{
 "data": [
  {
   "id": "deepseek/deepseek-v4-flash-vision-exp",
   "canonical_slug": "deepseek/deepseek-v4-flash-vision-exp-20260821",
   "hugging_face_id": null,
   "name": "DeepSeek: DeepSeek V4 Flash Vision Exp",
   "created": 1787311563,
   "description": "DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "DeepSeek",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000022",
    "completion": "0.00000066",
    "input_cache_read": "0.000000007",
    "overrides": [
     {
      "utc_start": 1000,
      "utc_end": 100,
      "prompt": "0.00000022",
      "completion": "0.00000066",
      "input_cache_read": "0.000000007"
     },
     {
      "utc_start": 100,
      "utc_end": 400,
      "prompt": "0.00000044",
      "completion": "0.00000132",
      "input_cache_read": "0.000000014"
     },
     {
      "utc_start": 400,
      "utc_end": 600,
      "prompt": "0.00000022",
      "completion": "0.00000066",
      "input_cache_read": "0.000000007"
     },
     {
      "utc_start": 600,
      "utc_end": 1000,
      "prompt": "0.00000044",
      "completion": "0.00000132",
      "input_cache_read": "0.000000014"
     }
    ]
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 384000,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "stop",
    "temperature",
    "tool_choice",
    "tools",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/deepseek/deepseek-v4-flash-vision-exp-20260821/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "high",
     "low"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "stealth/ox-alpha",
   "canonical_slug": "stealth/ox-alpha",
   "hugging_face_id": null,
   "name": "Ox Alpha",
   "created": 1787256295,
   "description": "Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0",
    "completion": "0"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 0.95
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": "2098-12-31",
   "links": {
    "details": "/api/v1/models/stealth/ox-alpha/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "high",
     "low"
    ],
    "default_effort": "max"
   }
  },
  {
   "id": "tencent/hy-mt2-1.8b",
   "canonical_slug": "tencent/hy-mt2-1.8b-20260521",
   "hugging_face_id": "tencent/Hy-MT2-1.8B",
   "name": "Tencent: Hy-MT2-1.8B",
   "created": 1787231581,
   "description": "Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...",
   "context_length": 8192,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000044",
    "completion": "0.000000177"
   },
   "top_provider": {
    "context_length": 8192,
    "max_completion_tokens": 4096,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "max_completion_tokens",
    "max_tokens",
    "stop",
    "temperature"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/tencent/hy-mt2-1.8b-20260521/endpoints"
   }
  },
  {
   "id": "~z-ai/glm-latest",
   "canonical_slug": "~z-ai/glm-latest",
   "alias_target": {
    "name": "Z.ai: GLM 5.3",
    "slug": "z-ai/glm-5.3"
   },
   "hugging_face_id": null,
   "name": "Z.ai: GLM Latest",
   "created": 1787151053,
   "description": "This model always redirects to the latest GLM model from Z.ai.",
   "context_length": 1048576,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Router",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000014",
    "completion": "0.0000044",
    "input_cache_read": "0.00000026"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 0.95
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": "2098-12-31",
   "links": {
    "details": "/api/v1/models/~z-ai/glm-latest/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "high",
     "low"
    ],
    "default_effort": "max"
   }
  },
  {
   "id": "z-ai/glm-5.3",
   "canonical_slug": "z-ai/glm-5.3-20260816",
   "hugging_face_id": null,
   "name": "Z.ai: GLM 5.3",
   "created": 1787086655,
   "description": "GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000014",
    "completion": "0.0000044",
    "input_cache_read": "0.00000026"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 0.95
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": "2098-12-31",
   "links": {
    "details": "/api/v1/models/z-ai/glm-5.3-20260816/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 59.5,
     "coding_index": 74.8,
     "agentic_index": 59.1
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "high",
     "low"
    ],
    "default_effort": "max"
   }
  },
  {
   "id": "google/gemini-3.7-flash",
   "canonical_slug": "google/gemini-3.7-flash-20260813",
   "hugging_face_id": null,
   "name": "Google: Gemini 3.7 Flash",
   "created": 1786640581,
   "description": "Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "video",
     "file",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000375",
    "completion": "0.000001875",
    "image": "0.000000375",
    "audio": "0.000000375",
    "input_audio_cache": "0.0000000375",
    "web_search": "0.014",
    "internal_reasoning": "0.000001875",
    "input_cache_read": "0.0000000375",
    "input_cache_write": "0.0000000208333333333333"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3.7-flash-20260813/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1277,
      "win_rate": 59.8,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1358,
      "win_rate": 64.9,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1334,
      "win_rate": 58,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1350,
      "win_rate": 62.4,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1347,
      "win_rate": 59.6,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1324,
      "win_rate": 56,
      "rank": 10
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1323,
      "win_rate": 56.4,
      "rank": 6
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 56,
     "coding_index": 76.1,
     "agentic_index": 45.1
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "google/gemini-3.7-flash:batch",
   "canonical_slug": "google/gemini-3.7-flash-20260813",
   "hugging_face_id": null,
   "name": "Google: Gemini 3.7 Flash (batch)",
   "created": 1786640581,
   "description": "Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "video",
     "file",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000001875",
    "completion": "0.0000009375",
    "image": "0.0000001875",
    "audio": "0.0000001875",
    "input_audio_cache": "0.00000001875",
    "web_search": "0.014",
    "internal_reasoning": "0.0000009375",
    "input_cache_read": "0.00000001875",
    "input_cache_write": "0.0000000208333333333333"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3.7-flash-20260813/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1277,
      "win_rate": 59.8,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1358,
      "win_rate": 64.9,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1334,
      "win_rate": 58,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1350,
      "win_rate": 62.4,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1347,
      "win_rate": 59.6,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1324,
      "win_rate": 56,
      "rank": 10
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1323,
      "win_rate": 56.4,
      "rank": 6
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 56,
     "coding_index": 76.1,
     "agentic_index": 45.1
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "qwen/qwen3.8-2.4t-a95b",
   "canonical_slug": "qwen/qwen3.8-2.4t-a95b-20260812",
   "hugging_face_id": "Qwen/Qwen3.8-2.4T-A95B",
   "name": "Qwen: Qwen3.8 2.4T A95B",
   "created": 1786551702,
   "description": "Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000006",
    "input_cache_read": "0.00000025"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 0.95,
    "top_k": 20
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3.8-2.4t-a95b-20260812/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 57.7,
     "coding_index": 71.9,
     "agentic_index": 57.1
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "xhigh",
     "medium",
     "low"
    ],
    "default_effort": "xhigh"
   }
  },
  {
   "id": "bytedance-seed/seed-2.0-code",
   "canonical_slug": "bytedance-seed/seed-2.0-code-20260730",
   "hugging_face_id": null,
   "name": "ByteDance Seed: Seed-2.0-Code",
   "created": 1786550701,
   "description": "Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...",
   "context_length": 262144,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000005",
    "completion": "0.000003",
    "overrides": [
     {
      "min_prompt_tokens": 128000,
      "prompt": "0.000001",
      "completion": "0.000006"
     }
    ]
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/bytedance-seed/seed-2.0-code-20260730/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "x-ai/grok-4.6",
   "canonical_slug": "x-ai/grok-4.6-20260810",
   "hugging_face_id": null,
   "name": "SpaceXAI: Grok 4.6",
   "created": 1786548957,
   "description": "Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.",
   "context_length": 500000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Grok",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000006",
    "web_search": "0.005",
    "input_cache_read": "0.0000005",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.000004",
      "completion": "0.000012",
      "input_cache_read": "0.000001"
     }
    ]
   },
   "top_provider": {
    "context_length": 500000,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/x-ai/grok-4.6-20260810/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1313,
      "win_rate": 64.8,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1293,
      "win_rate": 55.7,
      "rank": 6
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1282,
      "win_rate": 58.2,
      "rank": 2
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1253,
      "win_rate": 55.5,
      "rank": 6
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1280,
      "win_rate": 57.3,
      "rank": 6
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1328,
      "win_rate": 53.3,
      "rank": 9
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1319,
      "win_rate": 62.1,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1327,
      "win_rate": 53.6,
      "rank": 7
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1314,
      "win_rate": 51.9,
      "rank": 9
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1340,
      "win_rate": 55.7,
      "rank": 6
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1274,
      "win_rate": 52.5,
      "rank": 6
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1336,
      "win_rate": 57.8,
      "rank": 6
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1323,
      "win_rate": 53.7,
      "rank": 7
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 60.9,
     "coding_index": 76.8,
     "agentic_index": 58.7
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "liquid/lfm-2.5-2.6b:free",
   "canonical_slug": "liquid/lfm-2.5-2.6b-20260811",
   "hugging_face_id": "LiquidAI/LFM2.5-2.6B",
   "name": "LiquidAI: LFM2.5-2.6B (free)",
   "created": 1786470519,
   "description": "LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...",
   "context_length": 65536,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0",
    "completion": "0"
   },
   "top_provider": {
    "context_length": 65536,
    "max_completion_tokens": 8192,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_completion_tokens",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 0.1,
    "top_k": 50,
    "repetition_penalty": 1.1
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/liquid/lfm-2.5-2.6b-20260811/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "meta/muse-glimmer-30b",
   "canonical_slug": "meta/muse-glimmer-30b-20260810",
   "hugging_face_id": "meta-models/Muse-Glimmer-30B",
   "name": "Meta: Muse Glimmer 30B",
   "created": 1786302394,
   "description": "Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...",
   "context_length": 131072,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000003",
    "completion": "0.0000011",
    "input_cache_read": "0.00000004"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 0.95,
    "top_k": 64
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/meta/muse-glimmer-30b-20260810/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "meta/muse-spark-1.2",
   "canonical_slug": "meta/muse-spark-1.2-20260805",
   "hugging_face_id": null,
   "name": "Meta: Muse Spark 1.2",
   "created": 1785959287,
   "description": "Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "video",
     "file",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.00000425",
    "web_search": "0.0025",
    "input_cache_read": "0.00000015"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": null,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/meta/muse-spark-1.2-20260805/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1247,
      "win_rate": 56.1,
      "rank": 10
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1246,
      "win_rate": 49.9,
      "rank": 13
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1166,
      "win_rate": 43.4,
      "rank": 16
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1208,
      "win_rate": 47.4,
      "rank": 17
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1223,
      "win_rate": 48.7,
      "rank": 11
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1261,
      "win_rate": 52.3,
      "rank": 9
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1345,
      "win_rate": 62.1,
      "rank": 7
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1343,
      "win_rate": 59.1,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1362,
      "win_rate": 62.9,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1352,
      "win_rate": 60.3,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1346,
      "win_rate": 58.8,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1336,
      "win_rate": 57.6,
      "rank": 2
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 56.8,
     "coding_index": 72.2,
     "agentic_index": 49.3
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "qwen/qwen3.8-max",
   "canonical_slug": "qwen/qwen3.8-max-20260803",
   "hugging_face_id": null,
   "name": "Qwen: Qwen3.8 Max",
   "created": 1785731612,
   "description": "Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000006",
    "input_cache_read": "0.00000025",
    "input_cache_write": "0.0000025"
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3.8-max-20260803/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1340,
      "win_rate": 65.4,
      "rank": 4
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1267,
      "win_rate": 55.8,
      "rank": 3
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1341,
      "win_rate": 64.2,
      "rank": 1
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1378,
      "win_rate": 59.5,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1323,
      "win_rate": 55.2,
      "rank": 8
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1285,
      "win_rate": 53.1,
      "rank": 18
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1340,
      "win_rate": 57.5,
      "rank": 7
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1356,
      "win_rate": 60.1,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1304,
      "win_rate": 53.4,
      "rank": 13
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 58.1,
     "coding_index": 71.8,
     "agentic_index": 58.4
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "xhigh"
   }
  },
  {
   "id": "qwen/qwen3.7-flash",
   "canonical_slug": "qwen/qwen3.7-flash-20260727",
   "hugging_face_id": null,
   "name": "Qwen: Qwen3.7 Flash",
   "created": 1785190561,
   "description": "Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000003",
    "completion": "0.00000013",
    "input_cache_read": "0.000000006",
    "input_cache_write": "0.000000038",
    "overrides": [
     {
      "min_prompt_tokens": 32000,
      "prompt": "0.0000001",
      "completion": "0.0000004",
      "input_cache_read": "0.00000002",
      "input_cache_write": "0.000000125"
     },
     {
      "min_prompt_tokens": 256000,
      "prompt": "0.0000002",
      "completion": "0.0000008",
      "input_cache_read": "0.00000004",
      "input_cache_write": "0.00000025"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "temperature",
    "tool_choice",
    "tools",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3.7-flash-20260727/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supports_max_tokens": true
   }
  },
  {
   "id": "anthropic/claude-opus-5",
   "canonical_slug": "anthropic/claude-opus-5-20260723",
   "hugging_face_id": null,
   "name": "Claude Opus 5",
   "created": 1784912544,
   "description": "Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Claude",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000005",
    "completion": "0.000025",
    "web_search": "0.01",
    "input_cache_read": "0.0000005",
    "input_cache_write": "0.00000625",
    "input_cache_write_1h": "0.00001"
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "verbosity"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/anthropic/claude-opus-5-20260723/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1354,
      "win_rate": 69.3,
      "rank": 3
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1273,
      "win_rate": 55.5,
      "rank": 7
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1380,
      "win_rate": 63.6,
      "rank": 2
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1351,
      "win_rate": 59.4,
      "rank": 2
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1359,
      "win_rate": 60.8,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1382,
      "win_rate": 62.3,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1365,
      "win_rate": 62.8,
      "rank": 1
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1373,
      "win_rate": 61.9,
      "rank": 2
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1333,
      "win_rate": 57.7,
      "rank": 3
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 63.1,
     "coding_index": 78,
     "agentic_index": 59.2
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "anthropic/claude-opus-5:batch",
   "canonical_slug": "anthropic/claude-opus-5-20260723",
   "hugging_face_id": null,
   "name": "Claude Opus 5 (batch)",
   "created": 1784912544,
   "description": "Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Claude",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000025",
    "completion": "0.0000125",
    "web_search": "0.01",
    "input_cache_read": "0.00000025",
    "input_cache_write": "0.000003125",
    "input_cache_write_1h": "0.000005"
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "stop",
    "structured_outputs",
    "tool_choice",
    "tools",
    "verbosity"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/anthropic/claude-opus-5-20260723/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1354,
      "win_rate": 69.3,
      "rank": 3
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1273,
      "win_rate": 55.5,
      "rank": 7
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1380,
      "win_rate": 63.6,
      "rank": 2
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1351,
      "win_rate": 59.4,
      "rank": 2
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1359,
      "win_rate": 60.8,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1382,
      "win_rate": 62.3,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1365,
      "win_rate": 62.8,
      "rank": 1
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1373,
      "win_rate": 61.9,
      "rank": 2
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1333,
      "win_rate": 57.7,
      "rank": 3
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 63.1,
     "coding_index": 78,
     "agentic_index": 59.2
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "google/gemini-3.6-flash",
   "canonical_slug": "google/gemini-3.6-flash-20260721",
   "hugging_face_id": null,
   "name": "Google: Gemini 3.6 Flash",
   "created": 1784646733,
   "description": "Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "video",
     "file",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000075",
    "completion": "0.00000375",
    "image": "0.00000075",
    "audio": "0.00000075",
    "input_audio_cache": "0.000000075",
    "web_search": "0.014",
    "internal_reasoning": "0.00000375",
    "input_cache_read": "0.000000075",
    "input_cache_write": "0.0000000416666666666667"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3.6-flash-20260721/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1202,
      "win_rate": 53.8,
      "rank": 6
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1223,
      "win_rate": 53.7,
      "rank": 13
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1212,
      "win_rate": 46.1,
      "rank": 18
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1151,
      "win_rate": 40.6,
      "rank": 19
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1264,
      "win_rate": 55.1,
      "rank": 5
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1172,
      "win_rate": 39.1,
      "rank": 16
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1245,
      "win_rate": 48.8,
      "rank": 13
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1323,
      "win_rate": 53.5,
      "rank": 10
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1274,
      "win_rate": 54.5,
      "rank": 11
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1319,
      "win_rate": 54,
      "rank": 9
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1322,
      "win_rate": 53.3,
      "rank": 8
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1297,
      "win_rate": 51.8,
      "rank": 19
