3.2-thinking": { "displayName": "DeepSeek V3.2 Thinking", "description": "DeepSeek chat model for instruction following, coding, and analysis", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 8000, "knowledgeCutoff": "2024-07", "lastUpdated": "2025-12-01", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "deepseek/deepseek-v4-flash": { "displayName": "DeepSeek V4 Flash", "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "deepseek/deepseek-v4-flash-0731": { "displayName": "DeepSeek V4 Flash 0731", "description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "deepseek/deepseek-v4-flash-vision-exp": { "displayName": "DeepSeek V4 Flash Vision Exp", "description": "Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-09-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "deepseek/deepseek-v4-pro": { "displayName": "DeepSeek V4 Pro", "description": "Open MoE flagship with million-token context for coding and long agent runs", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-04-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "deepseek/deepseek-v4-pro-0813": { "displayName": "DeepSeek V4 Pro 0813", "description": "Flagship DeepSeek model for coding, reasoning, and agentic work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 384000, "structuredOutput": true, "lastUpdated": "2026-08-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "deepseek/deepseek-v4.1-flash": { "displayName": "DeepSeek V4.1 Flash", "description": "DeepSeek V4.1 Flash model for reasoning and agentic coding", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-05", "structuredOutput": true, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "fish-audio/s1": { "displayName": "S1", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2025-10-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "fish-audio/s1-free": { "displayName": "S1 (Free)", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2025-10-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
         "fish-audio/s2-pro": { "displayName": "S2 Pro", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-03-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "fish-audio/s2-pro-free": { "displayName": "S2 Pro (Free)", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-03-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
         "fish-audio/s2.1-pro": { "displayName": "S2.1 Pro", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-07-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
-        "fish-audio/s2.1-pro-free": { "displayName": "S2.1 Pro (Free)", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-07-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
         "fish-audio/transcribe-1": { "displayName": "Transcribe-1", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "lifecycle": "active", "lastUpdated": "2026-03-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["text"] } },
-        "fish-audio/transcribe-1-free": { "displayName": "Transcribe-1 (Free)", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "lifecycle": "active", "lastUpdated": "2026-03-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "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": 65536, "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 (Gemini 2.5 Flash Image)", "description": "Nano Banana image model for fast generation, edits, and character-consistent assets", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "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": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-06-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "google/gemini-2.5-flash-image": { "displayName": "Nano Banana (Gemini 2.5 Flash Image)", "description": "Nano Banana image model for fast generation, edits, and character-consistent assets", "lifecycle": "active", "contextWindow": 32768, "maxOutputTokens": 65535, "knowledgeCutoff": "2024-06", "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": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "google/gemini-2.5-pro": { "displayName": "Gemini 2.5 Pro", "description": "Google's proven reasoning model for coding, math, and multimodal analysis", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 65536, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2025-06-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "audio", "video", "pdf"], "output": ["text"] } },
-        "google/gemini-3-flash": { "displayName": "Gemini 3 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65000, "knowledgeCutoff": "2025-03", "lastUpdated": "2025-12-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "google/gemini-3-flash": { "displayName": "Gemini 3 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65000, "knowledgeCutoff": "2025-03", "lastUpdated": "2025-12-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "google/gemini-3-pro-image": { "displayName": "Nano Banana Pro", "description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
-        "google/gemini-3.1-flash-image": { "displayName": "Nano Banana 2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["minimal", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
-        "google/gemini-3.1-flash-image-preview": { "displayName": "Gemini 3.1 Flash Image Preview (Nano Banana 2)", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["minimal", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
-        "google/gemini-3.1-flash-lite": { "displayName": "Gemini 3.1 Flash Lite", "description": "Low-latency Gemini model for high-volume multimodal and agent workloads", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-05-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "google/gemini-3.1-flash-lite-image": { "displayName": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 4096, "knowledgeCutoff": "2025-01", "structuredOutput": false, "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
-        "google/gemini-3.1-pro-preview": { "displayName": "Gemini 3.1 Pro Preview", "description": "Reasoning-first Gemini preview for agentic coding and complex problem solving", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-02-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "google/gemini-3.5-flash": { "displayName": "Gemini 3.5 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-05-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "google/gemini-3.5-flash-lite": { "displayName": "Gemini 3.5 Flash Lite", "description": "Low-latency Gemini model for high-volume multimodal and agent workloads", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65000, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-07-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "google/gemini-3.1-flash-image": { "displayName": "Nano Banana 2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
+        "google/gemini-3.1-flash-image-preview": { "displayName": "Gemini 3.1 Flash Image Preview (Nano Banana 2)", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
+        "google/gemini-3.1-flash-lite": { "displayName": "Gemini 3.1 Flash Lite", "description": "Low-latency Gemini model for high-volume multimodal and agent workloads", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-05-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "google/gemini-3.1-flash-lite-image": { "displayName": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 65536, "maxOutputTokens": 4096, "knowledgeCutoff": "2025-01", "structuredOutput": false, "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
+        "google/gemini-3.1-pro-preview": { "displayName": "Gemini 3.1 Pro Preview", "description": "Reasoning-first Gemini preview for agentic coding and complex problem solving", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-02-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "google/gemini-3.5-flash": { "displayName": "Gemini 3.5 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-05-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "google/gemini-3.5-flash-lite": { "displayName": "Gemini 3.5 Flash Lite", "description": "Low-latency Gemini model for high-volume multimodal and agent workloads", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65000, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-07-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "google/gemini-3.5-transcribe": { "displayName": "Gemini 3.5 Transcribe", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "lifecycle": "active", "lastUpdated": "2026-08-26", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["text"] } },
         "google/gemini-3.5-transcribe-live": { "displayName": "Gemini 3.5 Transcribe Live", "description": "Speech transcription model for accurate audio-to-text and captioning workflows", "lifecycle": "active", "lastUpdated": "2026-08-26", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["text"] } },
-        "google/gemini-3.6-flash": { "displayName": "Gemini 3.6 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-07-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "google/gemini-3.7-flash": { "displayName": "Gemini 3.7 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-08-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "google/gemini-3.8-flash": { "displayName": "Gemini 3.8 Flash", "description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65536, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "google/gemini-3.6-flash": { "displayName": "Gemini 3.6 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-07-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "google/gemini-3.7-flash": { "displayName": "Gemini 3.7 Flash", "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65535, "knowledgeCutoff": "2026-03", "structuredOutput": true, "lastUpdated": "2026-08-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "google/gemini-3.8-flash": { "displayName": "Gemini 3.8 Flash", "description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65535, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "google/gemini-3.8-flash-lite-tts": { "displayName": "Gemini 3.8 Flash-Lite TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "google/gemini-3.8-flash-tts": { "displayName": "Gemini 3.8 Flash TTS", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
+        "google/gemini-3.8-live": { "displayName": "Gemini 3.8 Live", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-09-15", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
+        "google/gemini-3.8-live-extended-thinking": { "displayName": "Gemini 3.8 Live Extended Thinking", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-09-15", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
         "google/gemini-embedding-001": { "displayName": "Gemini Embedding 001", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1536, "knowledgeCutoff": "2025-05", "lastUpdated": "2025-05-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "google/gemini-embedding-2": { "displayName": "Gemini Embedding 2", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "knowledgeCutoff": "2025-11", "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "google/gemini-omni-flash-preview": { "displayName": "Gemini Omni Flash Preview", "description": "Omni-modal model for text, vision, audio, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 57920, "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "google/gemini-omni-flash-preview": { "displayName": "Gemini Omni Flash Preview", "description": "Omni-modal model for text, vision, audio, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 57920, "lastUpdated": "2026-06-30", "capabilities": { "vision": true, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "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": 131072, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "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": 131072, "structuredOutput": true, "lastUpdated": "2026-04-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "google/text-embedding-005": { "displayName": "Text Embedding 005", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1536, "lastUpdated": "2024-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1628,13 +1704,14 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "inception/mercury-2": { "displayName": "Mercury 2", "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "lastUpdated": "2026-03-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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": { "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 }, "thinkingOptions": { "toggle": 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", "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-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 }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "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 }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "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"] } },
+        "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, "lastUpdated": "2026-04-16", "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, "lastUpdated": "2026-04-16", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "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"] } },
@@ -1644,59 +1721,52 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "klingai/kling-v3.0-i2v": { "displayName": "Kling v3.0 Image-to-Video", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-02-05", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
         "klingai/kling-v3.0-motion-control": { "displayName": "Kling v3.0 Motion Control", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "lastUpdated": "2026-03-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
         "klingai/kling-v3.0-t2v": { "displayName": "Kling v3.0 Text-to-Video", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "lastUpdated": "2026-02-05", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
-        "kwaipilot/kat-coder-air-v2.5": { "displayName": "Kat Coder Air 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"] } },
-        "kwaipilot/kat-coder-pro-v1": { "displayName": "KAT-Coder-Pro V1", "description": "Coding model for repository understanding, refactors, and agentic engineering tasks", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10-24", "capabilities": { "vision": false, "reasoning": true, "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": 256000, "maxOutputTokens": 256000, "lastUpdated": "2026-03-30", "capabilities": { "vision": false, "reasoning": true, "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": 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", "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-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", "low", "medium", "high"] }, "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"] } },
-        "meta/muse-spark-1.2": { "displayName": "Muse Spark 1.2", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "meta/muse-spark-1.2": { "displayName": "Muse Spark 1.2", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "meta/muse-spark-1.2-contributor": { "displayName": "Muse Spark 1.2 Contributor", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "lastUpdated": "2026-08-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "meta/muse-spark-1.3": { "displayName": "Muse Spark 1.3", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "meta/muse-spark-1.3": { "displayName": "Muse Spark 1.3", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "structuredOutput": true, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "meta/muse-spark-1.3-contributor": { "displayName": "Muse Spark 1.3 Contributor", "description": "Open Llama multimodal model for image understanding and text reasoning", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 1048576, "lastUpdated": "2026-09-02", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "minimax/minimax-h3": { "displayName": "MiniMax H3", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "lastUpdated": "2026-07-30", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
         "minimax/minimax-h3-max": { "displayName": "MiniMax H3 Max", "description": "Video model for prompt-guided generation, editing, and motion workflows", "lifecycle": "active", "lastUpdated": "2026-08-27", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["video"] } },
-        "minimax/minimax-m2": { "displayName": "MiniMax M2", "description": "Efficient open MiniMax model built for coding agents and tool-heavy workflows", "lifecycle": "active", "contextWindow": 205000, "maxOutputTokens": 205000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10-27", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "minimax/minimax-m2": { "displayName": "MiniMax M2", "description": "Efficient open MiniMax model built for coding agents and tool-heavy workflows", "lifecycle": "active", "contextWindow": 205000, "maxOutputTokens": 205000, "lastUpdated": "2025-10-27", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-m2.1": { "displayName": "MiniMax M2.1", "description": "Earlier MiniMax agent model for practical coding and productivity tasks", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "lastUpdated": "2025-12-23", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-m2.1-lightning": { "displayName": "MiniMax M2.1 Lightning", "description": "High-speed MiniMax model for low-latency coding and agent workflows", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-10-27", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-m2.5": { "displayName": "MiniMax M2.5", "description": "Prior MiniMax coding model for agent workflows, office edits, and automation", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131000, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-m2.5-highspeed": { "displayName": "MiniMax M2.5 High Speed", "description": "High-speed MiniMax model for low-latency coding and agent workflows", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131000, "lastUpdated": "2026-02-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-m2.7": { "displayName": "Minimax M2.7", "description": "Open MiniMax flagship for coding agents, office automation, and complex environments", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131000, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "minimax/minimax-m2.7-highspeed": { "displayName": "MiniMax M2.7 High Speed", "description": "Low-latency M2.7 variant for interactive coding plans and agent loops", "lifecycle": "active", "contextWindow": 204800, "maxOutputTokens": 131100, "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "minimax/minimax-m3": { "displayName": "MiniMax M3", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 512000, "maxOutputTokens": 512000, "lastUpdated": "2026-06-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "minimax/minimax-m3": { "displayName": "MiniMax M3", "description": "MiniMax multimodal model for long-context coding, perception, and agent planning", "lifecycle": "active", "contextWindow": 512000, "maxOutputTokens": 512000, "lastUpdated": "2026-06-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "mistral/codestral": { "displayName": "Codestral (latest)", "description": "Mistral code model for completions, refactors, and developer IDE workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 4096, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-01-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "mistral/codestral-embed": { "displayName": "Codestral Embed", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1536, "lastUpdated": "2025-05-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mistral/devstral-2": { "displayName": "Devstral 2", "description": "Mistral coding agent model for repository tasks and software engineering workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-09", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mistral/devstral-small-2": { "displayName": "Devstral Small 2", "description": "Mistral coding agent model for repository tasks and software engineering workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-05-07", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistral/ministral-14b": { "displayName": "Ministral 14B", "description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-01", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "mistral/ministral-14b": { "displayName": "Ministral 14B", "description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-01", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "mistral/ministral-3b": { "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"] } },
         "mistral/ministral-8b": { "displayName": "Ministral 8B (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"] } },
         "mistral/mistral-embed": { "displayName": "Mistral Embed", "description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1536, "lastUpdated": "2023-12-11", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "mistral/mistral-large-3": { "displayName": "Mistral Large 3", "description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistral/mistral-medium": { "displayName": "Mistral Medium 3.1", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 64000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-05-07", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistral/mistral-medium-3.5": { "displayName": "Mistral Medium Latest", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "lastUpdated": "2026-05-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistral/mistral-nemo": { "displayName": "Mistral Nemo", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-04", "lastUpdated": "2024-07-01", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistral/mistral-small": { "displayName": "Mistral Small (latest)", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 32000, "maxOutputTokens": 4000, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-03-16", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "mistral/pixtral-12b": { "displayName": "Pixtral 12B", "description": "Mistral vision-language model for image understanding and multimodal chat", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-09", "lastUpdated": "2024-09-01", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "mistral/mistral-large-3": { "displayName": "Mistral Large 3", "description": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-12-02", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "mistral/mistral-medium-3.5": { "displayName": "Mistral Medium Latest", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 256000, "lastUpdated": "2026-05-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "mistral/mistral-nemo": { "displayName": "Mistral Nemo", "description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "lifecycle": "active", "contextWindow": 60288, "maxOutputTokens": 