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1328,
      "win_rate": 55.3,
      "rank": 8
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1323,
      "win_rate": 56.2,
      "rank": 5
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 51.6,
     "coding_index": 69.2,
     "agentic_index": 40.5
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "google/gemini-3.6-flash:batch",
   "canonical_slug": "google/gemini-3.6-flash-20260721",
   "hugging_face_id": null,
   "name": "Google: Gemini 3.6 Flash (batch)",
   "created": 1784646733,
   "description": "Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "video",
     "file",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000375",
    "completion": "0.000001875",
    "image": "0.000000375",
    "audio": "0.000000375",
    "input_audio_cache": "0.0000000375",
    "web_search": "0.014",
    "internal_reasoning": "0.000001875",
    "input_cache_read": "0.0000000375",
    "input_cache_write": "0.0000000416666666666667"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3.6-flash-20260721/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1202,
      "win_rate": 53.8,
      "rank": 6
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1223,
      "win_rate": 53.7,
      "rank": 13
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1212,
      "win_rate": 46.1,
      "rank": 18
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1151,
      "win_rate": 40.6,
      "rank": 19
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1264,
      "win_rate": 55.1,
      "rank": 5
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1172,
      "win_rate": 39.1,
      "rank": 16
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1245,
      "win_rate": 48.8,
      "rank": 13
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1323,
      "win_rate": 53.5,
      "rank": 10
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1274,
      "win_rate": 54.5,
      "rank": 11
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1319,
      "win_rate": 54,
      "rank": 9
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1322,
      "win_rate": 53.3,
      "rank": 8
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1297,
      "win_rate": 51.8,
      "rank": 19
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1328,
      "win_rate": 55.3,
      "rank": 8
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1323,
      "win_rate": 56.2,
      "rank": 5
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 51.6,
     "coding_index": 69.2,
     "agentic_index": 40.5
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "google/gemini-3.5-flash-lite",
   "canonical_slug": "google/gemini-3.5-flash-lite-20260721",
   "hugging_face_id": null,
   "name": "Google: Gemini 3.5 Flash Lite",
   "created": 1784646726,
   "description": "Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "video",
     "file",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000003",
    "completion": "0.0000025",
    "image": "0.0000003",
    "audio": "0.0000003",
    "input_audio_cache": "0.00000003",
    "web_search": "0.014",
    "internal_reasoning": "0.0000025",
    "input_cache_read": "0.00000003",
    "input_cache_write": "0.0000000833333333333333"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3.5-flash-lite-20260721/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 37.4,
     "coding_index": 49.3,
     "agentic_index": 27.2
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "minimal"
   }
  },
  {
   "id": "google/gemini-3.5-flash-lite:batch",
   "canonical_slug": "google/gemini-3.5-flash-lite-20260721",
   "hugging_face_id": null,
   "name": "Google: Gemini 3.5 Flash Lite (batch)",
   "created": 1784646726,
   "description": "Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "video",
     "file",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000015",
    "completion": "0.00000125",
    "image": "0.00000015",
    "audio": "0.00000015",
    "input_audio_cache": "0.000000015",
    "web_search": "0.014",
    "internal_reasoning": "0.00000125",
    "input_cache_read": "0.000000015"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3.5-flash-lite-20260721/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 37.4,
     "coding_index": 49.3,
     "agentic_index": 27.2
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "minimal"
   }
  },
  {
   "id": "openrouter/auto-beta",
   "canonical_slug": "openrouter/auto-beta",
   "hugging_face_id": null,
   "name": "Auto Router (Beta)",
   "created": 1784311165,
   "description": "Auto Router (Beta) is a task-aware router from OpenRouter. It classifies each request, then routes it the [most popular model](/rankings#task-spend) for that task based on aggregate spend, filtered by your...",
   "context_length": 2000000,
   "architecture": {
    "modality": "text+image+file+audio+video->text+image",
    "input_modalities": [
     "text",
     "image",
     "audio",
     "file",
     "video"
    ],
    "output_modalities": [
     "text",
     "image"
    ],
    "tokenizer": "Router",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "-1",
    "completion": "-1"
   },
   "top_provider": {
    "context_length": null,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "prediction",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_a",
    "top_k",
    "top_logprobs",
    "top_p",
    "web_search_options"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openrouter/auto-beta/endpoints"
   }
  },
  {
   "id": "moonshotai/kimi-k3",
   "canonical_slug": "moonshotai/kimi-k3-20260715",
   "hugging_face_id": "moonshotai/Kimi-K3",
   "name": "MoonshotAI: Kimi K3",
   "created": 1784215858,
   "description": "Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000003",
    "completion": "0.000015",
    "input_cache_read": "0.0000003"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": 0.95,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/moonshotai/kimi-k3-20260715/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1254,
      "win_rate": 55.7,
      "rank": 8
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1364,
      "win_rate": 67.4,
      "rank": 2
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1199,
      "win_rate": 48.5,
      "rank": 11
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1259,
      "win_rate": 59.1,
      "rank": 2
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1297,
      "win_rate": 58.1,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1296,
      "win_rate": 59.6,
      "rank": 4
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1329,
      "win_rate": 62.7,
      "rank": 2
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1445,
      "win_rate": 69.3,
      "rank": 1
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1407,
      "win_rate": 66.1,
      "rank": 1
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1376,
      "win_rate": 64.9,
      "rank": 1
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1438,
      "win_rate": 68.8,
      "rank": 1
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1356,
      "win_rate": 65.9,
      "rank": 2
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1377,
      "win_rate": 63.3,
      "rank": 1
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1372,
      "win_rate": 63,
      "rank": 1
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 59.7,
     "coding_index": 76.2,
     "agentic_index": 54.3
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "high",
     "low"
    ],
    "default_effort": "max"
   }
  },
  {
   "id": "meta/muse-spark-1.1",
   "canonical_slug": "meta/muse-spark-1.1-20260709",
   "hugging_face_id": null,
   "name": "Meta: Muse Spark 1.1",
   "created": 1784215741,
   "description": "Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "video",
     "file",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.00000425",
    "web_search": "0.0025",
    "input_cache_read": "0.00000015"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": null,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/meta/muse-spark-1.1-20260709/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1191,
      "win_rate": 48.2,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1205,
      "win_rate": 48.1,
      "rank": 16
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1243,
      "win_rate": 48.7,
      "rank": 14
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1141,
      "win_rate": 39.4,
      "rank": 20
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1204,
      "win_rate": 51.8,
      "rank": 8
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1205,
      "win_rate": 44.7,
      "rank": 18
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1178,
      "win_rate": 44.2,
      "rank": 15
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1238,
      "win_rate": 50.1,
      "rank": 17
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1300,
      "win_rate": 53.6,
      "rank": 17
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1331,
      "win_rate": 62.2,
      "rank": 2
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1303,
      "win_rate": 53.8,
      "rank": 13
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1300,
      "win_rate": 53.5,
      "rank": 13
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1315,
      "win_rate": 53.5,
      "rank": 13
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1267,
      "win_rate": 51.5,
      "rank": 9
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1320,
      "win_rate": 54.6,
      "rank": 11
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1291,
      "win_rate": 53,
      "rank": 19
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 53.2,
     "coding_index": 71.3,
     "agentic_index": 39.7
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-luna-pro",
   "canonical_slug": "openai/gpt-5.6-luna-pro-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Luna Pro",
   "created": 1783590867,
   "description": "GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000002",
    "completion": "0.0000012",
    "web_search": "0.01",
    "input_cache_read": "0.00000002",
    "input_cache_write": "0.00000025",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.0000004",
      "completion": "0.0000018",
      "input_cache_read": "0.00000004",
      "input_cache_write": "0.0000005"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-luna-pro-20260709/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-luna-pro:batch",
   "canonical_slug": "openai/gpt-5.6-luna-pro-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Luna Pro (batch)",
   "created": 1783590867,
   "description": "GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000001",
    "completion": "0.0000006",
    "web_search": "0.01",
    "input_cache_read": "0.00000001",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.0000002",
      "completion": "0.0000009",
      "input_cache_read": "0.00000002"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-luna-pro-20260709/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-luna",
   "canonical_slug": "openai/gpt-5.6-luna-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Luna",
   "created": 1783590864,
   "description": "GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000002",
    "completion": "0.0000012",
    "web_search": "0.01",
    "input_cache_read": "0.00000002",
    "input_cache_write": "0.00000025",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.0000004",
      "completion": "0.0000018",
      "input_cache_read": "0.00000004",
      "input_cache_write": "0.0000005"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-luna-20260709/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 52.3,
     "coding_index": 71.4,
     "agentic_index": 46.9
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-luna:batch",
   "canonical_slug": "openai/gpt-5.6-luna-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Luna (batch)",
   "created": 1783590864,
   "description": "GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000001",
    "completion": "0.0000006",
    "web_search": "0.01",
    "input_cache_read": "0.00000001",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.0000002",
      "completion": "0.0000009",
      "input_cache_read": "0.00000002"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-luna-20260709/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 52.3,
     "coding_index": 71.4,
     "agentic_index": 46.9
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-terra-pro",
   "canonical_slug": "openai/gpt-5.6-terra-pro-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Terra Pro",
   "created": 1783590861,
   "description": "GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000012",
    "web_search": "0.01",
    "input_cache_read": "0.0000002",
    "input_cache_write": "0.0000025",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.000004",
      "completion": "0.000018",
      "input_cache_read": "0.0000004",
      "input_cache_write": "0.000005"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-terra-pro-20260709/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-terra-pro:batch",
   "canonical_slug": "openai/gpt-5.6-terra-pro-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Terra Pro (batch)",
   "created": 1783590861,
   "description": "GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000001",
    "completion": "0.000006",
    "web_search": "0.01",
    "input_cache_read": "0.0000001",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.000002",
      "completion": "0.000009",
      "input_cache_read": "0.0000002"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-terra-pro-20260709/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-terra",
   "canonical_slug": "openai/gpt-5.6-terra-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Terra",
   "created": 1783590857,
   "description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000012",
    "web_search": "0.01",
    "input_cache_read": "0.0000002",
    "input_cache_write": "0.0000025",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.000004",
      "completion": "0.000018",
      "input_cache_read": "0.0000004",
      "input_cache_write": "0.000005"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-terra-20260709/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 56.6,
     "coding_index": 76.7,
     "agentic_index": 50.2
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-terra:batch",
   "canonical_slug": "openai/gpt-5.6-terra-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Terra (batch)",
   "created": 1783590857,
   "description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000001",
    "completion": "0.000006",
    "web_search": "0.01",
    "input_cache_read": "0.0000001",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.000002",
      "completion": "0.000009",
      "input_cache_read": "0.0000002"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-terra-20260709/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 56.6,
     "coding_index": 76.7,
     "agentic_index": 50.2
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-sol-pro",
   "canonical_slug": "openai/gpt-5.6-sol-pro-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Sol Pro",
   "created": 1783590854,
   "description": "GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000025",
    "completion": "0.000015",
    "web_search": "0.01",
    "input_cache_read": "0.00000025",
    "input_cache_write": "0.000003125",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.000005",
      "completion": "0.0000225",
      "input_cache_read": "0.0000005",
      "input_cache_write": "0.00000625"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-sol-pro-20260709/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-sol-pro:batch",
   "canonical_slug": "openai/gpt-5.6-sol-pro-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Sol Pro (batch)",
   "created": 1783590854,
   "description": "GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.0000075",
    "web_search": "0.01",
    "input_cache_read": "0.000000125",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.0000025",
      "completion": "0.00001125",
      "input_cache_read": "0.00000025"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-sol-pro-20260709/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-sol",
   "canonical_slug": "openai/gpt-5.6-sol-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Sol",
   "created": 1783590850,
   "description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000025",
    "completion": "0.000015",
    "web_search": "0.01",
    "input_cache_read": "0.00000025",
    "input_cache_write": "0.000003125",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.000005",
      "completion": "0.0000225",
      "input_cache_read": "0.0000005",
      "input_cache_write": "0.00000625"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-sol-20260709/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 60.9,
     "coding_index": 77.4,
     "agentic_index": 57.8
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.6-sol:batch",
   "canonical_slug": "openai/gpt-5.6-sol-20260709",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-5.6 Sol (batch)",
   "created": 1783590850,
   "description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.0000075",
    "web_search": "0.01",
    "input_cache_read": "0.000000125",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.0000025",
      "completion": "0.00001125",
      "input_cache_read": "0.00000025"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.6-sol-20260709/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 60.9,
     "coding_index": 77.4,
     "agentic_index": 57.8
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "x-ai/grok-4.5",
   "canonical_slug": "x-ai/grok-4.5-20260708",
   "hugging_face_id": null,
   "name": "SpaceXAI: Grok 4.5",
   "created": 1783523154,
   "description": "Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.",
   "context_length": 500000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Grok",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000006",
    "web_search": "0.005",
    "input_cache_read": "0.0000003",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.000004",
      "completion": "0.000012",
      "input_cache_read": "0.0000006"
     }
    ]
   },
   "top_provider": {
    "context_length": 500000,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/x-ai/grok-4.5-20260708/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1222,
      "win_rate": 56.6,
      "rank": 5
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1268,
      "win_rate": 67.7,
      "rank": 4
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1278,
      "win_rate": 62.6,
      "rank": 9
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1270,
      "win_rate": 62.2,
      "rank": 3
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1214,
      "win_rate": 52.8,
      "rank": 6
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1248,
      "win_rate": 53.1,
      "rank": 9
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1249,
      "win_rate": 53.9,
      "rank": 8
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1248,
      "win_rate": 53.8,
      "rank": 12
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1308,
      "win_rate": 50.5,
      "rank": 14
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1300,
      "win_rate": 58.6,
      "rank": 7
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1307,
      "win_rate": 51.5,
      "rank": 12
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1296,
      "win_rate": 49.8,
      "rank": 15
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1306,
      "win_rate": 49.6,
      "rank": 15
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1265,
      "win_rate": 52.1,
      "rank": 11
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1311,
      "win_rate": 53.2,
      "rank": 13
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1308,
      "win_rate": 53.9,
      "rank": 11
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 55.8,
     "coding_index": 72.4,
     "agentic_index": 48.9
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "~x-ai/grok-latest",
   "canonical_slug": "~x-ai/grok-latest",
   "alias_target": {
    "name": "SpaceXAI: Grok 4.6",
    "slug": "x-ai/grok-4.6"
   },
   "hugging_face_id": null,
   "name": "xAI: Grok Latest",
   "created": 1783519360,
   "description": "This model always redirects to the latest Grok model from xAI.",
   "context_length": 500000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Router",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000006",
    "web_search": "0.005",
    "input_cache_read": "0.0000005",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.000004",
      "completion": "0.000012",
      "input_cache_read": "0.000001"
     }
    ]
   },
   "top_provider": {
    "context_length": 500000,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/~x-ai/grok-latest/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "aion-labs/aion-3.0-mini",
   "canonical_slug": "aion-labs/aion-3.0-mini-20260707",
   "hugging_face_id": null,
   "name": "AionLabs: Aion-3.0-Mini",
   "created": 1783443096,
   "description": "Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...",
   "context_length": 131072,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000007",
    "completion": "0.0000014",
    "input_cache_read": "0.00000018"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/aion-labs/aion-3.0-mini-20260707/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "aion-labs/aion-3.0",
   "canonical_slug": "aion-labs/aion-3.0-20260707",
   "hugging_face_id": null,