16000, "knowledgeCutoff": "2024-04", "lastUpdated": "2024-07-01", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "mistral/mistral-small": { "displayName": "Mistral Small (latest)", "description": "Efficient Mistral model for fast chat, extraction, and production assistants", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 4000, "knowledgeCutoff": "2025-06", "lastUpdated": "2026-03-16", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "mixedbread/toast-1": { "displayName": "Toast 1", "description": "Specialized search model for knowledge-intensive questions, multi-step retrieval, and evidence synthesis", "lifecycle": "active", "contextWindow": 131000, "maxOutputTokens": 4000, "lastUpdated": "2026-08-13", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "moonshotai/kimi-k2": { "displayName": "Kimi K2 Instruct", "description": "Kimi model for long-context chat, coding, and agentic reasoning", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "lastUpdated": "2025-09-05", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "moonshotai/kimi-k2-thinking": { "displayName": "Kimi K2 Thinking", "description": "Thinking Kimi model for slower research passes, planning, and hard technical questions", "lifecycle": "active", "contextWindow": 216144, "maxOutputTokens": 216144, "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "moonshotai/kimi-k2.5": { "displayName": "Kimi K2.5", "description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work", "lifecycle": "active", "contextWindow": 262114, "maxOutputTokens": 262114, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "moonshotai/kimi-k2-thinking": { "displayName": "Kimi K2 Thinking", "description": "Thinking Kimi model for slower research passes, planning, and hard technical questions", "lifecycle": "active", "contextWindow": 216144, "maxOutputTokens": 216144, "knowledgeCutoff": "2024-08", "lastUpdated": "2025-11-06", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "moonshotai/kimi-k2.5": { "displayName": "Kimi K2.5", "description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "moonshotai/kimi-k2.6": { "displayName": "Kimi K2.6", "description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context", "lifecycle": "active", "contextWindow": 262000, "maxOutputTokens": 262000, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-04-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "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": 256000, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "moonshotai/kimi-k2.7-code-highspeed": { "displayName": "Kimi K2.7 Code High Speed", "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", "pdf"], "output": ["text"] } },
-        "moonshotai/kimi-k3": { "displayName": "Kimi K3", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "moonshotai/kimi-k3-fast": { "displayName": "Kimi K3 Fast", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "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": 256000, "maxOutputTokens": 32768, "knowledgeCutoff": "2025-01", "structuredOutput": true, "lastUpdated": "2026-06-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "moonshotai/kimi-k2.7-code-highspeed": { "displayName": "Kimi K2.7 Code High Speed", "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 }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "moonshotai/kimi-k3": { "displayName": "Kimi K3", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "high", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "moonshotai/kimi-k3-fast": { "displayName": "Kimi K3 Fast", "description": "Kimi multimodal agent model for visual understanding, coding, and planning", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-07-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "morph/morph-v3-fast": { "displayName": "Morph v3 Fast", "description": "Efficient model for low-latency assistance, extraction, and routine automation", "lifecycle": "active", "contextWindow": 16000, "maxOutputTokens": 16000, "lastUpdated": "2024-08-15", "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": 32000, "maxOutputTokens": 32000, "lastUpdated": "2024-08-15", "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": 262144, "maxOutputTokens": 262144, "lastUpdated": "2025-12-15", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/nemotron-3-super-120b-a12b": { "displayName": "NVIDIA Nemotron 3 Super 120B A12B", "description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "lastUpdated": "2026-03-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "nvidia/nemotron-3-ultra-550b-a55b": { "displayName": "Nemotron 3 Ultra", "description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65000, "lastUpdated": "2026-06-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/nemotron-3-super-120b-a12b": { "displayName": "NVIDIA Nemotron 3 Super 120B A12B", "description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 32000, "lastUpdated": "2026-03-11", "capabilities": { "vision": false, "reasoning": true, "functionCalling": false }, "thinkingOptions": { "efforts": ["none", "low", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "nvidia/nemotron-3-ultra-550b-a55b": { "displayName": "Nemotron 3 Ultra", "description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 65000, "lastUpdated": "2026-06-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "nvidia/nemotron-3.5-lightning": { "displayName": "Nemotron 3.5 Lightning 30B", "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-nano-12b-v2-vl": { "displayName": "Nvidia Nemotron Nano 12B V2 VL", "description": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "lastUpdated": "2025-10-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "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, "lastUpdated": "2025-08-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1721,42 +1791,47 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "openai/gpt-5-mini-fast": { "displayName": "GPT-5 mini (Fast)", "description": "Small GPT-5 for responsive agents, coding help, and everyday automation", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-05-30", "structuredOutput": true, "lastUpdated": "2025-08-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/gpt-5-nano": { "displayName": "GPT-5 Nano", "description": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-05-30", "structuredOutput": true, "lastUpdated": "2025-08-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "openai/gpt-5-pro": { "displayName": "GPT-5 pro", "description": "Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 128000, "maxOutputTokens": 272000, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-10-06", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.1-codex": { "displayName": "GPT-5.1-Codex", "description": "Codex GPT for repository edits, code review, and practical software agents", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-11-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.1-codex-max": { "displayName": "GPT 5.1 Codex Max", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-11-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.1-codex-mini": { "displayName": "GPT-5.1 Codex mini", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-11-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.1-thinking": { "displayName": "GPT 5.1 Thinking", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-08-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text", "image"] } },
-        "openai/gpt-5.1-thinking-fast": { "displayName": "GPT 5.1 Thinking (Fast)", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "lastUpdated": "2025-11-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.2": { "displayName": "GPT-5.2", "description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-10", "structuredOutput": true, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.2-codex": { "displayName": "GPT-5.2-Codex", "description": "Code-specialist GPT for repository edits, reviews, and long-running software agents", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.2-fast": { "displayName": "GPT 5.2 (Fast)", "description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.1-codex": { "displayName": "GPT-5.1-Codex", "description": "Codex GPT for repository edits, code review, and practical software agents", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-11-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.1-codex-max": { "displayName": "GPT 5.1 Codex Max", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-11-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.1-codex-mini": { "displayName": "GPT-5.1 Codex mini", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-09-30", "structuredOutput": true, "lastUpdated": "2025-11-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.1-thinking": { "displayName": "GPT 5.1 Thinking", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2024-10", "lastUpdated": "2025-08-07", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.1-thinking-fast": { "displayName": "GPT 5.1 Thinking (Fast)", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "lastUpdated": "2025-11-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.2": { "displayName": "GPT-5.2", "description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.2-codex": { "displayName": "GPT-5.2-Codex", "description": "Code-specialist GPT for repository edits, reviews, and long-running software agents", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.2-fast": { "displayName": "GPT 5.2 (Fast)", "description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/gpt-5.2-pro": { "displayName": "GPT 5.2 ", "description": "Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": false, "lastUpdated": "2025-12-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.3-codex": { "displayName": "GPT 5.3 Codex", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-02-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.3-codex-fast": { "displayName": "GPT 5.3 Codex (Fast)", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-02-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.4": { "displayName": "GPT 5.4", "description": "Agent-ready GPT for coding and computer-use workflows at a lower cost", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.4-fast": { "displayName": "GPT 5.4 (Fast)", "description": "Agent-ready GPT for coding and computer-use workflows at a lower cost", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.4-mini": { "displayName": "GPT 5.4 Mini", "description": "Strong small GPT for coding subagents, quick tool use, and high-volume work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.4-mini-fast": { "displayName": "GPT 5.4 Mini (Fast)", "description": "Strong small GPT for coding subagents, quick tool use, and high-volume work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.4-nano": { "displayName": "GPT 5.4 Nano", "description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.4-pro": { "displayName": "GPT 5.4 Pro", "description": "More exact GPT-5.4 tier for demanding professional reasoning and agent tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": false, "lastUpdated": "2026-03-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.5": { "displayName": "GPT 5.5", "description": "Default frontier GPT for coding, computer use, research, and knowledge work", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 872000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12-01", "structuredOutput": true, "lastUpdated": "2026-04-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.5-fast": { "displayName": "GPT 5.5 (Fast)", "description": "Default frontier GPT for coding, computer use, research, and knowledge work", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 872000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12-01", "structuredOutput": true, "lastUpdated": "2026-04-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.3-codex": { "displayName": "GPT 5.3 Codex", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-02-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.3-codex-fast": { "displayName": "GPT 5.3 Codex (Fast)", "description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-02-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.4": { "displayName": "GPT 5.4", "description": "Agent-ready GPT for coding and computer-use workflows at a lower cost", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.4-fast": { "displayName": "GPT 5.4 (Fast)", "description": "Agent-ready GPT for coding and computer-use workflows at a lower cost", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.4-mini": { "displayName": "GPT 5.4 Mini", "description": "Strong small GPT for coding subagents, quick tool use, and high-volume work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.4-mini-fast": { "displayName": "GPT 5.4 Mini (Fast)", "description": "Strong small GPT for coding subagents, quick tool use, and high-volume work", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.4-nano": { "displayName": "GPT 5.4 Nano", "description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": true, "lastUpdated": "2026-03-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.4-pro": { "displayName": "GPT 5.4 Pro", "description": "More exact GPT-5.4 tier for demanding professional reasoning and agent tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "structuredOutput": false, "lastUpdated": "2026-03-05", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.5": { "displayName": "GPT 5.5", "description": "Default frontier GPT for coding, computer use, research, and knowledge work", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 872000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12-01", "structuredOutput": true, "lastUpdated": "2026-04-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.5-fast": { "displayName": "GPT 5.5 (Fast)", "description": "Default frontier GPT for coding, computer use, research, and knowledge work", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 872000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12-01", "structuredOutput": true, "lastUpdated": "2026-04-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/gpt-5.5-pro": { "displayName": "GPT 5.5 Pro", "description": "Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 872000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12-01", "structuredOutput": true, "lastUpdated": "2026-04-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/gpt-5.6-luna": { "displayName": "GPT 5.6 Luna", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/gpt-5.6-luna-fast": { "displayName": "GPT 5.6 Luna (Fast)", "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.6-sol": { "displayName": "GPT 5.6 Sol", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.6-sol-fast": { "displayName": "GPT 5.6 Sol (Fast)", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.6-terra": { "displayName": "GPT 5.6 Terra", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.6-terra-fast": { "displayName": "GPT 5.6 Terra (Fast)", "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-6-astra": { "displayName": "GPT-6 Astra", "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-30", "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-6-astra-fast": { "displayName": "GPT-6 Astra (Fast)", "description": "Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.6-sol": { "displayName": "GPT 5.6 Sol", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.6-sol-fast": { "displayName": "GPT 5.6 Sol (Fast)", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.6-terra": { "displayName": "GPT 5.6 Terra", "description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.6-terra-fast": { "displayName": "GPT 5.6 Terra (Fast)", "description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-6-astra": { "displayName": "GPT-6 Astra", "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-30", "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-6-astra-fast": { "displayName": "GPT-6 Astra (Fast)", "description": "Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-09-04", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-6-luna": { "displayName": "GPT-6 Luna", "description": "OpenAI's most efficient model for focused, high-volume tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05-18", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-6-luna-fast": { "displayName": "GPT-6 Luna (Fast)", "description": "OpenAI's most efficient model for focused, high-volume tasks", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-05-18", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-6-sol": { "displayName": "GPT-6 Sol", "description": "OpenAI model for complex coding and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-20", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-6-sol-fast": { "displayName": "GPT-6 Sol (Fast)", "description": "OpenAI model for complex coding and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-04-20", "structuredOutput": true, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/gpt-image-1": { "displayName": "GPT Image 1", "description": "OpenAI image model for production generation, edits, and brand-safe visual workflows", "lifecycle": "active", "lastUpdated": "2025-04-24", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "openai/gpt-image-1-mini": { "displayName": "GPT Image 1 Mini", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2025-10-06", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "openai/gpt-image-1.5": { "displayName": "GPT Image 1.5", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2025-11-25", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "openai/gpt-image-2": { "displayName": "GPT Image 2", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-04-21", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "openai/gpt-image-2.5-flare": { "displayName": "GPT Image 2.5 Flare", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-09-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "openai/gpt-image-2.5-sunburst": { "displayName": "GPT Image 2.5 Sunburst", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-09-08", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
-        "openai/gpt-oss-120b": { "displayName": "GPT OSS 120B", "description": "Open GPT reasoning model for self-hosted agents and controllable deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "knowledgeCutoff": "2024-10", "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "openai/gpt-oss-20b": { "displayName": "GPT OSS 20B", "description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads", "lifecycle": "active", "contextWindow": 131072, "inputLimit": 122880, "maxOutputTokens": 8192, "knowledgeCutoff": "2024-10", "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "openai/gpt-live-1": { "displayName": "GPT-Live 1", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-09-10", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
+        "openai/gpt-oss-120b": { "displayName": "GPT OSS 120B", "description": "Open GPT reasoning model for self-hosted agents and controllable deployments", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2025-08-05", "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, "inputLimit": 122880, "maxOutputTokens": 8192, "structuredOutput": true, "lastUpdated": "2025-08-05", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "openai/gpt-oss-safeguard-120b": { "displayName": "GPT OSS Safeguard 120B", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "inputLimit": 112000, "maxOutputTokens": 16000, "structuredOutput": true, "lastUpdated": "2025-10-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "openai/gpt-oss-safeguard-20b": { "displayName": "gpt-oss-safeguard-20b", "description": "Safety model for policy screening, moderation, and risk-aware routing workflows", "lifecycle": "active", "contextWindow": 128000, "inputLimit": 112000, "maxOutputTokens": 16000, "structuredOutput": true, "lastUpdated": "2025-10-29", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "openai/gpt-realtime-1.5": { "displayName": "GPT-Realtime-1.5", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-02-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
@@ -1786,30 +1861,34 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
+        "quiverai/arrow-2": { "displayName": "Arrow 2", "description": "Fast SVG generation model for creation, vectorization, editing, and animation", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "lastUpdated": "2026-09-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text", "image"] } },
+        "quiverai/arrow-2-telos": { "displayName": "Arrow 2 Telos", "description": "High-fidelity SVG generation model for complex vector work and long-context refinement", "lifecycle": "active", "contextWindow": 131072, "maxOutputTokens": 131072, "lastUpdated": "2026-09-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text", "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"] } },
         "recraft/recraft-v3": { "displayName": "Recraft V3", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 512, "lastUpdated": "2024-10", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "recraft/recraft-v4": { "displayName": "Recraft V4", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-02-17", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "recraft/recraft-v4-pro": { "displayName": "Recraft V4 Pro", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-02-17", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "recraft/recraft-v4.1": { "displayName": "Recraft V4.1", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-05-14", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
+        "recraft/recraft-v4.1-flash": { "displayName": "Recraft V4.1 Flash", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-09-23", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "recraft/recraft-v4.1-pro": { "displayName": "Recraft V4.1 Pro", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-05-14", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "recraft/recraft-v4.1-utility": { "displayName": "Recraft V4.1 Utility", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-05-14", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "recraft/recraft-v4.1-utility-pro": { "displayName": "Recraft V4.1 Utility Pro", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-05-14", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