   "name": "AionLabs: Aion-3.0",
   "created": 1783443095,
   "description": "Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...",
   "context_length": 131072,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000003",
    "completion": "0.000006",
    "input_cache_read": "0.00000075"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/aion-labs/aion-3.0-20260707/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "sakana/fugu-ultra",
   "canonical_slug": "sakana/fugu-ultra-20260615",
   "hugging_face_id": null,
   "name": "Sakana: Fugu Ultra",
   "created": 1782276303,
   "description": "Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000005",
    "completion": "0.00003",
    "web_search": "0.01",
    "input_cache_read": "0.0000005",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.00001",
      "completion": "0.000045",
      "input_cache_read": "0.000001"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 128000,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "reasoning",
    "reasoning_effort",
    "structured_outputs",
    "tool_choice",
    "tools",
    "web_search_options"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/sakana/fugu-ultra-20260615/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high"
    ],
    "default_effort": "xhigh"
   }
  },
  {
   "id": "google/gemini-3-pro-image",
   "canonical_slug": "google/gemini-3-pro-image-20260528",
   "hugging_face_id": null,
   "name": "Google: Nano Banana Pro (Gemini 3 Pro Image)",
   "created": 1781754054,
   "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...",
   "context_length": 131072,
   "architecture": {
    "modality": "text+image->text+image",
    "input_modalities": [
     "image",
     "text"
    ],
    "output_modalities": [
     "image",
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000012",
    "image": "0.000002",
    "image_output": "0.00012",
    "audio": "0.000002",
    "input_audio_cache": "0.0000002",
    "web_search": "0.014",
    "internal_reasoning": "0.000012",
    "input_cache_read": "0.0000002",
    "input_cache_write": "0.000000375"
   },
   "top_provider": {
    "context_length": 65536,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3-pro-image-20260528/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openrouter/fusion",
   "canonical_slug": "openrouter/fusion",
   "hugging_face_id": null,
   "name": "OpenRouter: Fusion",
   "created": 1781371647,
   "description": "Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Router",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "-1",
    "completion": "-1"
   },
   "top_provider": {
    "context_length": null,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openrouter/fusion/endpoints"
   }
  },
  {
   "id": "moonshotai/kimi-k2.7-code",
   "canonical_slug": "moonshotai/kimi-k2.7-code-20260612",
   "hugging_face_id": "moonshotai/Kimi-K2.7-Code",
   "name": "MoonshotAI: Kimi K2.7 Code",
   "created": 1781266361,
   "description": "MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...",
   "context_length": 262144,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000067",
    "completion": "0.0000034",
    "input_cache_read": "0.00000017"
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 262144,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "parallel_tool_calls",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/moonshotai/kimi-k2.7-code-20260612/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1137,
      "win_rate": 43.1,
      "rank": 16
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1164,
      "win_rate": 46.6,
      "rank": 25
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1210,
      "win_rate": 53,
      "rank": 19
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1183,
      "win_rate": 49.3,
      "rank": 12
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1212,
      "win_rate": 54.1,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1197,
      "win_rate": 49.2,
      "rank": 22
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1168,
      "win_rate": 44.4,
      "rank": 17
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1211,
      "win_rate": 47.8,
      "rank": 21
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1289,
      "win_rate": 52.1,
      "rank": 23
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1250,
      "win_rate": 52.6,
      "rank": 14
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1283,
      "win_rate": 52.1,
      "rank": 25
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1244,
      "win_rate": 50.1,
      "rank": 34
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1250,
      "win_rate": 49.5,
      "rank": 33
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1215,
      "win_rate": 48,
      "rank": 26
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1291,
      "win_rate": 53.1,
      "rank": 22
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1292,
      "win_rate": 53.7,
      "rank": 18
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 43,
     "coding_index": 60.8,
     "agentic_index": 30.3
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true
   }
  },
  {
   "id": "moonshotai/kimi-k2.7-code:batch",
   "canonical_slug": "moonshotai/kimi-k2.7-code-20260612",
   "hugging_face_id": "moonshotai/Kimi-K2.7-Code",
   "name": "MoonshotAI: Kimi K2.7 Code (batch)",
   "created": 1781266361,
   "description": "MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...",
   "context_length": 262144,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000095",
    "completion": "0.000004",
    "input_cache_read": "0.00000019"
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/moonshotai/kimi-k2.7-code-20260612/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1137,
      "win_rate": 43.1,
      "rank": 16
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1164,
      "win_rate": 46.6,
      "rank": 25
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1210,
      "win_rate": 53,
      "rank": 19
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1183,
      "win_rate": 49.3,
      "rank": 12
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1212,
      "win_rate": 54.1,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1197,
      "win_rate": 49.2,
      "rank": 22
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1168,
      "win_rate": 44.4,
      "rank": 17
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1211,
      "win_rate": 47.8,
      "rank": 21
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1289,
      "win_rate": 52.1,
      "rank": 23
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1250,
      "win_rate": 52.6,
      "rank": 14
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1283,
      "win_rate": 52.1,
      "rank": 25
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1244,
      "win_rate": 50.1,
      "rank": 34
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1250,
      "win_rate": 49.5,
      "rank": 33
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1215,
      "win_rate": 48,
      "rank": 26
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1291,
      "win_rate": 53.1,
      "rank": 22
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1292,
      "win_rate": 53.7,
      "rank": 18
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 43,
     "coding_index": 60.8,
     "agentic_index": 30.3
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true
   }
  },
  {
   "id": "~anthropic/claude-fable-latest",
   "canonical_slug": "~anthropic/claude-fable-latest",
   "alias_target": {
    "name": "Anthropic: Claude Fable 5",
    "slug": "anthropic/claude-fable-5"
   },
   "hugging_face_id": null,
   "name": "Anthropic: Claude Fable Latest",
   "created": 1781029944,
   "description": "This model always redirects to the latest model in the Claude Fable family.",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Router",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00001",
    "completion": "0.00005",
    "web_search": "0.01",
    "input_cache_read": "0.000001",
    "input_cache_write": "0.0000125",
    "input_cache_write_1h": "0.00002"
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "stop",
    "structured_outputs",
    "tool_choice",
    "tools",
    "verbosity"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/~anthropic/claude-fable-latest/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "anthropic/claude-fable-5",
   "canonical_slug": "anthropic/claude-5-fable-20260609",
   "hugging_face_id": null,
   "name": "Anthropic: Claude Fable 5",
   "created": 1781007515,
   "description": "Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Claude",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00001",
    "completion": "0.00005",
    "web_search": "0.01",
    "input_cache_read": "0.000001",
    "input_cache_write": "0.0000125",
    "input_cache_write_1h": "0.00002"
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 128000,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "stop",
    "structured_outputs",
    "tool_choice",
    "tools",
    "verbosity"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/anthropic/claude-5-fable-20260609/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1298,
      "win_rate": 65,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "agentichtmlslides",
      "elo": 1254,
      "win_rate": 59.4,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "agenticslides(html)",
      "elo": 1252,
      "win_rate": 59.5,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1306,
      "win_rate": 65.3,
      "rank": 2
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1296,
      "win_rate": 61,
      "rank": 5
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1344,
      "win_rate": 70.2,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1267,
      "win_rate": 60.7,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1264,
      "win_rate": 57,
      "rank": 4
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1314,
      "win_rate": 62.2,
      "rank": 2
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1294,
      "win_rate": 59.2,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1365,
      "win_rate": 62.3,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1367,
      "win_rate": 70.6,
      "rank": 1
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1340,
      "win_rate": 59.2,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1335,
      "win_rate": 58.3,
      "rank": 6
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1383,
      "win_rate": 63.4,
      "rank": 2
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1344,
      "win_rate": 65.3,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1343,
      "win_rate": 58.5,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1321,
      "win_rate": 58.2,
      "rank": 8
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 62.1,
     "coding_index": 76.5,
     "agentic_index": 56.6
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "anthropic/claude-fable-5:batch",
   "canonical_slug": "anthropic/claude-5-fable-20260609",
   "hugging_face_id": null,
   "name": "Anthropic: Claude Fable 5 (batch)",
   "created": 1781007515,
   "description": "Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Claude",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000005",
    "completion": "0.000025",
    "web_search": "0.01",
    "input_cache_read": "0.0000005",
    "input_cache_write": "0.00000625",
    "input_cache_write_1h": "0.00001"
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "stop",
    "structured_outputs",
    "tool_choice",
    "tools",
    "verbosity"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/anthropic/claude-5-fable-20260609/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1298,
      "win_rate": 65,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "agentichtmlslides",
      "elo": 1254,
      "win_rate": 59.4,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "agenticslides(html)",
      "elo": 1252,
      "win_rate": 59.5,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1306,
      "win_rate": 65.3,
      "rank": 2
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1296,
      "win_rate": 61,
      "rank": 5
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1344,
      "win_rate": 70.2,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1267,
      "win_rate": 60.7,
      "rank": 1
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1264,
      "win_rate": 57,
      "rank": 4
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1314,
      "win_rate": 62.2,
      "rank": 2
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1294,
      "win_rate": 59.2,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1365,
      "win_rate": 62.3,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1367,
      "win_rate": 70.6,
      "rank": 1
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1340,
      "win_rate": 59.2,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1335,
      "win_rate": 58.3,
      "rank": 6
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1383,
      "win_rate": 63.4,
      "rank": 2
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1344,
      "win_rate": 65.3,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1343,
      "win_rate": 58.5,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1321,
      "win_rate": 58.2,
      "rank": 8
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 62.1,
     "coding_index": 76.5,
     "agentic_index": 56.6
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "qwen/qwen3.7-plus",
   "canonical_slug": "qwen/qwen3.7-plus-20260602",
   "hugging_face_id": null,
   "name": "Qwen: Qwen3.7 Plus",
   "created": 1780491783,
   "description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000032",
    "completion": "0.00000128",
    "input_cache_read": "0.000000064",
    "input_cache_write": "0.0000004",
    "overrides": [
     {
      "min_prompt_tokens": 256000,
      "prompt": "0.00000096",
      "completion": "0.00000384",
      "input_cache_read": "0.000000192",
      "input_cache_write": "0.0000012"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1287,
      "win_rate": 49.5,
      "rank": 24
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1171,
      "win_rate": 44.1,
      "rank": 38
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1289,
      "win_rate": 50.5,
      "rank": 21
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1280,
      "win_rate": 51.6,
      "rank": 20
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1295,
      "win_rate": 51.1,
      "rank": 21
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1256,
      "win_rate": 52.8,
      "rank": 15
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1275,
      "win_rate": 48.9,
      "rank": 27
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1291,
      "win_rate": 51.5,
      "rank": 20
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 39.4,
     "coding_index": 55.9,
     "agentic_index": 20.7
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true
   }
  },
  {
   "id": "stepfun/step-3.7-flash",
   "canonical_slug": "stepfun/step-3.7-flash-20260528",
   "hugging_face_id": "stepfun-ai/Step-3.7-Flash",
   "name": "StepFun: Step 3.7 Flash",
   "created": 1779985069,
   "description": "Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...",
   "context_length": 262144,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000002",
    "completion": "0.00000115",
    "input_cache_read": "0.00000004"
   },
   "top_provider": {
    "context_length": 256000,
    "max_completion_tokens": 256000,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/stepfun/step-3.7-flash-20260528/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1170,
      "win_rate": 41.8,
      "rank": 60
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1187,
      "win_rate": 45.9,
      "rank": 26
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1202,
      "win_rate": 43.9,
      "rank": 53
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1192,
      "win_rate": 44.2,
      "rank": 55
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1190,
      "win_rate": 40.8,
      "rank": 55
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1114,
      "win_rate": 38.6,
      "rank": 56
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1199,
      "win_rate": 43.3,
      "rank": 54
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1211,
      "win_rate": 45.3,
      "rank": 50
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 30.9,
     "coding_index": 39.6,
     "agentic_index": 21.7
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "x-ai/grok-build-0.1",
   "canonical_slug": "x-ai/grok-build-0.1-20260520",
   "hugging_face_id": null,
   "name": "SpaceXAI: Grok Build 0.1",
   "created": 1779298123,
   "description": "Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...",
   "context_length": 256000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Grok",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000001",
    "completion": "0.000002",
    "web_search": "0.005",
    "input_cache_read": "0.0000002",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.000002",
      "completion": "0.000004",
      "input_cache_read": "0.0000004"
     }
    ]
   },
   "top_provider": {
    "context_length": 256000,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/x-ai/grok-build-0.1-20260520/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 40.7,
     "coding_index": 51.5,
     "agentic_index": 28.9
    }
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "google/gemini-3.5-flash",
   "canonical_slug": "google/gemini-3.5-flash-20260519",
   "hugging_face_id": null,
   "name": "Google: Gemini 3.5 Flash",
   "created": 1779193800,
   "description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "video",
     "file",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000015",
    "completion": "0.000009",
    "image": "0.0000015",
    "audio": "0.000003",
    "input_audio_cache": "0.0000003",
    "web_search": "0.014",
    "internal_reasoning": "0.000009",
    "input_cache_read": "0.00000015",
    "input_cache_write": "0.0000000833333333333333"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-01-01",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3.5-flash-20260519/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1187,
      "win_rate": 55.5,
      "rank": 10
     },
     {
      "arena": "agents",
      "category": "agentichtmlslides",
      "elo": 1162,
      "win_rate": 45.8,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "agenticslides",
      "elo": 1244,
      "win_rate": 57.5,
      "rank": 4
     },
     {
      "arena": "agents",
      "category": "agenticslides(html)",
      "elo": 1162,
      "win_rate": 45.7,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "agenticslides(python-pptx)",
      "elo": 1242,
      "win_rate": 57.8,
      "rank": 3
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1212,
      "win_rate": 58.1,
      "rank": 14
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1236,
      "win_rate": 58.3,
      "rank": 15
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1135,
      "win_rate": 42.9,
      "rank": 21
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1155,
      "win_rate": 47,
      "rank": 18
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1220,
      "win_rate": 52.9,
      "rank": 13
     },
     {
      "arena": "agents",
      "category": "pptxslides",
      "elo": 1244,
      "win_rate": 57.7,
      "rank": 3
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1247,
      "win_rate": 57.4,
      "rank": 9
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1239,
      "win_rate": 53.4,
      "rank": 16
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1289,
      "win_rate": 57.9,
      "rank": 22
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1291,
      "win_rate": 59.6,
      "rank": 8
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1287,
      "win_rate": 55.5,
      "rank": 22
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1258,
      "win_rate": 54.6,
      "rank": 27
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1301,
      "win_rate": 54.9,
      "rank": 17
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1292,
      "win_rate": 60.9,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1299,
      "win_rate": 56.2,
      "rank": 17
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1281,
      "win_rate": 54.8,
      "rank": 24
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 52,
     "coding_index": 70.1,
     "agentic_index": 39.7
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "google/gemini-3.5-flash:batch",
   "canonical_slug": "google/gemini-3.5-flash-20260519",
   "hugging_face_id": null,
   "name": "Google: Gemini 3.5 Flash (batch)",
   "created": 1779193800,
   "description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "video",
     "file",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000075",
    "completion": "0.0000045",
    "image": "0.00000075",
    "audio": "0.0000015",
    "input_audio_cache": "0.00000015",
    "web_search": "0.014",
    "internal_reasoning": "0.0000045",
    "input_cache_read": "0.000000075"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-01-01",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3.5-flash-20260519/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1187,
      "win_rate": 55.5,
      "rank": 10
     },
     {
      "arena": "agents",
      "category": "agentichtmlslides",
      "elo": 1162,
      "win_rate": 45.8,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "agenticslides",
      "elo": 1244,