-        "sakana/fugu-max": { "displayName": "Fugu Max", "description": "Multi-agent model for routing expert agents across complex analytical tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "sakana/fugu-ultra": { "displayName": "Fugu Ultra", "description": "Quality-first multi-agent model for hard research, analysis, and competitions", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "structuredOutput": true, "lastUpdated": "2026-06-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "sakana/fugu-ultra-v2": { "displayName": "Fugu Ultra v2", "description": "Quality-first multi-agent model for hard research, analysis, and competitions", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "sakana/namazu": { "displayName": "Sakana Namazu", "description": "Multi-agent model for routing expert agents across complex analytical tasks", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "lastUpdated": "2026-08-03", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "sakana/fugu-max": { "displayName": "Fugu Max", "description": "Multi-agent model for routing expert agents across complex analytical tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "sakana/fugu-ultra": { "displayName": "Fugu Ultra", "description": "Quality-first multi-agent model for hard research, analysis, and competitions", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "structuredOutput": true, "lastUpdated": "2026-06-15", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "sakana/fugu-ultra-v2": { "displayName": "Fugu Ultra v2", "description": "Quality-first multi-agent model for hard research, analysis, and competitions", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "lastUpdated": "2026-09-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "sakana/namazu": { "displayName": "Sakana Namazu", "description": "Multi-agent model for routing expert agents across complex analytical tasks", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "lastUpdated": "2026-08-03", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "spacexai/grok-4.1-fast-non-reasoning": { "displayName": "Grok 4.1 Fast Non-Reasoning", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "lastUpdated": "2025-11-19", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "spacexai/grok-4.1-fast-reasoning": { "displayName": "Grok 4.1 Fast Reasoning", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "structuredOutput": true, "lastUpdated": "2025-11-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "spacexai/grok-4.20-multi-agent": { "displayName": "Grok 4.20 Multi-Agent", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "spacexai/grok-4.20-multi-agent-beta": { "displayName": "Grok 4.20 Multi Agent Beta", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "spacexai/grok-4.1-fast-reasoning": { "displayName": "Grok 4.1 Fast Reasoning", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "structuredOutput": true, "lastUpdated": "2025-11-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "spacexai/grok-4.20-multi-agent": { "displayName": "Grok 4.20 Multi-Agent", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "spacexai/grok-4.20-multi-agent-beta": { "displayName": "Grok 4.20 Multi Agent Beta", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "spacexai/grok-4.20-non-reasoning": { "displayName": "Grok 4.20 Non-Reasoning", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-10", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "spacexai/grok-4.20-non-reasoning-beta": { "displayName": "Grok 4.20 Beta Non-Reasoning", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-11", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "spacexai/grok-4.20-reasoning": { "displayName": "Grok 4.20 Reasoning", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "spacexai/grok-4.20-reasoning-beta": { "displayName": "Grok 4.20 Beta Reasoning", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "spacexai/grok-4.20-reasoning": { "displayName": "Grok 4.20 Reasoning", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-10", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "spacexai/grok-4.20-reasoning-beta": { "displayName": "Grok 4.20 Beta Reasoning", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 2000000, "lastUpdated": "2026-03-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "spacexai/grok-4.3": { "displayName": "Grok 4.3", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "structuredOutput": true, "lastUpdated": "2026-04-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "spacexai/grok-4.5": { "displayName": "Grok 4.5", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "spacexai/grok-4.6": { "displayName": "Grok 4.6", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "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"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "spacexai/grok-build-0.1": { "displayName": "Grok Build 0.1", "description": "Grok coding model for agentic engineering, edits, and codebase workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "structuredOutput": true, "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "spacexai/grok-4.6": { "displayName": "Grok 4.6", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "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"] } },
+        "spacexai/grok-4.7": { "displayName": "Grok 4.7", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-09-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "spacexai/grok-build-0.1": { "displayName": "Grok Build 0.1", "description": "Grok coding model for agentic engineering, edits, and codebase workflows", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 256000, "structuredOutput": true, "lastUpdated": "2026-04-16", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "spacexai/grok-imagine-image": { "displayName": "Grok Imagine Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-01-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "spacexai/grok-imagine-image-2.0": { "displayName": "Grok Imagine Image 2.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-08-07", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
         "spacexai/grok-imagine-video": { "displayName": "Grok Imagine", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "lastUpdated": "2026-01-28", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["video"] } },
@@ -1820,6 +1899,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "spacexai/grok-voice-think-fast-2.0": { "displayName": "Grok Voice Think Fast 2.0", "description": "Speech generation model for controllable voice, narration, and audio delivery", "lifecycle": "active", "lastUpdated": "2026-07-29", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "audio"], "output": ["text", "audio"] } },
         "stepfun/step-3.5-flash": { "displayName": "StepFun 3.5 Flash", "description": "StepFun flash lane for quick multimodal reasoning and coding assistance", "lifecycle": "active", "contextWindow": 262114, "maxOutputTokens": 262114, "knowledgeCutoff": "2025-01", "lastUpdated": "2026-02-13", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "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"], "output": ["text"] } },
+        "stepfun/step-5-preview": { "displayName": "Step 5 Preview", "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "lifecycle": "active", "contextWindow": 1000000, "inputLimit": 1000000, "maxOutputTokens": 1000000, "structuredOutput": true, "lastUpdated": "2026-09-20", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "tencent/hy-mt2-lite": { "displayName": "Tencent Hy-MT2-Lite", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 8000, "maxOutputTokens": 4000, "lastUpdated": "2026-06-12", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "tencent/hy-mt2-plus": { "displayName": "Tencent Hy-MT2-Plus", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 8000, "maxOutputTokens": 4000, "lastUpdated": "2026-06-12", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "tencent/hy-mt2-pro": { "displayName": "Tencent Hy-MT2-Pro", "description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks", "lifecycle": "active", "contextWindow": 8000, "maxOutputTokens": 4000, "lastUpdated": "2026-05-21", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1841,6 +1921,9 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "voyage/voyage-law-2": { "displayName": "voyage-law-2", "description": "General-purpose chat model for instruction following, writing, and analysis", "lifecycle": "active", "contextWindow": 8192, "maxOutputTokens": 1536, "lastUpdated": "2024-03", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["text"] } },
         "xiaomi/mimo-v2.5": { "displayName": "MiMo M2.5", "description": "Open MiMo model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 131100, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "xiaomi/mimo-v2.5-pro": { "displayName": "MiMo V2.5 Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 131000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-04-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "xiaomi/mimo-v2.6-flash": { "displayName": "MiMo V2.6 Flash", "description": "MiMo Flash model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "xiaomi/mimo-v2.6-pro": { "displayName": "MiMo V2.6 Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "xiaomi/mimo-v2.6-pro-ultraspeed": { "displayName": "MiMo V2.6 Pro UltraSpeed", "description": "MiMo pro model for strong multimodal reasoning and agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "minimal", "low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "zai/glm-4.5": { "displayName": "GLM 4.5", "description": "Hybrid-reasoning GLM release that made the 4.5 line broadly useful", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 96000, "knowledgeCutoff": "2025-07", "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai/glm-4.5-air": { "displayName": "GLM 4.5 Air", "description": "Lighter GLM-4.5 variant for fast coding assistance and cheaper agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 96000, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai/glm-4.5v": { "displayName": "GLM 4.5V", "description": "GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 66000, "maxOutputTokens": 16000, "knowledgeCutoff": "2025-08", "lastUpdated": "2025-08-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
@@ -1851,11 +1934,12 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "zai/glm-5": { "displayName": "GLM-5", "description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows", "lifecycle": "active", "contextWindow": 202800, "maxOutputTokens": 131100, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai/glm-5-turbo": { "displayName": "GLM 5 Turbo", "description": "Faster GLM-5 lane for coding agents that need lower latency", "lifecycle": "active", "contextWindow": 202800, "maxOutputTokens": 131100, "structuredOutput": true, "lastUpdated": "2026-03-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai/glm-5.1": { "displayName": "GLM 5.1", "description": "Strong GLM coding model for agentic engineering, terminals, and repository generation", "lifecycle": "active", "contextWindow": 202800, "maxOutputTokens": 64000, "structuredOutput": true, "lastUpdated": "2026-04-07", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "zai/glm-5.2": { "displayName": "GLM 5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "zai/glm-5.2-fast": { "displayName": "GLM 5.2 Fast", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["high", "xhigh"], "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "zai/glm-5.2": { "displayName": "GLM 5.2", "description": "Open flagship GLM for long-horizon coding agents and million-token context work", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "zai/glm-5.2-fast": { "displayName": "GLM 5.2 Fast", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-06-13", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai/glm-5.3": { "displayName": "GLM 5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "zai/glm-5.3-fast": { "displayName": "GLM 5.3 Fast", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "zai/glm-5.3-fast": { "displayName": "GLM 5.3 Fast", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 262144, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text"], "output": ["text"] } },
         "zai/glm-5.3-flash": { "displayName": "GLM 5.3 Flash", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131000, "structuredOutput": true, "lastUpdated": "2026-08-26", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "zai/glm-5.3-flashx": { "displayName": "GLM 5.3 FlashX", "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"], "output": ["text"] } },
         "zai/glm-5v-turbo": { "displayName": "GLM 5V Turbo", "description": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "lastUpdated": "2026-04-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
     },
     "xai": {
@@ -1865,10 +1949,10 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "grok-4.3": { "displayName": "Grok 4.3", "description": "xAI's Grok for chat, coding, agentic tools, and lower hallucination risk", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 30000, "structuredOutput": true, "lastUpdated": "2026-04-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "grok-4.5": { "displayName": "Grok 4.5", "description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "grok-4.6": { "displayName": "Grok 4.6", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "knowledgeCutoff": "2026-02-01", "structuredOutput": true, "lastUpdated": "2026-08-12", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "grok-4.7": { "displayName": "Grok 4.7", "description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "knowledgeCutoff": "2026-05", "structuredOutput": true, "lastUpdated": "2026-09-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "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-imagine-image": { "displayName": "Grok Imagine Image", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 16000, "lastUpdated": "2026-01-28", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "pdf"], "output": ["image", "pdf"] } },
-        "grok-imagine-image-2.0": { "displayName": "Grok Imagine Image 2.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 64000, "lastUpdated": "2026-08-07", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "pdf"], "output": ["image", "pdf"] } },
-        "grok-imagine-image-quality": { "displayName": "Grok Imagine Image Quality", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 16000, "lastUpdated": "2026-04-03", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "pdf"], "output": ["image", "pdf"] } },
+        "grok-imagine-image-quality": { "displayName": "Grok Imagine Image Quality", "description": "Higher-fidelity Grok Imagine image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 16000, "lastUpdated": "2026-04-03", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "pdf"], "output": ["image", "pdf"] } },
         "grok-imagine-video": { "displayName": "Grok Imagine Video", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 1024, "lastUpdated": "2026-01-28", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["video"] } },
         "grok-imagine-video-1.5": { "displayName": "Grok Imagine Video 1.5", "description": "Video model for image-to-video generation, editing, and extension workflows", "lifecycle": "active", "contextWindow": 1024, "lastUpdated": "2026-05-30", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image", "audio", "pdf"], "output": ["video"] } },
     },
@@ -1879,6 +1963,9 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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": "2026-06-24", "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": "2026-06-24", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "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"] } },
+        "mimo-v2.6-flash": { "displayName": "MiMo-V2.6-Flash", "description": "MiMo Flash model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "mimo-v2.6-pro": { "displayName": "MiMo-V2.6-Pro", "description": "MiMo Pro model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "mimo-v2.6-pro-ultraspeed": { "displayName": "MiMo-V2.6-Pro-UltraSpeed", "description": "MiMo pro model for strong multimodal reasoning and agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-21", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1888,6 +1975,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
+        "mimo-v2.6-flash": { "displayName": "MiMo-V2.6-Flash", "description": "MiMo Flash model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "mimo-v2.6-pro": { "displayName": "MiMo-V2.6-Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
     },
     "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1897,6 +1986,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
+        "mimo-v2.6-flash": { "displayName": "MiMo-V2.6-Flash", "description": "MiMo Flash model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "mimo-v2.6-pro": { "displayName": "MiMo-V2.6-Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
     },
     "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", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
@@ -1906,6 +1997,8 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
+        "mimo-v2.6-flash": { "displayName": "MiMo-V2.6-Flash", "description": "MiMo Flash model for multimodal coding agents and long-context automation", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
+        "mimo-v2.6-pro": { "displayName": "MiMo-V2.6-Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 1048576, "maxOutputTokens": 131072, "lastUpdated": "2026-09-22", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video"], "output": ["text"] } },
     },
     "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"] } },
@@ -1914,6 +2007,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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-4.6v-flash": { "displayName": "GLM-4.6V-Flash", "description": "Lightweight GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 32768, "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", "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"] } },
@@ -1923,6 +2017,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "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"] } },
         "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-flashx": { "displayName": "GLM-5.3-FlashX", "description": "High-speed GLM-5.3-Flash serving option for coding and agent workflows", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 131072, "structuredOutput": true, "lastUpdated": "2026-09-18", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
         "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": {
@@ -2000,7 +2095,7 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "openai/gpt-5.4-nano": { "displayName": "GPT-5.4 Nano", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 400000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "capabilities": { "vision": false, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "openai/gpt-5.4-pro": { "displayName": "GPT-5.4 Pro", "description": "Frontier GPT model for professional reasoning, coding, and multimodal work", "lifecycle": "active", "contextWindow": 1050000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "openai/gpt-5.5": { "displayName": "GPT-5.5", "description": "Default frontier GPT for coding, computer use, research, and knowledge work", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12-01", "structuredOutput": true, "lastUpdated": "2026-04-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "openai/gpt-5.5-instant": { "displayName": "GPT-5.5 Instant", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 400000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12-01", "structuredOutput": true, "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
+        "openai/gpt-5.5-instant": { "displayName": "GPT-5.5 Instant", "description": "Compact GPT model for low-latency assistance and high-volume workloads", "lifecycle": "active", "contextWindow": 400000, "inputLimit": 272000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12-01", "structuredOutput": true, "lastUpdated": "2026-05-28", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/gpt-5.5-pro": { "displayName": "GPT-5.5 Pro", "description": "Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-12-01", "structuredOutput": true, "lastUpdated": "2026-04-23", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["medium", "high", "xhigh"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/gpt-5.6-luna": { "displayName": "GPT-5.6 Luna", "description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "openai/gpt-5.6-sol": { "displayName": "GPT-5.6 Sol", "description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "lifecycle": "active", "contextWindow": 1050000, "inputLimit": 922000, "maxOutputTokens": 128000, "knowledgeCutoff": "2026-02-16", "structuredOutput": true, "lastUpdated": "2026-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high", "xhigh", "max"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
@@ -2025,36 +2120,38 @@ export const GENERATED_MODELS_DEV_METADATA = {
         "volcengine/doubao-seed-2.0-mini": { "displayName": "Doubao-Seed-2.0-mini", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2026-02-14", "lastUpdated": "2026-02-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "volcengine/doubao-seed-2.0-pro": { "displayName": "Doubao-Seed-2.0-pro", "description": "Multimodal reasoning model for visual analysis, planning, and tool use", "lifecycle": "active", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2026-02-14", "lastUpdated": "2026-02-14", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
         "volcengine/doubao-seed-code": { "displayName": "Doubao-Seed-Code", "description": "Coding model for repository understanding, refactors, and agentic engineering tasks", "lifecycle": "deprecated", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-11", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "x-ai/grok-4": { "displayName": "Grok 4", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "deprecated", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-07-09", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["image", "text"], "output": ["text"] } },
-        "x-ai/grok-4-fast": { "displayName": "Grok 4 Fast", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "deprecated", "contextWindow": 2000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-09-19", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "x-ai/grok-4.1-fast": { "displayName": "Grok 4.1 Fast", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "deprecated", "contextWindow": 2000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-20", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "x-ai/grok-4.1-fast-non-reasoning": { "displayName": "Grok 4.1 Fast Non Reasoning", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "deprecated", "contextWindow": 2000000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-11-20", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
-        "x-ai/grok-4.2-fast": { "displayName": "Grok 4.2 Fast", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 30000, "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