      "win_rate": 57.5,
      "rank": 4
     },
     {
      "arena": "agents",
      "category": "agenticslides(html)",
      "elo": 1162,
      "win_rate": 45.7,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "agenticslides(python-pptx)",
      "elo": 1242,
      "win_rate": 57.8,
      "rank": 3
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1212,
      "win_rate": 58.1,
      "rank": 14
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1236,
      "win_rate": 58.3,
      "rank": 15
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1135,
      "win_rate": 42.9,
      "rank": 21
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1155,
      "win_rate": 47,
      "rank": 18
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1220,
      "win_rate": 52.9,
      "rank": 13
     },
     {
      "arena": "agents",
      "category": "pptxslides",
      "elo": 1244,
      "win_rate": 57.7,
      "rank": 3
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1247,
      "win_rate": 57.4,
      "rank": 9
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1239,
      "win_rate": 53.4,
      "rank": 16
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1289,
      "win_rate": 57.9,
      "rank": 22
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1291,
      "win_rate": 59.6,
      "rank": 8
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1287,
      "win_rate": 55.5,
      "rank": 22
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1258,
      "win_rate": 54.6,
      "rank": 27
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1301,
      "win_rate": 54.9,
      "rank": 17
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1292,
      "win_rate": 60.9,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1299,
      "win_rate": 56.2,
      "rank": 17
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1281,
      "win_rate": 54.8,
      "rank": 24
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 52,
     "coding_index": 70.1,
     "agentic_index": 39.7
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "anthropic/claude-opus-4.7-fast",
   "canonical_slug": "anthropic/claude-4.7-opus-fast-20260512",
   "hugging_face_id": null,
   "name": "Anthropic: Claude Opus 4.7 (Fast)",
   "created": 1778613011,
   "description": "Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Claude",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00003",
    "completion": "0.00015",
    "web_search": "0.01",
    "input_cache_read": "0.000003",
    "input_cache_write": "0.0000375",
    "input_cache_write_1h": "0.00006"
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "stop",
    "structured_outputs",
    "tool_choice",
    "tools",
    "verbosity"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/anthropic/claude-4.7-opus-fast-20260512/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": false,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "inclusionai/ring-2.6-1t",
   "canonical_slug": "inclusionai/ring-2.6-1t-20260508",
   "hugging_face_id": null,
   "name": "inclusionAI: Ring-2.6-1T",
   "created": 1778247440,
   "description": "Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...",
   "context_length": 262144,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000075",
    "completion": "0.000000625",
    "input_cache_read": "0.000000015"
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": "2026-08-24",
   "links": {
    "details": "/api/v1/models/inclusionai/ring-2.6-1t-20260508/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 31.7,
     "coding_index": 42.8,
     "agentic_index": 20.1
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "x-ai/grok-4.3",
   "canonical_slug": "x-ai/grok-4.3-20260430",
   "hugging_face_id": null,
   "name": "SpaceXAI: Grok 4.3",
   "created": 1777591821,
   "description": "Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Grok",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.0000025",
    "web_search": "0.005",
    "input_cache_read": "0.0000002",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.0000025",
      "completion": "0.000005",
      "input_cache_read": "0.0000004"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/x-ai/grok-4.3-20260430/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1010,
      "win_rate": 28.4,
      "rank": 19
     },
     {
      "arena": "agents",
      "category": "agentichtmlslides",
      "elo": 1066,
      "win_rate": 31.8,
      "rank": 10
     },
     {
      "arena": "agents",
      "category": "agenticslides",
      "elo": 1072,
      "win_rate": 31.9,
      "rank": 10
     },
     {
      "arena": "agents",
      "category": "agenticslides(html)",
      "elo": 1066,
      "win_rate": 31.7,
      "rank": 10
     },
     {
      "arena": "agents",
      "category": "agenticslides(python-pptx)",
      "elo": 1068,
      "win_rate": 32.4,
      "rank": 10
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 983,
      "win_rate": 22.2,
      "rank": 36
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1041,
      "win_rate": 29.3,
      "rank": 37
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1035,
      "win_rate": 31.2,
      "rank": 29
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1022,
      "win_rate": 28.9,
      "rank": 22
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1111,
      "win_rate": 36.6,
      "rank": 36
     },
     {
      "arena": "agents",
      "category": "pptxslides",
      "elo": 1071,
      "win_rate": 32.5,
      "rank": 9
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1072,
      "win_rate": 30.8,
      "rank": 21
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1166,
      "win_rate": 44.5,
      "rank": 25
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1170,
      "win_rate": 43.2,
      "rank": 59
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1172,
      "win_rate": 45.6,
      "rank": 37
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1211,
      "win_rate": 46.2,
      "rank": 47
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1203,
      "win_rate": 46.3,
      "rank": 49
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1209,
      "win_rate": 47.3,
      "rank": 46
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1125,
      "win_rate": 40.6,
      "rank": 53
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1220,
      "win_rate": 47,
      "rank": 44
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1213,
      "win_rate": 46,
      "rank": 49
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 37.9,
     "coding_index": 42.2,
     "agentic_index": 24.2
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "low"
   }
  },
  {
   "id": "~google/gemini-pro-latest",
   "canonical_slug": "~google/gemini-pro-latest",
   "alias_target": {
    "name": "Google: Gemini 3.1 Pro Preview",
    "slug": "google/gemini-3.1-pro-preview"
   },
   "hugging_face_id": null,
   "name": "Google Gemini Pro Latest",
   "created": 1777318451,
   "description": "This model always redirects to the latest model in the Google Gemini Pro family.",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "audio",
     "file",
     "image",
     "text",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Router",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000012",
    "image": "0.000002",
    "audio": "0.000002",
    "input_audio_cache": "0.0000002",
    "web_search": "0.014",
    "internal_reasoning": "0.000012",
    "input_cache_read": "0.0000002",
    "input_cache_write": "0.000000375",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.000004",
      "completion": "0.000018",
      "audio": "0.000004",
      "input_audio_cache": "0.0000004",
      "input_cache_read": "0.0000004"
     }
    ]
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/~google/gemini-pro-latest/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "~google/gemini-flash-latest",
   "canonical_slug": "~google/gemini-flash-latest",
   "alias_target": {
    "name": "Google: Gemini 3.7 Flash",
    "slug": "google/gemini-3.7-flash"
   },
   "hugging_face_id": null,
   "name": "Google Gemini Flash Latest",
   "created": 1777318398,
   "description": "This model always redirects to the latest model in the Google Gemini Flash family.",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "video",
     "file",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Router",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000375",
    "completion": "0.000001875",
    "image": "0.000000375",
    "audio": "0.000000375",
    "input_audio_cache": "0.0000000375",
    "web_search": "0.014",
    "internal_reasoning": "0.000001875",
    "input_cache_read": "0.0000000375",
    "input_cache_write": "0.0000000208333333333333"
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/~google/gemini-flash-latest/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "~openai/gpt-latest",
   "canonical_slug": "~openai/gpt-latest",
   "alias_target": {
    "name": "OpenAI: GPT-5.6 Sol",
    "slug": "openai/gpt-5.6-sol"
   },
   "hugging_face_id": null,
   "name": "OpenAI GPT Latest",
   "created": 1777318334,
   "description": "This model always redirects to the latest model in the OpenAI GPT family.",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Router",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000025",
    "completion": "0.000015",
    "web_search": "0.01",
    "input_cache_read": "0.00000025",
    "input_cache_write": "0.000003125",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.000005",
      "completion": "0.0000225",
      "input_cache_read": "0.0000005",
      "input_cache_write": "0.00000625"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2026-02-16",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/~openai/gpt-latest/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "max",
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "qwen/qwen3.5-plus-20260420",
   "canonical_slug": "qwen/qwen3.5-plus-20260420",
   "hugging_face_id": null,
   "name": "Qwen: Qwen3.5 Plus 2026-04-20",
   "created": 1777261368,
   "description": "Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000003",
    "completion": "0.0000018",
    "input_cache_write": "0.000000375",
    "overrides": [
     {
      "min_prompt_tokens": 256000,
      "prompt": "0.000000375",
      "completion": "0.00000225",
      "input_cache_write": "0.00000046875"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3.5-plus-20260420/endpoints"
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "qwen/qwen3.6-flash",
   "canonical_slug": "qwen/qwen3.6-flash",
   "hugging_face_id": null,
   "name": "Qwen: Qwen3.6 Flash",
   "created": 1777261362,
   "description": "Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000001875",
    "completion": "0.000001125",
    "input_cache_write": "0.000000234375",
    "overrides": [
     {
      "min_prompt_tokens": 256000,
      "prompt": "0.00000075",
      "completion": "0.000003",
      "input_cache_write": "0.0000009375"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3.6-flash/endpoints"
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "qwen/qwen3.6-max-preview",
   "canonical_slug": "qwen/qwen3.6-max-preview-20260420",
   "hugging_face_id": null,
   "name": "Qwen: Qwen3.6 Max Preview",
   "created": 1777260242,
   "description": "Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...",
   "context_length": 262144,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000001027",
    "completion": "0.000006162",
    "input_cache_write": "0.00000128375",
    "overrides": [
     {
      "min_prompt_tokens": 128000,
      "prompt": "0.00000158",
      "completion": "0.00000948",
      "input_cache_write": "0.000001975"
     }
    ]
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3.6-max-preview-20260420/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true
   }
  },
  {
   "id": "openai/gpt-5.5-pro",
   "canonical_slug": "openai/gpt-5.5-pro-20260423",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.5 Pro",
   "created": 1777051896,
   "description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00003",
    "completion": "0.00018",
    "web_search": "0.01",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.00006",
      "completion": "0.00027"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-12-01",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.5-pro-20260423/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.5-pro:batch",
   "canonical_slug": "openai/gpt-5.5-pro-20260423",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.5 Pro (batch)",
   "created": 1777051896,
   "description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000015",
    "completion": "0.00009",
    "web_search": "0.01",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.00003",
      "completion": "0.000135"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-12-01",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.5-pro-20260423/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.5",
   "canonical_slug": "openai/gpt-5.5-20260423",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.5",
   "created": 1777051893,
   "description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000005",
    "completion": "0.00003",
    "web_search": "0.01",
    "input_cache_read": "0.0000005",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.00001",
      "completion": "0.000045",
      "input_cache_read": "0.000001"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-12-01",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.5-20260423/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1186,
      "win_rate": 52.4,
      "rank": 12
     },
     {
      "arena": "agents",
      "category": "agentichtmlslides",
      "elo": 1084,
      "win_rate": 34.2,
      "rank": 9
     },
     {
      "arena": "agents",
      "category": "agenticslides",
      "elo": 1150,
      "win_rate": 43.5,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "agenticslides(html)",
      "elo": 1077,
      "win_rate": 33.2,
      "rank": 9
     },
     {
      "arena": "agents",
      "category": "agenticslides(python-pptx)",
      "elo": 1155,
      "win_rate": 45.2,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1189,
      "win_rate": 50.9,
      "rank": 20
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1123,
      "win_rate": 43,
      "rank": 26
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1212,
      "win_rate": 52.4,
      "rank": 10
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1078,
      "win_rate": 35.7,
      "rank": 21
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1201,
      "win_rate": 51.6,
      "rank": 20
     },
     {
      "arena": "agents",
      "category": "pptxslides",
      "elo": 1157,
      "win_rate": 45.3,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1152,
      "win_rate": 43.3,
      "rank": 19
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1152,
      "win_rate": 42.6,
      "rank": 28
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1242,
      "win_rate": 51.7,
      "rank": 36
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1287,
      "win_rate": 61.1,
      "rank": 9
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1284,
      "win_rate": 55.1,
      "rank": 24
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1280,
      "win_rate": 56.5,
      "rank": 19
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1336,
      "win_rate": 59.8,
      "rank": 8
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1272,
      "win_rate": 57.8,
      "rank": 7
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1281,
      "win_rate": 55.4,
      "rank": 25
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1276,
      "win_rate": 54.2,
      "rank": 26
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 56.3,
     "coding_index": 74.9,
     "agentic_index": 47.4
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.5:batch",
   "canonical_slug": "openai/gpt-5.5-20260423",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.5 (batch)",
   "created": 1777051893,
   "description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000025",
    "completion": "0.000015",
    "web_search": "0.01",
    "input_cache_read": "0.00000025",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.000005",
      "completion": "0.0000225",
      "input_cache_read": "0.0000005"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-12-01",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.5-20260423/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1186,
      "win_rate": 52.4,
      "rank": 12
     },
     {
      "arena": "agents",
      "category": "agentichtmlslides",
      "elo": 1084,
      "win_rate": 34.2,
      "rank": 9
     },
     {
      "arena": "agents",
      "category": "agenticslides",
      "elo": 1150,
      "win_rate": 43.5,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "agenticslides(html)",
      "elo": 1077,
      "win_rate": 33.2,
      "rank": 9
     },
     {
      "arena": "agents",
      "category": "agenticslides(python-pptx)",
      "elo": 1155,
      "win_rate": 45.2,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1189,
      "win_rate": 50.9,
      "rank": 20
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1123,
      "win_rate": 43,
      "rank": 26
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1212,
      "win_rate": 52.4,
      "rank": 10
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1078,
      "win_rate": 35.7,
      "rank": 21
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1201,
      "win_rate": 51.6,
      "rank": 20
     },
     {
      "arena": "agents",
      "category": "pptxslides",
      "elo": 1157,
      "win_rate": 45.3,
      "rank": 7
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1152,
      "win_rate": 43.3,
      "rank": 19
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1152,
      "win_rate": 42.6,
      "rank": 28
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1242,
      "win_rate": 51.7,
      "rank": 36
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1287,
      "win_rate": 61.1,
      "rank": 9
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1284,
      "win_rate": 55.1,
      "rank": 24
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1280,
      "win_rate": 56.5,
      "rank": 19
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1336,
      "win_rate": 59.8,
      "rank": 8
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1272,
      "win_rate": 57.8,
      "rank": 7
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1281,
      "win_rate": 55.4,
      "rank": 25
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1276,
      "win_rate": 54.2,
      "rank": 26
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 56.3,
     "coding_index": 74.9,
     "agentic_index": 47.4
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openrouter/pareto-code",
   "canonical_slug": "openrouter/pareto-code",
   "hugging_face_id": "",
   "name": "Pareto Code Router",
   "created": 1776747900,
   "description": "The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...",
   "context_length": 2000000,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Router",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "-1",
    "completion": "-1"
   },
   "top_provider": {
    "context_length": null,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openrouter/pareto-code/endpoints"
   }
  },
  {
   "id": "qwen/qwen3.6-plus",
   "canonical_slug": "qwen/qwen3.6-plus-04-02",
   "hugging_face_id": "",
   "name": "Qwen: Qwen3.6 Plus",
   "created": 1775133557,
   "description": "Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000325",
    "completion": "0.00000195",
    "input_cache_write": "0.00000040625",
    "overrides": [
     {
      "min_prompt_tokens": 256000,
      "prompt": "0.0000013",
      "completion": "0.0000039",
      "input_cache_write": "0.000001625"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3.6-plus-04-02/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1246,
      "win_rate": 51.4,
      "rank": 35
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1145,
      "win_rate": 42.6,
      "rank": 46
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1259,
      "win_rate": 51.6,
      "rank": 36
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1251,
      "win_rate": 51.4,
      "rank": 32
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1244,
      "win_rate": 50.4,
      "rank": 35
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1202,
      "win_rate": 51.6,
      "rank": 31
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1264,
      "win_rate": 52.5,
      "rank": 34
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1260,
      "win_rate": 51.6,
      "rank": 34
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 40.5,
     "coding_index": 54.5,
     "agentic_index": 29
    }
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "arcee-ai/trinity-large-thinking",
   "canonical_slug": "arcee-ai/trinity-large-thinking",
   "hugging_face_id": "arcee-ai/Trinity-Large-Thinking",
   "name": "Arcee AI: Trinity Large Thinking",
   "created": 1775058318,
   "description": "Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...",
   "context_length": 262144,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000022",
    "completion": "0.00000085",
    "input_cache_read": "0.00000006"
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 262144,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 0.3,
    "top_p": 0.8,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/arcee-ai/trinity-large-thinking/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1127,
      "win_rate": 41.3,
      "rank": 78
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1074,
      "win_rate": 37.1,
      "rank": 56
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1142,
      "win_rate": 40.1,
      "rank": 80
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1120,
      "win_rate": 39.3,
      "rank": 84
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1115,
      "win_rate": 38.4,
      "rank": 85
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1056,
      "win_rate": 35.2,
      "rank": 69
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1072,
      "win_rate": 32.6,
      "rank": 90
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1157,
      "win_rate": 41.3,
      "rank": 77
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 18.7,
     "coding_index": 25.8,
     "agentic_index": 3.7
    }
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "x-ai/grok-4.20-multi-agent",
   "canonical_slug": "x-ai/grok-4.20-multi-agent-20260309",
   "hugging_face_id": "",
   "name": "SpaceXAI: Grok 4.20 Multi-Agent",
   "created": 1774979158,
   "description": "Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...",
   "context_length": 2000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Grok",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.0000025",
    "web_search": "0.005",
    "input_cache_read": "0.0000002",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.0000025",
      "completion": "0.000005",
      "input_cache_read": "0.0000004"
     }
    ]
   },
   "top_provider": {
    "context_length": 2000000,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "temperature",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-09-01",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/x-ai/grok-4.20-multi-agent-20260309/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "x-ai/grok-4.20",
   "canonical_slug": "x-ai/grok-4.20-20260309",
   "hugging_face_id": "",
   "name": "SpaceXAI: Grok 4.20",
   "created": 1774979019,
   "description": "Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...",
   "context_length": 2000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Grok",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.0000025",
    "web_search": "0.005",
    "input_cache_read": "0.0000002",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.0000025",
      "completion": "0.000005",
      "input_cache_read": "0.0000004"
     }
    ]
   },
   "top_provider": {
    "context_length": 2000000,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-09-01",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/x-ai/grok-4.20-20260309/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1073,
      "win_rate": 35.1,
      "rank": 34
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1087,
      "win_rate": 41,
      "rank": 29
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1089,
      "win_rate": 38.5,
      "rank": 26
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1180,
      "win_rate": 45.7,
      "rank": 12
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1139,
      "win_rate": 45.4,
      "rank": 33
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1180,
      "win_rate": 49.6,
      "rank": 23
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1238,
      "win_rate": 52.8,
      "rank": 38
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1211,
      "win_rate": 48.6,
      "rank": 20
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1245,
      "win_rate": 52.7,
      "rank": 38
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1241,
      "win_rate": 52.7,
      "rank": 37
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1231,
      "win_rate": 51.6,
      "rank": 40
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1202,
      "win_rate": 53,
      "rank": 30
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1228,
      "win_rate": 50.1,
      "rank": 42
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1249,
      "win_rate": 52.8,
      "rank": 37
     }
    ]
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": false
   }
  },
  {
   "id": "minimax/minimax-m2.7",
   "canonical_slug": "minimax/minimax-m2.7-20260318",
   "hugging_face_id": "MiniMaxAI/MiniMax-M2.7",
   "name": "MiniMax: MiniMax M2.7",
   "created": 1773836697,
   "description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...",
   "context_length": 204800,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000003",
    "completion": "0.0000012",
    "input_cache_read": "0.00000006"
   },
   "top_provider": {
    "context_length": 204800,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 0.95,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/minimax/minimax-m2.7-20260318/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1239,
      "win_rate": 50.7,
      "rank": 37
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1172,
      "win_rate": 47.6,
      "rank": 36
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1259,
      "win_rate": 52.3,
      "rank": 34
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1252,
      "win_rate": 52.5,
      "rank": 30
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1243,
      "win_rate": 51.7,
      "rank": 36
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1177,
      "win_rate": 49.4,
      "rank": 41
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1237,
      "win_rate": 49.5,
      "rank": 40
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1266,
      "win_rate": 53,
      "rank": 32
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 38.9,
     "coding_index": 52.6,
     "agentic_index": 25.9
    }
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "bytedance-seed/seed-2.0-lite",
   "canonical_slug": "bytedance-seed/seed-2.0-lite-20260309",
   "hugging_face_id": null,
   "name": "ByteDance Seed: Seed-2.0-Lite",
   "created": 1773157231,
   "description": "Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...",
   "context_length": 262144,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000025",
    "completion": "0.000002",
    "overrides": [
     {
      "min_prompt_tokens": 128000,
      "prompt": "0.0000005",
      "completion": "0.000004"
     }
    ]
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/bytedance-seed/seed-2.0-lite-20260309/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.4-pro",
   "canonical_slug": "openai/gpt-5.4-pro-20260305",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.4 Pro",
   "created": 1772734366,
   "description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00003",
    "completion": "0.00018",
    "web_search": "0.01",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.00006",
      "completion": "0.00027"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.4-pro-20260305/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.4-pro:batch",
   "canonical_slug": "openai/gpt-5.4-pro-20260305",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.4 Pro (batch)",
   "created": 1772734366,
   "description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000015",
    "completion": "0.00009",
    "web_search": "0.01",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.00003",
      "completion": "0.000135"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.4-pro-20260305/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.4",
   "canonical_slug": "openai/gpt-5.4-20260305",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.4",
   "created": 1772734352,
   "description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000025",
    "completion": "0.000015",
    "web_search": "0.01",
    "input_cache_read": "0.00000025",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.000005",
      "completion": "0.0000225",
      "input_cache_read": "0.0000005"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.4-20260305/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1147,
      "win_rate": 42.4,
      "rank": 67
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1233,
      "win_rate": 55.5,
      "rank": 18
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1237,
      "win_rate": 52.5,
      "rank": 40
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1257,
      "win_rate": 56.6,
      "rank": 28
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1274,
      "win_rate": 57.6,
      "rank": 26
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1235,
      "win_rate": 57.8,
      "rank": 19
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1267,
      "win_rate": 57.4,
      "rank": 29
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1240,
      "win_rate": 52.5,
      "rank": 41
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1060,
      "win_rate": 47.4,
      "rank": 35
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1051,
      "win_rate": 40.8,
      "rank": 36
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1135,
      "win_rate": 46.9,
      "rank": 22
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1137,
      "win_rate": 46.1,
      "rank": 34
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1095,
      "win_rate": 40.3,
      "rank": 32
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 53.1,
     "coding_index": 71.1,
     "agentic_index": 44.2
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": false,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.4:batch",
   "canonical_slug": "openai/gpt-5.4-20260305",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.4 (batch)",
   "created": 1772734352,
   "description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...",
   "context_length": 1050000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.0000075",
    "web_search": "0.01",
    "input_cache_read": "0.000000125",
    "overrides": [
     {
      "min_prompt_tokens": 272000,
      "prompt": "0.0000025",
      "completion": "0.00001125",
      "input_cache_read": "0.00000025"
     }
    ]
   },
   "top_provider": {
    "context_length": 1050000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.4-20260305/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1147,
      "win_rate": 42.4,
      "rank": 67
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1233,
      "win_rate": 55.5,
      "rank": 18
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1237,
      "win_rate": 52.5,
      "rank": 40
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1257,
      "win_rate": 56.6,
      "rank": 28
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1274,
      "win_rate": 57.6,
      "rank": 26
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1235,
      "win_rate": 57.8,
      "rank": 19
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1267,
      "win_rate": 57.4,
      "rank": 29
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1240,
      "win_rate": 52.5,
      "rank": 41
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1060,
      "win_rate": 47.4,
      "rank": 35
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1051,
      "win_rate": 40.8,
      "rank": 36
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1135,
      "win_rate": 46.9,
      "rank": 22
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1137,
      "win_rate": 46.1,
      "rank": 34
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1095,
      "win_rate": 40.3,
      "rank": 32
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 53.1,
     "coding_index": 71.1,
     "agentic_index": 44.2
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": false,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "bytedance-seed/seed-2.0-mini",
   "canonical_slug": "bytedance-seed/seed-2.0-mini-20260224",
   "hugging_face_id": "",
   "name": "ByteDance Seed: Seed-2.0-Mini",
   "created": 1772131107,
   "description": "Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...",
   "context_length": 262144,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000001",
    "completion": "0.0000004",
    "overrides": [
     {
      "min_prompt_tokens": 128000,
      "prompt": "0.0000002",
      "completion": "0.0000008"
     }
    ]
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/bytedance-seed/seed-2.0-mini-20260224/endpoints"
   },
   "reasoning": {
    "mandatory": false,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "google/gemini-3.1-pro-preview-customtools",
   "canonical_slug": "google/gemini-3.1-pro-preview-customtools-20260219",
   "hugging_face_id": null,
   "name": "Google: Gemini 3.1 Pro Preview Custom Tools",
   "created": 1772045923,
   "description": "Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "audio",
     "image",
     "video",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000012",
    "image": "0.000002",
    "audio": "0.000002",
    "input_audio_cache": "0.0000002",
    "web_search": "0.014",
    "internal_reasoning": "0.000012",
    "input_cache_read": "0.0000002",
    "input_cache_write": "0.000000375",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.000004",
      "completion": "0.000018",
      "audio": "0.000004",
      "input_audio_cache": "0.0000004",
      "input_cache_read": "0.0000004"
     }
    ]
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3.1-pro-preview-customtools-20260219/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "aion-labs/aion-2.0",
   "canonical_slug": "aion-labs/aion-2.0-20260223",
   "hugging_face_id": null,
   "name": "AionLabs: Aion-2.0",
   "created": 1771881306,
   "description": "Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....",
   "context_length": 131072,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000008",
    "completion": "0.0000016",
    "input_cache_read": "0.0000002"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/aion-labs/aion-2.0-20260223/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "google/gemini-3.1-pro-preview",
   "canonical_slug": "google/gemini-3.1-pro-preview-20260219",
   "hugging_face_id": "",
   "name": "Google: Gemini 3.1 Pro Preview",
   "created": 1771509627,
   "description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "audio",
     "file",
     "image",
     "text",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000012",
    "image": "0.000002",
    "audio": "0.000002",
    "input_audio_cache": "0.0000002",
    "web_search": "0.014",
    "internal_reasoning": "0.000012",
    "input_cache_read": "0.0000002",
    "input_cache_write": "0.000000375",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.000004",
      "completion": "0.000018",
      "audio": "0.000004",
      "input_audio_cache": "0.0000004",
      "input_cache_read": "0.0000004"
     }
    ]
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3.1-pro-preview-20260219/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1122,
      "win_rate": 44.6,
      "rank": 17
     },
     {
      "arena": "agents",
      "category": "agentichtmlslides",
      "elo": 1226,
      "win_rate": 55.8,
      "rank": 5
     },
     {
      "arena": "agents",
      "category": "agenticslides",
      "elo": 1112,
      "win_rate": 33.8,
      "rank": 8
     },
     {
      "arena": "agents",
      "category": "agenticslides(html)",
      "elo": 1219,
      "win_rate": 54.4,
      "rank": 5
     },
     {
      "arena": "agents",
      "category": "agenticslides(python-pptx)",
      "elo": 1107,
      "win_rate": 33.9,
      "rank": 8
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1078,
      "win_rate": 41.4,
      "rank": 33
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1104,
      "win_rate": 42.4,
      "rank": 27
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1236,
      "win_rate": 60,
      "rank": 6
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1167,
      "win_rate": 49.1,
      "rank": 15
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1140,
      "win_rate": 44.1,
      "rank": 30
     },
     {
      "arena": "agents",
      "category": "pptxslides",
      "elo": 1110,
      "win_rate": 34.1,
      "rank": 8
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1109,
      "win_rate": 31.9,
      "rank": 20
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1162,
      "win_rate": 45.4,
      "rank": 26
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1280,
      "win_rate": 59.3,
      "rank": 26
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1305,
      "win_rate": 63.7,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1268,
      "win_rate": 64.4,
      "rank": 29
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1260,
      "win_rate": 61.8,
      "rank": 26
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1238,
      "win_rate": 53.4,
      "rank": 38
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1328,
      "win_rate": 68.5,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1307,
      "win_rate": 69.4,
      "rank": 14
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1272,
      "win_rate": 64.4,
      "rank": 27
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 47.7,
     "coding_index": 68.8,
     "agentic_index": 23
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "google/gemini-3.1-pro-preview:batch",
   "canonical_slug": "google/gemini-3.1-pro-preview-20260219",
   "hugging_face_id": "",
   "name": "Google: Gemini 3.1 Pro Preview (batch)",
   "created": 1771509627,
   "description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "audio",
     "file",
     "image",
     "text",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000001",
    "completion": "0.000006",
    "image": "0.000001",
    "audio": "0.000001",
    "web_search": "0.014",
    "internal_reasoning": "0.000006",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.000002",
      "completion": "0.000009",
      "audio": "0.000002"
     }
    ]
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3.1-pro-preview-20260219/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "agenticgamedev",
      "elo": 1122,
      "win_rate": 44.6,
      "rank": 17
     },
     {
      "arena": "agents",
      "category": "agentichtmlslides",
      "elo": 1226,
      "win_rate": 55.8,
      "rank": 5
     },
     {
      "arena": "agents",
      "category": "agenticslides",
      "elo": 1112,
      "win_rate": 33.8,
      "rank": 8
     },
     {
      "arena": "agents",
      "category": "agenticslides(html)",
      "elo": 1219,
      "win_rate": 54.4,
      "rank": 5
     },
     {
      "arena": "agents",
      "category": "agenticslides(python-pptx)",
      "elo": 1107,
      "win_rate": 33.9,
      "rank": 8
     },
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1078,
      "win_rate": 41.4,
      "rank": 33
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1104,
      "win_rate": 42.4,
      "rank": 27
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1236,
      "win_rate": 60,
      "rank": 6
     },
     {
      "arena": "agents",
      "category": "htmlslides",
      "elo": 1167,
      "win_rate": 49.1,
      "rank": 15
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1140,
      "win_rate": 44.1,
      "rank": 30
     },
     {
      "arena": "agents",
      "category": "pptxslides",
      "elo": 1110,
      "win_rate": 34.1,
      "rank": 8
     },
     {
      "arena": "agents",
      "category": "python-pptxslides",
      "elo": 1109,
      "win_rate": 31.9,
      "rank": 20
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1162,
      "win_rate": 45.4,
      "rank": 26
     },
     {
      "arena": "models",
      "category": "3d",
      "elo": 1280,
      "win_rate": 59.3,
      "rank": 26
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1305,
      "win_rate": 63.7,
      "rank": 5
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1268,
      "win_rate": 64.4,
      "rank": 29
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1260,
      "win_rate": 61.8,
      "rank": 26
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1238,
      "win_rate": 53.4,
      "rank": 38
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1328,
      "win_rate": 68.5,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1307,
      "win_rate": 69.4,
      "rank": 14
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1272,
      "win_rate": 64.4,
      "rank": 27
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 47.7,
     "coding_index": 68.8,
     "agentic_index": 23
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "qwen/qwen3.5-plus-02-15",
   "canonical_slug": "qwen/qwen3.5-plus-20260216",
   "hugging_face_id": "",
   "name": "Qwen: Qwen3.5 Plus 2026-02-15",
   "created": 1771229416,
   "description": "The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "text",
     "image",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000026",
    "completion": "0.00000156",
    "overrides": [
     {
      "min_prompt_tokens": 256000,
      "prompt": "0.000000325",
      "completion": "0.00000195"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3.5-plus-20260216/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1165,
      "win_rate": 47.7,
      "rank": 64
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1127,
      "win_rate": 43.2,
      "rank": 51
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1191,
      "win_rate": 48.5,
      "rank": 60
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1158,
      "win_rate": 44.9,
      "rank": 70
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1141,
      "win_rate": 42.6,
      "rank": 73
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1148,
      "win_rate": 48.9,
      "rank": 48
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1204,
      "win_rate": 52.2,
      "rank": 51
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1207,
      "win_rate": 50,
      "rank": 56
     }
    ]
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "minimax/minimax-m2.5",