-        "x-ai/grok-4.2-fast-non-reasoning": { "displayName": "Grok 4.2 Fast Non Reasoning", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 30000, "knowledgeCutoff": "2025-08-31", "lastUpdated": "2026-03-20", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "x-ai/grok-4.2-fast": { "displayName": "Grok 4.2 Fast", "description": "Reasoning Grok for document-heavy analysis and long-horizon tool use", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 30000, "structuredOutput": true, "lastUpdated": "2026-03-09", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "x-ai/grok-4.2-fast-non-reasoning": { "displayName": "Grok 4.2 Fast Non Reasoning", "description": "Grok model for agentic tool use, reasoning, coding, and live assistance", "lifecycle": "active", "contextWindow": 2000000, "maxOutputTokens": 30000, "structuredOutput": true, "lastUpdated": "2026-03-09", "capabilities": { "vision": true, "reasoning": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
         "x-ai/grok-4.3": { "displayName": "Grok 4.3", "description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 1000000, "structuredOutput": true, "lastUpdated": "2026-04-17", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["none", "low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
         "x-ai/grok-4.5": { "displayName": "Grok 4.5", "description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk", "lifecycle": "active", "contextWindow": 500000, "maxOutputTokens": 500000, "structuredOutput": true, "lastUpdated": "2026-07-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "medium", "high"] }, "modalities": { "input": ["text", "image", "pdf"], "output": ["text"] } },
-        "x-ai/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"] } },
-        "x-ai/grok-code-fast-1": { "displayName": "Grok Code Fast 1", "description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "lifecycle": "deprecated", "contextWindow": 256000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-08-26", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "x-ai/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"] } },
+        "x-ai/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": false, "functionCalling": true }, "modalities": { "input": ["text", "image"], "output": ["text"] } },
+        "x-ai/grok-imagine-image-2.0": { "displayName": "Grok Imagine Image 2.0", "description": "Image model for prompt-driven generation, editing, and visual design workflows", "lifecycle": "active", "contextWindow": 66000, "lastUpdated": "2026-08-07", "capabilities": { "vision": true, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text", "image"], "output": ["image"] } },
+        "x-ai/grok-voice-stt-1.0": { "displayName": "Grok Voice STT 1.0", "description": "Grok Voice STT 1.0 is xAI's speech-to-text model. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.", "lifecycle": "active", "contextWindow": 15000, "maxOutputTokens": 15000, "lastUpdated": "2026-08-04", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["audio"], "output": ["text"] } },
+        "x-ai/grok-voice-tts-1.0": { "displayName": "Grok Voice TTS 1.0", "description": "Convert text into spoken audio with a single API call. The API supports a rich set of expressive voices, inline speech tags for fine-grained delivery control, and output formats from high-fidelity MP3 to telephony-optimized μ-law.", "lifecycle": "active", "contextWindow": 15000, "maxOutputTokens": 15000, "lastUpdated": "2026-07-31", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["audio"] } },
         "xiaomi/mimo-v2-flash": { "displayName": "MiMo-V2-Flash", "description": "MiMo flash model for fast multimodal assistance and agent workflows", "lifecycle": "active", "contextWindow": 262144, "maxOutputTokens": 65536, "knowledgeCutoff": "2024-12-01", "lastUpdated": "2026-02-04", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "xiaomi/mimo-v2-omni": { "displayName": "MiMo V2 Omni", "description": "MiMo omni model for text, image, video, audio, and agents", "lifecycle": "active", "contextWindow": 265000, "maxOutputTokens": 265000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "audio", "video", "pdf"], "output": ["text"] } },
         "xiaomi/mimo-v2-pro": { "displayName": "MiMo V2 Pro", "description": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 256000, "knowledgeCutoff": "2024-12", "lastUpdated": "2026-03-18", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
         "xiaomi/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"] } },
         "xiaomi/mimo-v2.5-pro": { "displayName": "MiMo-V2.5-Pro", "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "lifecycle": "active", "contextWindow": 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"] } },
-        "z-ai/glm-4.5": { "displayName": "GLM 4.5", "description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-07-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "z-ai/glm-4.5-air": { "displayName": "GLM 4.5 Air", "description": "Efficient GLM model for fast reasoning, coding, and agent workflows", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 64000, "knowledgeCutoff": "2025-01-01", "lastUpdated": "2025-07-25", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
-        "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", "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", "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", "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"] } },
+        "z-ai/glm-4.5": { "displayName": "GLM 4.5", "description": "Hybrid-reasoning GLM release that made the 4.5 line broadly useful", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 96000, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "z-ai/glm-4.5-air": { "displayName": "GLM 4.5 Air", "description": "Lighter GLM-4.5 variant for fast coding assistance and cheaper agents", "lifecycle": "active", "contextWindow": 128000, "maxOutputTokens": 96000, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-07-28", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "z-ai/glm-4.6": { "displayName": "GLM 4.6", "description": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-09-30", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": 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": 128000, "knowledgeCutoff": "2025-04", "lastUpdated": "2025-12-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "z-ai/glm-4.6v-flash": { "displayName": "GLM 4.6V FlashX", "description": "Lightweight GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "lastUpdated": "2025-12-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video"], "output": ["text"] } },
+        "z-ai/glm-4.6v-flash-free": { "displayName": "GLM 4.6V Flash (Free)", "description": "Lightweight GLM vision model for visual reasoning, documents, and multimodal agents", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "lastUpdated": "2025-12-08", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
+        "z-ai/glm-4.7": { "displayName": "GLM 4.7", "description": "Mature GLM model for dependable coding, reasoning, and structured agent tasks", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-04", "structuredOutput": true, "lastUpdated": "2025-12-22", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "z-ai/glm-4.7-flash-free": { "displayName": "GLM 4.7 Flash (Free)", "description": "Budget GLM lane for fast coding help, routing, and everyday automation", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": 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": 128000, "knowledgeCutoff": "2025-04", "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "z-ai/glm-5": { "displayName": "GLM 5", "description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-02-12", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "z-ai/glm-5-turbo": { "displayName": "GLM 5 Turbo", "description": "Faster GLM-5 lane for coding agents that need lower latency", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-03-16", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text"], "output": ["text"] } },
+        "z-ai/glm-5.1": { "displayName": "GLM 5.1", "description": "Strong GLM coding model for agentic engineering, terminals, and repository generation", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-04-07", "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": 128000, "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-5.3": { "displayName": "GLM 5.3", "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "structuredOutput": true, "lastUpdated": "2026-08-14", "capabilities": { "vision": false, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "efforts": ["low", "high", "max"] }, "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": 128000, "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"] } },
+        "z-ai/glm-5.3-flashx": { "displayName": "GLM 5.3 FlashX", "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "lifecycle": "active", "contextWindow": 1000000, "maxOutputTokens": 128000, "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"] } },
+        "z-ai/glm-5v-turbo": { "displayName": "GLM 5V Turbo", "description": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks", "lifecycle": "active", "contextWindow": 200000, "maxOutputTokens": 128000, "lastUpdated": "2026-04-01", "capabilities": { "vision": true, "reasoning": true, "functionCalling": true }, "thinkingOptions": { "toggle": true }, "modalities": { "input": ["text", "image", "video", "pdf"], "output": ["text"] } },
+        "z-ai/glm-image": { "displayName": "GLM-Image", "description": "GLM-Image is an image generation model adopts a hybrid autoregressive + diffusion decoder architecture. In general image generation quality, GLM‑Image aligns with mainstream latent diffusion approaches, but it shows significant advantages in text-rendering and knowledge‑intensive generation scenarios. It performs especially well in tasks requiring precise semantic understanding and complex information expression, while maintaining strong capabilities in high‑fidelity and fine‑grained detail generation. In addition to text‑to‑image generation, GLM‑Image also supports a rich set of image‑to‑image tasks including image editing, style transfer, identity‑preserving generation, and multi‑subject consistency.", "lifecycle": "active", "contextWindow": 10240, "lastUpdated": "2026-01-19", "capabilities": { "vision": false, "reasoning": false, "functionCalling": false }, "modalities": { "input": ["text"], "output": ["image"] } },
     },
 };
 export const GENERATED_MODELS_DEV_MODEL_PROVIDER_OVERRIDES = {
@@ -2066,7 +2163,7 @@ export const GENERATED_MODELS_DEV_MODEL_PROVIDER_OVERRIDES = {
     "alibaba-token-plan-cn": {},
     "alibaba-token-plan": {},
     "cerebras": {},
-    "cohere": { "north-mini-code-1-0": { "adapter": { "kind": "openai-compatible", "name": "provider" }, "baseUrl": "https://api.cohere.ai/compatibility/v1" } },
+    "cohere": { "north-mini-code-1-0": { "adapter": { "kind": "openai-compatible" }, "baseUrl": "https://api.cohere.ai/compatibility/v1" } },
     "cloudflare-workers-ai": {},
     "deepinfra": {},
     "deepseek": {},
@@ -2085,8 +2182,8 @@ export const GENERATED_MODELS_DEV_MODEL_PROVIDER_OVERRIDES = {
     "nvidia": {},
     "ollama-cloud": {},
     "openai": {},