   "canonical_slug": "minimax/minimax-m2.5-20260211",
   "hugging_face_id": "MiniMaxAI/MiniMax-M2.5",
   "name": "MiniMax: MiniMax M2.5",
   "created": 1770908502,
   "description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...",
   "context_length": 204800,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000027",
    "completion": "0.00000095",
    "input_cache_read": "0.00000003"
   },
   "top_provider": {
    "context_length": 198000,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 0.95,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/minimax/minimax-m2.5-20260211/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1216,
      "win_rate": 57.6,
      "rank": 43
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1232,
      "win_rate": 56.8,
      "rank": 41
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1194,
      "win_rate": 51.2,
      "rank": 54
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1212,
      "win_rate": 55.5,
      "rank": 45
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1191,
      "win_rate": 54.5,
      "rank": 35
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1199,
      "win_rate": 53.4,
      "rank": 53
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1242,
      "win_rate": 57.5,
      "rank": 40
     }
    ]
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "qwen/qwen3-max-thinking",
   "canonical_slug": "qwen/qwen3-max-thinking-20260123",
   "hugging_face_id": null,
   "name": "Qwen: Qwen3 Max Thinking",
   "created": 1770671901,
   "description": "Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...",
   "context_length": 262144,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000078",
    "completion": "0.0000039",
    "overrides": [
     {
      "min_prompt_tokens": 32000,
      "prompt": "0.00000156",
      "completion": "0.0000078"
     },
     {
      "min_prompt_tokens": 128000,
      "prompt": "0.00000195",
      "completion": "0.00000975"
     }
    ]
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3-max-thinking-20260123/endpoints"
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "stepfun/step-3.5-flash",
   "canonical_slug": "stepfun/step-3.5-flash",
   "hugging_face_id": "stepfun-ai/Step-3.5-Flash",
   "name": "StepFun: Step 3.5 Flash",
   "created": 1769728337,
   "description": "Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....",
   "context_length": 262144,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000001",
    "completion": "0.0000003"
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/stepfun/step-3.5-flash/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openai/gpt-5.2-codex",
   "canonical_slug": "openai/gpt-5.2-codex-20260114",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.2-Codex",
   "created": 1768409315,
   "description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000175",
    "completion": "0.000014",
    "web_search": "0.01",
    "input_cache_read": "0.000000175"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.2-codex-20260114/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "androidnative",
      "elo": 1176,
      "win_rate": 47.5,
      "rank": 23
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1026,
      "win_rate": 37.2,
      "rank": 38
     },
     {
      "arena": "agents",
      "category": "godotgamedev",
      "elo": 1142,
      "win_rate": 47.8,
      "rank": 19
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1139,
      "win_rate": 46.6,
      "rank": 32
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1087,
      "win_rate": 39.7,
      "rank": 33
     }
    ]
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "bytedance-seed/seed-1.6-flash",
   "canonical_slug": "bytedance-seed/seed-1.6-flash-20250625",
   "hugging_face_id": "",
   "name": "ByteDance Seed: Seed 1.6 Flash",
   "created": 1766505011,
   "description": "Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...",
   "context_length": 262144,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "image",
     "text",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000075",
    "completion": "0.0000003",
    "overrides": [
     {
      "min_prompt_tokens": 128000,
      "prompt": "0.0000001",
      "completion": "0.0000008"
     }
    ]
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/bytedance-seed/seed-1.6-flash-20250625/endpoints"
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "bytedance-seed/seed-1.6",
   "canonical_slug": "bytedance-seed/seed-1.6-20250625",
   "hugging_face_id": "",
   "name": "ByteDance Seed: Seed 1.6",
   "created": 1766504997,
   "description": "Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.",
   "context_length": 262144,
   "architecture": {
    "modality": "text+image+video->text",
    "input_modalities": [
     "image",
     "text",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000025",
    "completion": "0.000002",
    "overrides": [
     {
      "min_prompt_tokens": 128000,
      "prompt": "0.0000005",
      "completion": "0.000004"
     }
    ]
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/bytedance-seed/seed-1.6-20250625/endpoints"
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "minimax/minimax-m2.1",
   "canonical_slug": "minimax/minimax-m2.1",
   "hugging_face_id": "MiniMaxAI/MiniMax-M2.1",
   "name": "MiniMax: MiniMax M2.1",
   "created": 1766454997,
   "description": "MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...",
   "context_length": 204800,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000003",
    "completion": "0.0000012",
    "input_cache_read": "0.00000003"
   },
   "top_provider": {
    "context_length": 204800,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 0.9,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/minimax/minimax-m2.1/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1211,
      "win_rate": 57.5,
      "rank": 45
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1215,
      "win_rate": 55.3,
      "rank": 45
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1228,
      "win_rate": 57,
      "rank": 41
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1170,
      "win_rate": 50.4,
      "rank": 64
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1172,
      "win_rate": 55.4,
      "rank": 43
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1250,
      "win_rate": 60.9,
      "rank": 36
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1221,
      "win_rate": 55.4,
      "rank": 45
     }
    ]
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openai/gpt-5.2-pro",
   "canonical_slug": "openai/gpt-5.2-pro-20251211",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.2 Pro",
   "created": 1765389780,
   "description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "image",
     "text",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000021",
    "completion": "0.000168",
    "web_search": "0.01"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.2-pro-20251211/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5.2-pro:batch",
   "canonical_slug": "openai/gpt-5.2-pro-20251211",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.2 Pro (batch)",
   "created": 1765389780,
   "description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "image",
     "text",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000105",
    "completion": "0.000084",
    "web_search": "0.01"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.2-pro-20251211/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openrouter/bodybuilder",
   "canonical_slug": "openrouter/bodybuilder",
   "hugging_face_id": "",
   "name": "Body Builder (beta)",
   "created": 1764903653,
   "description": "Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...",
   "context_length": 128000,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Router",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "-1",
    "completion": "-1"
   },
   "top_provider": {
    "context_length": null,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openrouter/bodybuilder/endpoints"
   }
  },
  {
   "id": "openai/gpt-5.1-codex-max",
   "canonical_slug": "openai/gpt-5.1-codex-max-20251204",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.1-Codex-Max",
   "created": 1764878934,
   "description": "GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.00001",
    "web_search": "0.01",
    "input_cache_read": "0.000000125"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.1-codex-max-20251204/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "xhigh",
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "deepseek/deepseek-v3.2",
   "canonical_slug": "deepseek/deepseek-v3.2-20251201",
   "hugging_face_id": "deepseek-ai/DeepSeek-V3.2",
   "name": "DeepSeek: DeepSeek V3.2",
   "created": 1764594642,
   "description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...",
   "context_length": 163840,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "DeepSeek",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000269",
    "completion": "0.0000004",
    "input_cache_read": "0.0000001345"
   },
   "top_provider": {
    "context_length": 163840,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 0.95,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/deepseek/deepseek-v3.2-20251201/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1179,
      "win_rate": 49.5,
      "rank": 55
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1116,
      "win_rate": 40.5,
      "rank": 53
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1189,
      "win_rate": 49.3,
      "rank": 63
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1180,
      "win_rate": 48.1,
      "rank": 62
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1167,
      "win_rate": 46.6,
      "rank": 66
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1073,
      "win_rate": 40.8,
      "rank": 64
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1176,
      "win_rate": 46.8,
      "rank": 63
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1195,
      "win_rate": 50.2,
      "rank": 61
     }
    ],
    "artificial_analysis": {
     "intelligence_index": null,
     "coding_index": 44.2,
     "agentic_index": null
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": false
   }
  },
  {
   "id": "allenai/olmo-3-32b-think",
   "canonical_slug": "allenai/olmo-3-32b-think-20251121",
   "hugging_face_id": "allenai/Olmo-3-32B-Think",
   "name": "AllenAI: Olmo 3 32B Think",
   "created": 1763758276,
   "description": "Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...",
   "context_length": 65536,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000015",
    "completion": "0.0000005"
   },
   "top_provider": {
    "context_length": 65536,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 0.6,
    "top_p": 0.95,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/allenai/olmo-3-32b-think-20251121/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "google/gemini-3-pro-image-preview",
   "canonical_slug": "google/gemini-3-pro-image-preview-20251120",
   "hugging_face_id": "",
   "name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)",
   "created": 1763653797,
   "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...",
   "context_length": 65536,
   "architecture": {
    "modality": "text+image->text+image",
    "input_modalities": [
     "image",
     "text"
    ],
    "output_modalities": [
     "image",
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000002",
    "completion": "0.000012",
    "image": "0.000002",
    "image_output": "0.00012",
    "audio": "0.000002",
    "input_audio_cache": "0.0000002",
    "web_search": "0.014",
    "internal_reasoning": "0.000012",
    "input_cache_read": "0.0000002",
    "input_cache_write": "0.000000375"
   },
   "top_provider": {
    "context_length": 65536,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-3-pro-image-preview-20251120/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "graphicdesign",
      "elo": 1276,
      "win_rate": 65.8,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "image",
      "elo": 1263,
      "win_rate": 62.1,
      "rank": 3
     },
     {
      "arena": "models",
      "category": "logo",
      "elo": 1253,
      "win_rate": 61,
      "rank": 4
     },
     {
      "arena": "models",
      "category": "imageediting",
      "elo": 1276,
      "win_rate": 66,
      "rank": 2
     }
    ]
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openai/gpt-5.1",
   "canonical_slug": "openai/gpt-5.1-20251113",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.1",
   "created": 1763060305,
   "description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "image",
     "text",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.00001",
    "web_search": "0.01",
    "input_cache_read": "0.000000125"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.1-20251113/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1107,
      "win_rate": 43.7,
      "rank": 86
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1152,
      "win_rate": 48.6,
      "rank": 45
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1195,
      "win_rate": 53,
      "rank": 57
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1226,
      "win_rate": 58,
      "rank": 42
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1215,
      "win_rate": 55.9,
      "rank": 44
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1190,
      "win_rate": 57.4,
      "rank": 36
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1193,
      "win_rate": 52.9,
      "rank": 57
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1207,
      "win_rate": 54,
      "rank": 55
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 37.5,
     "coding_index": 49.4,
     "agentic_index": 21.6
    }
   },
   "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "none"
    ],
    "default_effort": "none"
   }
  },
  {
   "id": "openai/gpt-5.1-codex",
   "canonical_slug": "openai/gpt-5.1-codex-20251113",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5.1-Codex",
   "created": 1763060298,
   "description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.00001",
    "web_search": "0.01",
    "input_cache_read": "0.00000013"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5.1-codex-20251113/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1086,
      "win_rate": 44.5,
      "rank": 30
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1191,
      "win_rate": 53.4,
      "rank": 23
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1055,
      "win_rate": 44,
      "rank": 35
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1177,
      "win_rate": 54.6,
      "rank": 66
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1235,
      "win_rate": 55.9,
      "rank": 39
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1174,
      "win_rate": 50.5,
      "rank": 61
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1264,
      "win_rate": 60,
      "rank": 32
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1182,
      "win_rate": 56.1,
      "rank": 68
     }
    ]
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "moonshotai/kimi-k2-thinking",
   "canonical_slug": "moonshotai/kimi-k2-thinking-20251106",
   "hugging_face_id": "moonshotai/Kimi-K2-Thinking",
   "name": "MoonshotAI: Kimi K2 Thinking",
   "created": 1762440622,
   "description": "Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...",
   "context_length": 262144,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000006",
    "completion": "0.0000025",
    "input_cache_read": "0.00000015"
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 100352,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/moonshotai/kimi-k2-thinking-20251106/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "website",
      "elo": 1133,
      "win_rate": 48.8,
      "rank": 87
     }
    ],
    "artificial_analysis": {
     "intelligence_index": null,
     "coding_index": 21,
     "agentic_index": null
    }
   },
   "reasoning": {
    "mandatory": true,
    "default_enabled": true
   }
  },
  {
   "id": "perplexity/sonar-pro-search",
   "canonical_slug": "perplexity/sonar-pro-search",
   "hugging_face_id": "",
   "name": "Perplexity: Sonar Pro Search",
   "created": 1761854366,
   "description": "Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...",
   "context_length": 200000,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000003",
    "completion": "0.000015",
    "web_search": "0.018"
   },
   "top_provider": {
    "context_length": 200000,
    "max_completion_tokens": 8000,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "structured_outputs",
    "temperature",
    "top_k",
    "top_p",
    "web_search_options"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/perplexity/sonar-pro-search/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openai/gpt-oss-safeguard-20b",
   "canonical_slug": "openai/gpt-oss-safeguard-20b",
   "hugging_face_id": "openai/gpt-oss-safeguard-20b",
   "name": "OpenAI: gpt-oss-safeguard-20b",
   "created": 1761752836,
   "description": "gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...",
   "context_length": 131072,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000075",
    "completion": "0.0000003",
    "input_cache_read": "0.0000000375"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-oss-safeguard-20b/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "minimax/minimax-m2",
   "canonical_slug": "minimax/minimax-m2",
   "hugging_face_id": "MiniMaxAI/MiniMax-M2",
   "name": "MiniMax: MiniMax M2",
   "created": 1761252093,
   "description": "MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...",
   "context_length": 204800,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000255",
    "completion": "0.00000102"
   },
   "top_provider": {
    "context_length": 204800,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 0.95,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/minimax/minimax-m2/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1143,
      "win_rate": 48.3,
      "rank": 70
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1160,
      "win_rate": 48.1,
      "rank": 74
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1162,
      "win_rate": 50,
      "rank": 68
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1154,
      "win_rate": 48.1,
      "rank": 69
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1141,
      "win_rate": 55.3,
      "rank": 50
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1163,
      "win_rate": 49.2,
      "rank": 69
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1162,
      "win_rate": 48,
      "rank": 74
     }
    ]
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openai/gpt-5-image-mini",
   "canonical_slug": "openai/gpt-5-image-mini",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5 Image Mini",
   "created": 1760624583,
   "description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text+image",
    "input_modalities": [
     "file",
     "image",
     "text"
    ],
    "output_modalities": [
     "image",
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000025",
    "completion": "0.000002",
    "image_output": "0.000008",
    "web_search": "0.01",
    "input_cache_read": "0.00000025"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5-image-mini/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "graphicdesign",
      "elo": 1190,
      "win_rate": 47.7,
      "rank": 9
     },
     {
      "arena": "models",
      "category": "image",
      "elo": 1203,
      "win_rate": 51,
      "rank": 9
     },
     {
      "arena": "models",
      "category": "logo",
      "elo": 1220,
      "win_rate": 51.4,
      "rank": 6
     }
    ]
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "qwen/qwen3-vl-8b-thinking",
   "canonical_slug": "qwen/qwen3-vl-8b-thinking",
   "hugging_face_id": "Qwen/Qwen3-VL-8B-Thinking",
   "name": "Qwen: Qwen3 VL 8B Thinking",
   "created": 1760463746,
   "description": "Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...",
   "context_length": 131072,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "image",
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000018",
    "completion": "0.0000021"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 0.95
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3-vl-8b-thinking/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openai/gpt-5-image",
   "canonical_slug": "openai/gpt-5-image",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5 Image",
   "created": 1760447986,
   "description": "[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text+image",
    "input_modalities": [
     "image",
     "text",
     "file"
    ],
    "output_modalities": [
     "image",
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00001",
    "completion": "0.00001",
    "image_output": "0.00004",
    "web_search": "0.01",
    "input_cache_read": "0.00000125"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5-image/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "graphicdesign",
      "elo": 1197,
      "win_rate": 48.9,
      "rank": 7
     },
     {
      "arena": "models",
      "category": "image",
      "elo": 1211,
      "win_rate": 53.9,
      "rank": 7
     },
     {
      "arena": "models",
      "category": "logo",
      "elo": 1214,
      "win_rate": 52.7,
      "rank": 7
     }
    ]
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "qwen/qwen3-vl-30b-a3b-thinking",
   "canonical_slug": "qwen/qwen3-vl-30b-a3b-thinking",
   "hugging_face_id": "Qwen/Qwen3-VL-30B-A3B-Thinking",
   "name": "Qwen: Qwen3 VL 30B A3B Thinking",
   "created": 1759794479,
   "description": "Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...",
   "context_length": 262144,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000002",
    "completion": "0.0000024"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 0.8,
    "top_p": 0.95,
    "top_k": 20,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": 1
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-03-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3-vl-30b-a3b-thinking/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openai/gpt-5-pro",
   "canonical_slug": "openai/gpt-5-pro-2025-10-06",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5 Pro",
   "created": 1759776663,
   "description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "image",
     "text",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000015",
    "completion": "0.00012",
    "web_search": "0.01"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-09-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5-pro-2025-10-06/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "openai/gpt-5-pro:batch",
   "canonical_slug": "openai/gpt-5-pro-2025-10-06",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5 Pro (batch)",
   "created": 1759776663,
   "description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "image",
     "text",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000075",
    "completion": "0.00006",
    "web_search": "0.01"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-09-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5-pro-2025-10-06/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "anthropic/claude-sonnet-4.5",
   "canonical_slug": "anthropic/claude-4.5-sonnet-20250929",
   "hugging_face_id": "",
   "name": "Anthropic: Claude Sonnet 4.5",
   "created": 1759161676,
   "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Claude",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000003",
    "completion": "0.000015",
    "web_search": "0.01",
    "input_cache_read": "0.0000003",
    "input_cache_write": "0.00000375",
    "input_cache_write_1h": "0.000006",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.000006",
      "completion": "0.0000225",
      "input_cache_read": "0.0000006",
      "input_cache_write": "0.0000075",
      "input_cache_write_1h": "0.000012"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 64000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "response_format",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 1,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-01-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1203,
      "win_rate": 51,
      "rank": 47
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1237,
      "win_rate": 56.1,
      "rank": 17
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1207,
      "win_rate": 51.5,
      "rank": 48
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1189,
      "win_rate": 47.3,
      "rank": 56
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1202,
      "win_rate": 51.1,
      "rank": 50
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1155,
      "win_rate": 52.2,
      "rank": 46
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1199,
      "win_rate": 49.4,
      "rank": 52
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1210,
      "win_rate": 51.8,
      "rank": 51
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1084,
      "win_rate": 43.7,
      "rank": 31
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1187,
      "win_rate": 52.9,
      "rank": 24
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1096,
      "win_rate": 43.2,
      "rank": 31
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 37.4,
     "coding_index": 52.1,
     "agentic_index": 26.4
    }
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "anthropic/claude-sonnet-4.5:batch",
   "canonical_slug": "anthropic/claude-4.5-sonnet-20250929",
   "hugging_face_id": "",
   "name": "Anthropic: Claude Sonnet 4.5 (batch)",
   "created": 1759161676,
   "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Claude",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000015",
    "completion": "0.0000075",
    "web_search": "0.01",
    "input_cache_read": "0.00000015",
    "input_cache_write": "0.000001875",
    "input_cache_write_1h": "0.000003",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.000003",
      "completion": "0.00001125",
      "input_cache_read": "0.0000003",
      "input_cache_write": "0.00000375",
      "input_cache_write_1h": "0.000006"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 64000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 1,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-01-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1203,
      "win_rate": 51,
      "rank": 47
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1237,
      "win_rate": 56.1,
      "rank": 17
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1207,
      "win_rate": 51.5,
      "rank": 48
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1189,
      "win_rate": 47.3,
      "rank": 56
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1202,
      "win_rate": 51.1,
      "rank": 50
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1155,
      "win_rate": 52.2,
      "rank": 46
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1199,
      "win_rate": 49.4,
      "rank": 52
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1210,
      "win_rate": 51.8,
      "rank": 51
     },
     {
      "arena": "agents",
      "category": "fullstack",
      "elo": 1084,
      "win_rate": 43.7,
      "rank": 31
     },
     {
      "arena": "agents",
      "category": "mobileapps",
      "elo": 1187,
      "win_rate": 52.9,
      "rank": 24
     },
     {
      "arena": "agents",
      "category": "webapps",
      "elo": 1096,
      "win_rate": 43.2,
      "rank": 31
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 37.4,
     "coding_index": 52.1,
     "agentic_index": 26.4
    }
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "qwen/qwen3-vl-235b-a22b-thinking",
   "canonical_slug": "qwen/qwen3-vl-235b-a22b-thinking",
   "hugging_face_id": "Qwen/Qwen3-VL-235B-A22B-Thinking",
   "name": "Qwen: Qwen3 VL 235B A22B Thinking",
   "created": 1758668690,
   "description": "Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....",
   "context_length": 131072,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000004",
    "completion": "0.000004"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 0.8,
    "top_p": 0.95,
    "top_k": 20,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": 1
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-03-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3-vl-235b-a22b-thinking/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "qwen/qwen3-max",
   "canonical_slug": "qwen/qwen3-max",
   "hugging_face_id": "",
   "name": "Qwen: Qwen3 Max",
   "created": 1758662808,
   "description": "Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...",
   "context_length": 262144,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000078",
    "completion": "0.0000039",
    "input_cache_read": "0.000000156",
    "input_cache_write": "0.000000975",
    "overrides": [
     {
      "min_prompt_tokens": 32000,
      "prompt": "0.00000156",
      "completion": "0.0000078",
      "input_cache_read": "0.000000312",
      "input_cache_write": "0.00000195"
     },
     {
      "min_prompt_tokens": 128000,
      "prompt": "0.00000195",
      "completion": "0.00000975",
      "input_cache_read": "0.00000039",
      "input_cache_write": "0.0000024375"
     }
    ]
   },
   "top_provider": {
    "context_length": 262144,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": 1,
    "top_p": 1,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-06-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3-max/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1119,
      "win_rate": 43.5,
      "rank": 82
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1161,
      "win_rate": 47.2,
      "rank": 41
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1134,
      "win_rate": 44,
      "rank": 84
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1122,
      "win_rate": 41.2,
      "rank": 83
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1130,
      "win_rate": 43.9,
      "rank": 80
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1052,
      "win_rate": 37.3,
      "rank": 70
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1105,
      "win_rate": 40.2,
      "rank": 85
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1139,
      "win_rate": 44.5,
      "rank": 85
     }
    ]
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "qwen/qwen3-coder-plus",
   "canonical_slug": "qwen/qwen3-coder-plus",
   "hugging_face_id": "",
   "name": "Qwen: Qwen3 Coder Plus",
   "created": 1758662707,
   "description": "Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000065",
    "completion": "0.00000325",
    "input_cache_read": "0.00000013",
    "input_cache_write": "0.0000008125",
    "overrides": [
     {
      "min_prompt_tokens": 32000,
      "prompt": "0.00000117",
      "completion": "0.00000585",
      "input_cache_read": "0.000000234",
      "input_cache_write": "0.0000014625"
     },
     {
      "min_prompt_tokens": 128000,
      "prompt": "0.00000195",
      "completion": "0.00000975",
      "input_cache_read": "0.00000039",
      "input_cache_write": "0.0000024375"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-06-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3-coder-plus/endpoints"
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "openai/gpt-5-codex:batch",
   "canonical_slug": "openai/gpt-5-codex",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5 Codex (batch)",
   "created": 1758643403,
   "description": "GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
     "text",
     "image"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000625",
    "completion": "0.000005",
    "web_search": "0.01",
    "input_cache_read": "0.0000000625"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-09-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5-codex/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "qwen/qwen3-coder-flash",
   "canonical_slug": "qwen/qwen3-coder-flash",
   "hugging_face_id": "",
   "name": "Qwen: Qwen3 Coder Flash",
   "created": 1758115536,
   "description": "Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000195",
    "completion": "0.000000975",
    "input_cache_read": "0.000000039",
    "input_cache_write": "0.00000024375",
    "overrides": [
     {
      "min_prompt_tokens": 32000,
      "prompt": "0.000000325",
      "completion": "0.000001625",
      "input_cache_read": "0.000000065",
      "input_cache_write": "0.00000040625"
     },
     {
      "min_prompt_tokens": 128000,
      "prompt": "0.00000052",
      "completion": "0.0000026",
      "input_cache_read": "0.000000104",
      "input_cache_write": "0.00000065"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "response_format",
    "seed",
    "stop",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-06-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3-coder-flash/endpoints"
   }
  },
  {
   "id": "qwen/qwen3-next-80b-a3b-thinking",
   "canonical_slug": "qwen/qwen3-next-80b-a3b-thinking-2509",
   "hugging_face_id": "Qwen/Qwen3-Next-80B-A3B-Thinking",
   "name": "Qwen: Qwen3 Next 80B A3B Thinking",
   "created": 1757612284,
   "description": "Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...",
   "context_length": 262144,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000015",
    "completion": "0.0000012"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-09-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3-next-80b-a3b-thinking-2509/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 16.9,
     "coding_index": 17.4,
     "agentic_index": 2.1
    }
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "qwen/qwen-plus-2025-07-28",
   "canonical_slug": "qwen/qwen-plus-2025-07-28",
   "hugging_face_id": "",
   "name": "Qwen: Qwen Plus 0728",
   "created": 1757347599,
   "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.",
   "context_length": 1000000,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000026",
    "completion": "0.00000078",
    "overrides": [
     {
      "min_prompt_tokens": 256000,
      "prompt": "0.00000078",
      "completion": "0.00000234"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-03-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints"
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "qwen/qwen-plus-2025-07-28:thinking",
   "canonical_slug": "qwen/qwen-plus-2025-07-28",
   "hugging_face_id": "",
   "name": "Qwen: Qwen Plus 0728 (thinking)",
   "created": 1757347599,
   "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.",
   "context_length": 1000000,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000026",
    "completion": "0.00000078",
    "overrides": [
     {
      "min_prompt_tokens": 256000,
      "prompt": "0.00000078",
      "completion": "0.00000234"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-03-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints"
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "qwen/qwen3-30b-a3b-thinking-2507",
   "canonical_slug": "qwen/qwen3-30b-a3b-thinking-2507",
   "hugging_face_id": "Qwen/Qwen3-30B-A3B-Thinking-2507",
   "name": "Qwen: Qwen3 30B A3B Thinking 2507",
   "created": 1756399192,
   "description": "Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...",
   "context_length": 81920,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000002",
    "completion": "0.0000024"
   },
   "top_provider": {
    "context_length": 81920,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": "2025-06-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3-30b-a3b-thinking-2507/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 946,
      "win_rate": 33.3,
      "rank": 110
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 950,
      "win_rate": 35.5,
      "rank": 118
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 14.6,
     "coding_index": 12.1,
     "agentic_index": 1.8
    }
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openai/gpt-5",
   "canonical_slug": "openai/gpt-5-2025-08-07",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5",
   "created": 1754587413,
   "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.00001",
    "web_search": "0.01",
    "input_cache_read": "0.000000125"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-09-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5-2025-08-07/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1101,
      "win_rate": 41.3,
      "rank": 87
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1174,
      "win_rate": 49,
      "rank": 34
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1192,
      "win_rate": 54.5,
      "rank": 59
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1243,
      "win_rate": 60.5,
      "rank": 36
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1221,
      "win_rate": 59.3,
      "rank": 43
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1229,
      "win_rate": 64.1,
      "rank": 21
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1206,
      "win_rate": 57.4,
      "rank": 49
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1204,
      "win_rate": 53.7,
      "rank": 57
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 35.3,
     "coding_index": 37.8,
     "agentic_index": 26.5
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5:batch",
   "canonical_slug": "openai/gpt-5-2025-08-07",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5 (batch)",
   "created": 1754587413,
   "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000625",
    "completion": "0.000005",
    "web_search": "0.01",
    "input_cache_read": "0.0000000625"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-09-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5-2025-08-07/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1101,
      "win_rate": 41.3,
      "rank": 87
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1174,
      "win_rate": 49,
      "rank": 34
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1192,
      "win_rate": 54.5,
      "rank": 59
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1243,
      "win_rate": 60.5,
      "rank": 36
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1221,
      "win_rate": 59.3,
      "rank": 43
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1229,
      "win_rate": 64.1,
      "rank": 21
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1206,
      "win_rate": 57.4,
      "rank": 49
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1204,
      "win_rate": 53.7,
      "rank": 57
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 35.3,
     "coding_index": 37.8,
     "agentic_index": 26.5
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5-mini",
   "canonical_slug": "openai/gpt-5-mini-2025-08-07",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5 Mini",
   "created": 1754587407,
   "description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000025",
    "completion": "0.000002",
    "web_search": "0.01",
    "input_cache_read": "0.000000025"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-05-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5-mini-2025-08-07/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1083,
      "win_rate": 36.9,
      "rank": 89
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1155,
      "win_rate": 44.5,
      "rank": 42
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1139,
      "win_rate": 43.5,
      "rank": 82
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1152,
      "win_rate": 43.7,
      "rank": 73
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1165,
      "win_rate": 46.5,
      "rank": 67
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1132,
      "win_rate": 45.8,
      "rank": 52
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1133,
      "win_rate": 41.9,
      "rank": 73
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1145,
      "win_rate": 44.3,
      "rank": 80
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 25.8,
     "coding_index": 15.6,
     "agentic_index": 19.6
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5-mini:batch",
   "canonical_slug": "openai/gpt-5-mini-2025-08-07",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5 Mini (batch)",
   "created": 1754587407,
   "description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000125",
    "completion": "0.000001",
    "web_search": "0.01",
    "input_cache_read": "0.0000000125"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-05-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5-mini-2025-08-07/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1083,
      "win_rate": 36.9,
      "rank": 89
     },
     {
      "arena": "models",
      "category": "asciiart",
      "elo": 1155,
      "win_rate": 44.5,
      "rank": 42
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1139,
      "win_rate": 43.5,
      "rank": 82
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1152,
      "win_rate": 43.7,
      "rank": 73
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1165,
      "win_rate": 46.5,
      "rank": 67
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1132,
      "win_rate": 45.8,
      "rank": 52
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1133,
      "win_rate": 41.9,
      "rank": 73
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1145,
      "win_rate": 44.3,
      "rank": 80
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 25.8,
     "coding_index": 15.6,
     "agentic_index": 19.6
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5-nano",
   "canonical_slug": "openai/gpt-5-nano-2025-08-07",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5 Nano",
   "created": 1754587402,
   "description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000005",
    "completion": "0.0000004",
    "web_search": "0.01",
    "input_cache_read": "0.000000005"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_completion_tokens",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-05-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5-nano-2025-08-07/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1011,
      "win_rate": 36.3,
      "rank": 102
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1109,
      "win_rate": 48,
      "rank": 89
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1077,
      "win_rate": 46.2,
      "rank": 92
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1081,
      "win_rate": 46.5,
      "rank": 92
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1093,
      "win_rate": 51.9,
      "rank": 87
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1121,
      "win_rate": 48.9,
      "rank": 90
     }
    ]
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-5-nano:batch",
   "canonical_slug": "openai/gpt-5-nano-2025-08-07",
   "hugging_face_id": "",
   "name": "OpenAI: GPT-5 Nano (batch)",
   "created": 1754587402,
   "description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...",
   "context_length": 400000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000025",
    "completion": "0.0000002",
    "web_search": "0.01",
    "input_cache_read": "0.0000000025"
   },
   "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-05-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-5-nano-2025-08-07/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1011,
      "win_rate": 36.3,
      "rank": 102