-    "opencode": { "claude-3-5-haiku": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-fable-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-fable-5-1": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-haiku-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-1": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-6": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-7": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-8": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4-6": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "gemini-3-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3-pro": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.1-pro": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.5-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.5-flash-lite": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.6-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.7-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.8-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gpt-5": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5-codex": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5-nano": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.1": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.1-codex": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.1-codex-max": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.1-codex-mini": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.2": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.2-codex": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.3-codex": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.3-codex-spark": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.4": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.4-mini": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.4-nano": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.4-pro": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.5": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.5-pro": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.6-luna": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.6-sol": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.6-terra": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-6-astra": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-4.5": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-4.6": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-build-0.1": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "minimax-m2.1-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m2.5-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m3-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "muse-spark-1.2": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "muse-spark-1.2-contributor-free": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "muse-spark-1.3": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "muse-spark-1.3-contributor-free": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "qwen3.5-plus": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "qwen3.6-plus": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "qwen3.6-plus-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } } },
-    "opencode-go": { "gpt-5.6-luna": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-4.5": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-4.6": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "minimax-m2.5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m2.7": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m3": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "muse-spark-1.2-contributor": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "muse-spark-1.3-contributor": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "qwen3.8-flash": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } } },
+    "opencode": { "claude-3-5-haiku": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-fable-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-fable-5-1": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-haiku-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-1": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-6": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-7": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-4-8": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-opus-5-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-4-6": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "claude-sonnet-5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "gemini-3-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3-pro": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.1-pro": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.5-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.5-flash-lite": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.6-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.7-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gemini-3.8-flash": { "adapter": { "kind": "google", "normalizeBaseUrl": false } }, "gpt-5": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5-codex": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5-nano": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.1": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.1-codex": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.1-codex-max": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.1-codex-mini": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.2": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.2-codex": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.3-codex": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.3-codex-spark": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.4": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.4-mini": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.4-nano": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.4-pro": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.5": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.5-pro": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.6-luna": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.6-sol": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-5.6-terra": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-6-astra": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-6-luna": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-6-sol": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-4.5": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-4.6": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-4.7": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-build-0.1": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "minimax-m2.1-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m2.5-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m3-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "muse-spark-1.2": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "muse-spark-1.2-contributor-free": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "muse-spark-1.3": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "muse-spark-1.3-contributor-free": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "qwen3.5-plus": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "qwen3.6-plus": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "qwen3.6-plus-free": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "qwen3.8-flash": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } } },
+    "opencode-go": { "gpt-5.6-luna": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "gpt-6-luna": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-4.5": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-4.6": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "grok-4.7": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "minimax-m2.5": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m2.7": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "minimax-m3": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } }, "muse-spark-1.2-contributor": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "muse-spark-1.3-contributor": { "adapter": { "kind": "openai", "responses": { "adapter": "openai", "reasoningReplay": "encrypted-content" } } }, "qwen3.8-flash": { "adapter": { "kind": "anthropic", "auth": "api-key", "normalizeBaseUrl": true } } },
     "openrouter": {},
     "siliconflow": {},
     "stepfun": {},
@@ -2125,9 +2222,9 @@ export const GENERATED_MODELS_DEV_PROVIDER_FACTS = {
     "google": { "id": "google", "name": "Google", "doc": "https://ai.google.dev/gemini-api/docs/models" },
     "groq": { "id": "groq", "name": "Groq", "doc": "https://console.groq.com/docs/models" },
     "huggingface": { "id": "huggingface", "name": "Hugging Face", "api": "https://router.huggingface.co/v1", "doc": "https://huggingface.co/docs/inference-providers" },
-    "kimi-coding-plan": { "id": "kimi-for-coding", "name": "Kimi For Coding", "api": "https://api.kimi.com/coding/v1", "doc": "https://www.kimi.com/code/docs/en/kimi-code/models.html" },
+    "kimi-coding-plan": { "id": "kimi-code-plan-cn", "name": "Kimi For Coding (kimi.com)", "api": "https://api.kimi.com/coding/v1", "doc": "https://www.kimi.com/code/docs/en/kimi-code/models.html" },
     "MiniMax": { "id": "minimax", "name": "MiniMax (minimax.io)", "api": "https://api.minimax.io/anthropic/v1", "doc": "https://platform.minimax.io/docs/guides/quickstart" },
-    "MiniMax-cn": { "id": "minimax-cn", "name": "MiniMax (minimaxi.com)", "api": "https://api.minimaxi.com/anthropic/v1", "doc": "https://platform.minimaxi.com/docs/guides/quickstart" },
+    "MiniMax-cn": { "id": "minimax-cn", "name": "MiniMax (minimax.cn)", "api": "https://api.minimax.cn/anthropic/v1", "doc": "https://platform.minimaxi.com/docs/guides/quickstart" },
     "minimax-coding-plan": { "id": "minimax-coding-plan", "name": "MiniMax Token Plan (minimax.io)", "api": "https://api.minimax.io/anthropic/v1", "doc": "https://platform.minimax.io/docs/token-plan/intro" },
     "mistral": { "id": "mistral", "name": "Mistral", "doc": "https://docs.mistral.ai/getting-started/models/" },
     "moonshot": { "id": "moonshotai-cn", "name": "Moonshot AI (China)", "api": "https://api.moonshot.cn/v1", "doc": "https://platform.moonshot.cn/docs/api/chat" },
@@ -2136,7 +2233,7 @@ export const GENERATED_MODELS_DEV_PROVIDER_FACTS = {
     "ollama-cloud": { "id": "ollama-cloud", "name": "Ollama Cloud", "api": "https://ollama.com/v1", "doc": "https://docs.ollama.com/cloud" },
     "openai": { "id": "openai", "name": "OpenAI", "doc": "https://platform.openai.com/docs/models" },
     "opencode": { "id": "opencode", "name": "OpenCode Zen", "api": "https://opencode.ai/zen/v1", "doc": "https://opencode.ai/docs/zen" },
-    "opencode-go": { "id": "opencode-go", "name": "OpenCode Go", "api": "https://opencode.ai/zen/go/v1", "doc": "https://opencode.ai/docs/zen" },
+    "opencode-go": { "id": "opencode-go", "name": "OpenCode Go", "api": "https://opencode.ai/zen/go/v1", "doc": "https://opencode.ai/docs/go" },
     "openrouter": { "id": "openrouter", "name": "OpenRouter", "api": "https://openrouter.ai/api/v1", "doc": "https://openrouter.ai/models" },
     "siliconflow": { "id": "siliconflow", "name": "SiliconFlow", "api": "https://api.siliconflow.com/v1", "doc": "https://cloud.siliconflow.com/models" },
     "stepfun": { "id": "stepfun", "name": "StepFun (China)", "api": "https://api.stepfun.com/v1", "doc": "https://platform.stepfun.com/docs/zh/overview/concept" },