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1109,
      "win_rate": 48,
      "rank": 89
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1077,
      "win_rate": 46.2,
      "rank": 92
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1081,
      "win_rate": 46.5,
      "rank": 92
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1093,
      "win_rate": 51.9,
      "rank": 87
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1121,
      "win_rate": 48.9,
      "rank": 90
     }
    ]
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low",
     "minimal"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-oss-120b",
   "canonical_slug": "openai/gpt-oss-120b",
   "hugging_face_id": "openai/gpt-oss-120b",
   "name": "OpenAI: gpt-oss-120b",
   "created": 1754414231,
   "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...",
   "context_length": 131072,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000003",
    "completion": "0.00000017",
    "input_cache_read": "0.00000003"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_a",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-06-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-oss-120b/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 946,
      "win_rate": 29.4,
      "rank": 105
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 987,
      "win_rate": 33.4,
      "rank": 112
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1008,
      "win_rate": 43.6,
      "rank": 103
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1028,
      "win_rate": 40.5,
      "rank": 102
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 953,
      "win_rate": 35.7,
      "rank": 107
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 988,
      "win_rate": 32.5,
      "rank": 114
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 24.1,
     "coding_index": 30.4,
     "agentic_index": 13.4
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-oss-20b",
   "canonical_slug": "openai/gpt-oss-20b",
   "hugging_face_id": "openai/gpt-oss-20b",
   "name": "OpenAI: gpt-oss-20b",
   "created": 1754414229,
   "description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...",
   "context_length": 131072,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000003",
    "completion": "0.00000013",
    "input_cache_read": "0.00000003"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 131072,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-06-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-oss-20b/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 953,
      "win_rate": 39.7,
      "rank": 107
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 872,
      "win_rate": 27.9,
      "rank": 122
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 15.2,
     "coding_index": 20.7,
     "agentic_index": 3.1
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "openai/gpt-oss-20b:free",
   "canonical_slug": "openai/gpt-oss-20b",
   "hugging_face_id": "openai/gpt-oss-20b",
   "name": "OpenAI: gpt-oss-20b (free)",
   "created": 1754414229,
   "description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...",
   "context_length": 131072,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0",
    "completion": "0"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-06-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-oss-20b/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 953,
      "win_rate": 39.7,
      "rank": 107
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 872,
      "win_rate": 27.9,
      "rank": 122
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 15.2,
     "coding_index": 20.7,
     "agentic_index": 3.1
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high",
     "medium",
     "low"
    ],
    "default_effort": "medium"
   }
  },
  {
   "id": "qwen/qwen3-235b-a22b-thinking-2507",
   "canonical_slug": "qwen/qwen3-235b-a22b-thinking-2507",
   "hugging_face_id": "Qwen/Qwen3-235B-A22B-Thinking-2507",
   "name": "Qwen: Qwen3 235B A22B Thinking 2507",
   "created": 1753449557,
   "description": "Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...",
   "context_length": 262144,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen3",
    "instruct_type": "qwen3"
   },
   "pricing": {
    "prompt": "0.00000023",
    "completion": "0.0000023"
   },
   "top_provider": {
    "context_length": 131072,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-06-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen3-235b-a22b-thinking-2507/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1043,
      "win_rate": 40.4,
      "rank": 95
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1057,
      "win_rate": 40.8,
      "rank": 100
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 970,
      "win_rate": 32.6,
      "rank": 106
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 993,
      "win_rate": 34.2,
      "rank": 109
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 971,
      "win_rate": 34,
      "rank": 106
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1072,
      "win_rate": 42,
      "rank": 99
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 19.9,
     "coding_index": 22.1,
     "agentic_index": 3.8
    }
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "google/gemini-2.5-pro",
   "canonical_slug": "google/gemini-2.5-pro",
   "hugging_face_id": "",
   "name": "Google: Gemini 2.5 Pro",
   "created": 1750169544,
   "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "file",
     "audio",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.00001",
    "image": "0.00000125",
    "audio": "0.00000125",
    "input_audio_cache": "0.000000125",
    "web_search": "0.014",
    "internal_reasoning": "0.00001",
    "input_cache_read": "0.000000125",
    "input_cache_write": "0.000000375",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.0000025",
      "completion": "0.000015",
      "audio": "0.0000025",
      "input_audio_cache": "0.00000025",
      "input_cache_read": "0.00000025"
     }
    ]
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-01-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-2.5-pro/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1126,
      "win_rate": 50.6,
      "rank": 79
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1177,
      "win_rate": 57.5,
      "rank": 65
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1243,
      "win_rate": 68.2,
      "rank": 35
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1147,
      "win_rate": 54.2,
      "rank": 70
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1166,
      "win_rate": 57.5,
      "rank": 66
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1187,
      "win_rate": 58.4,
      "rank": 64
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 25.9,
     "coding_index": 33.3,
     "agentic_index": 7.2
    }
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "google/gemini-2.5-pro:batch",
   "canonical_slug": "google/gemini-2.5-pro",
   "hugging_face_id": "",
   "name": "Google: Gemini 2.5 Pro (batch)",
   "created": 1750169544,
   "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "file",
     "audio",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000000625",
    "completion": "0.000005",
    "image": "0.000000625",
    "audio": "0.000000625",
    "input_audio_cache": "0.000000125",
    "web_search": "0.014",
    "internal_reasoning": "0.000005",
    "input_cache_read": "0.000000125",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.00000125",
      "completion": "0.0000075",
      "audio": "0.00000125",
      "input_audio_cache": "0.00000025",
      "input_cache_read": "0.00000025"
     }
    ]
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-01-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-2.5-pro/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1126,
      "win_rate": 50.6,
      "rank": 79
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1177,
      "win_rate": 57.5,
      "rank": 65
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1243,
      "win_rate": 68.2,
      "rank": 35
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1147,
      "win_rate": 54.2,
      "rank": 70
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1166,
      "win_rate": 57.5,
      "rank": 66
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1187,
      "win_rate": 58.4,
      "rank": 64
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 25.9,
     "coding_index": 33.3,
     "agentic_index": 7.2
    }
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "google/gemini-2.5-pro-preview",
   "canonical_slug": "google/gemini-2.5-pro-preview-06-05",
   "hugging_face_id": "",
   "name": "Google: Gemini 2.5 Pro Preview 06-05",
   "created": 1749137257,
   "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio->text",
    "input_modalities": [
     "file",
     "image",
     "text",
     "audio"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.00001",
    "image": "0.00000125",
    "audio": "0.00000125",
    "input_audio_cache": "0.000000125",
    "web_search": "0.014",
    "internal_reasoning": "0.00001",
    "input_cache_read": "0.000000125",
    "input_cache_write": "0.000000375",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.0000025",
      "completion": "0.000015",
      "audio": "0.0000025",
      "input_audio_cache": "0.00000025",
      "input_cache_read": "0.00000025"
     }
    ]
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": "2025-01-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-2.5-pro-preview-06-05/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "deepseek/deepseek-r1-0528",
   "canonical_slug": "deepseek/deepseek-r1-0528",
   "hugging_face_id": "deepseek-ai/DeepSeek-R1-0528",
   "name": "DeepSeek: R1 0528",
   "created": 1748455170,
   "description": "May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...",
   "context_length": 163840,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "DeepSeek",
    "instruct_type": "deepseek-r1"
   },
   "pricing": {
    "prompt": "0.0000005",
    "completion": "0.00000215",
    "input_cache_read": "0.00000035"
   },
   "top_provider": {
    "context_length": 163840,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-03-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/deepseek/deepseek-r1-0528/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1157,
      "win_rate": 53.3,
      "rank": 66
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1163,
      "win_rate": 52.6,
      "rank": 72
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1203,
      "win_rate": 60.9,
      "rank": 48
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1133,
      "win_rate": 49.3,
      "rank": 76
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1079,
      "win_rate": 48.7,
      "rank": 61
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1129,
      "win_rate": 54.9,
      "rank": 75
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1169,
      "win_rate": 52.7,
      "rank": 71
     }
    ]
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "anthropic/claude-sonnet-4",
   "canonical_slug": "anthropic/claude-4-sonnet-20250522",
   "hugging_face_id": "",
   "name": "Anthropic: Claude Sonnet 4",
   "created": 1747930371,
   "description": "Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...",
   "context_length": 1000000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "image",
     "text",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Claude",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000003",
    "completion": "0.000015",
    "web_search": "0.01",
    "input_cache_read": "0.0000003",
    "input_cache_write": "0.00000375",
    "input_cache_write_1h": "0.000006",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.000006",
      "completion": "0.0000225",
      "input_cache_read": "0.0000006",
      "input_cache_write": "0.0000075",
      "input_cache_write_1h": "0.000012"
     }
    ]
   },
   "top_provider": {
    "context_length": 200000,
    "max_completion_tokens": 64000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "stop",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-01-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/anthropic/claude-4-sonnet-20250522/endpoints"
   },
   "benchmarks": {
    "design_arena": [
     {
      "arena": "models",
      "category": "3d",
      "elo": 1185,
      "win_rate": 57.8,
      "rank": 53
     },
     {
      "arena": "models",
      "category": "codecategories",
      "elo": 1166,
      "win_rate": 53.4,
      "rank": 71
     },
     {
      "arena": "models",
      "category": "dataviz",
      "elo": 1179,
      "win_rate": 56.5,
      "rank": 63
     },
     {
      "arena": "models",
      "category": "gamedev",
      "elo": 1175,
      "win_rate": 54.8,
      "rank": 60
     },
     {
      "arena": "models",
      "category": "svg",
      "elo": 1119,
      "win_rate": 51.1,
      "rank": 55
     },
     {
      "arena": "models",
      "category": "uicomponent",
      "elo": 1155,
      "win_rate": 57.9,
      "rank": 70
     },
     {
      "arena": "models",
      "category": "website",
      "elo": 1166,
      "win_rate": 52.4,
      "rank": 72
     }
    ],
    "artificial_analysis": {
     "intelligence_index": 29.8,
     "coding_index": 37.6,
     "agentic_index": 17.6
    }
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "google/gemini-2.5-pro-preview-05-06",
   "canonical_slug": "google/gemini-2.5-pro-preview-03-25",
   "hugging_face_id": "",
   "name": "Google: Gemini 2.5 Pro Preview 05-06",
   "created": 1746578513,
   "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...",
   "context_length": 1048576,
   "architecture": {
    "modality": "text+image+file+audio+video->text",
    "input_modalities": [
     "text",
     "image",
     "file",
     "audio",
     "video"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Gemini",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000125",
    "completion": "0.00001",
    "image": "0.00000125",
    "audio": "0.00000125",
    "input_audio_cache": "0.000000125",
    "web_search": "0.014",
    "internal_reasoning": "0.00001",
    "input_cache_read": "0.000000125",
    "input_cache_write": "0.000000375",
    "overrides": [
     {
      "min_prompt_tokens": 200000,
      "prompt": "0.0000025",
      "completion": "0.000015",
      "audio": "0.0000025",
      "input_audio_cache": "0.00000025",
      "input_cache_read": "0.00000025"
     }
    ]
   },
   "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 65535,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-01-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/google/gemini-2.5-pro-preview-03-25/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openai/o4-mini-high",
   "canonical_slug": "openai/o4-mini-high-2025-04-16",
   "hugging_face_id": "",
   "name": "OpenAI: o4 Mini High",
   "created": 1744824212,
   "description": "OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...",
   "context_length": 200000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "image",
     "text",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000011",
    "completion": "0.0000044",
    "web_search": "0.01",
    "input_cache_read": "0.000000275"
   },
   "top_provider": {
    "context_length": 200000,
    "max_completion_tokens": 100000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-06-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/o4-mini-high-2025-04-16/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "openai/o4-mini-high:batch",
   "canonical_slug": "openai/o4-mini-high-2025-04-16",
   "hugging_face_id": "",
   "name": "OpenAI: o4 Mini High (batch)",
   "created": 1744824212,
   "description": "OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...",
   "context_length": 200000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "image",
     "text",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000055",
    "completion": "0.0000022",
    "web_search": "0.01",
    "input_cache_read": "0.0000001375"
   },
   "top_provider": {
    "context_length": 200000,
    "max_completion_tokens": 100000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-06-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/o4-mini-high-2025-04-16/endpoints"
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "openai/o1-pro",
   "canonical_slug": "openai/o1-pro",
   "hugging_face_id": "",
   "name": "OpenAI: o1-pro",
   "created": 1742423211,
   "description": "The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...",
   "context_length": 200000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00015",
    "completion": "0.0006",
    "web_search": "0.01"
   },
   "top_provider": {
    "context_length": 200000,
    "max_completion_tokens": 100000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "structured_outputs"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": "2023-10-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/o1-pro/endpoints"
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "openai/o1-pro:batch",
   "canonical_slug": "openai/o1-pro",
   "hugging_face_id": "",
   "name": "OpenAI: o1-pro (batch)",
   "created": 1742423211,
   "description": "The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...",
   "context_length": 200000,
   "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
     "text",
     "image",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.000075",
    "completion": "0.0003",
    "web_search": "0.01"
   },
   "top_provider": {
    "context_length": 200000,
    "max_completion_tokens": 100000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "structured_outputs"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": "2023-10-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/o1-pro/endpoints"
   },
   "reasoning": {
    "mandatory": false
   }
  },
  {
   "id": "rekaai/reka-flash-3",
   "canonical_slug": "rekaai/reka-flash-3",
   "hugging_face_id": "RekaAI/reka-flash-3",
   "name": "Reka Flash 3",
   "created": 1741812813,
   "description": "Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...",
   "context_length": 65536,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Other",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000001",
    "completion": "0.0000002"
   },
   "top_provider": {
    "context_length": 65536,
    "max_completion_tokens": 65536,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2025-01-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/rekaai/reka-flash-3/endpoints"
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openai/o3-mini-high",
   "canonical_slug": "openai/o3-mini-high-2025-01-31",
   "hugging_face_id": "",
   "name": "OpenAI: o3 Mini High",
   "created": 1739372611,
   "description": "OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...",
   "context_length": 200000,
   "architecture": {
    "modality": "text+file->text",
    "input_modalities": [
     "text",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.0000011",
    "completion": "0.0000044",
    "web_search": "0.01",
    "input_cache_read": "0.00000055"
   },
   "top_provider": {
    "context_length": 200000,
    "max_completion_tokens": 100000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2023-10-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/o3-mini-high-2025-01-31/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 15.7,
     "coding_index": 16.3,
     "agentic_index": 1.7
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "openai/o3-mini-high:batch",
   "canonical_slug": "openai/o3-mini-high-2025-01-31",
   "hugging_face_id": "",
   "name": "OpenAI: o3 Mini High (batch)",
   "created": 1739372611,
   "description": "OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...",
   "context_length": 200000,
   "architecture": {
    "modality": "text+file->text",
    "input_modalities": [
     "text",
     "file"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000055",
    "completion": "0.0000022",
    "web_search": "0.01",
    "input_cache_read": "0.000000275"
   },
   "top_provider": {
    "context_length": 200000,
    "max_completion_tokens": 100000,
    "is_moderated": true
   },
   "per_request_limits": null,
   "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "reasoning_effort",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "frequency_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2023-10-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/o3-mini-high-2025-01-31/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 15.7,
     "coding_index": 16.3,
     "agentic_index": 1.7
    }
   },
   "reasoning": {
    "mandatory": true,
    "supported_efforts": [
     "high"
    ],
    "default_effort": "high"
   }
  },
  {
   "id": "qwen/qwen-plus",
   "canonical_slug": "qwen/qwen-plus-2025-01-25",
   "hugging_face_id": "",
   "name": "Qwen: Qwen-Plus",
   "created": 1738409840,
   "description": "Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.",
   "context_length": 1000000,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "Qwen",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00000026",
    "completion": "0.00000078",
    "input_cache_read": "0.000000052",
    "input_cache_write": "0.000000325",
    "overrides": [
     {
      "min_prompt_tokens": 256000,
      "prompt": "0.00000078",
      "completion": "0.00000234",
      "input_cache_read": "0.000000156",
      "input_cache_write": "0.000000975"
     }
    ]
   },
   "top_provider": {
    "context_length": 1000000,
    "max_completion_tokens": 32768,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "logprobs",
    "max_tokens",
    "presence_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": "2025-03-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/qwen/qwen-plus-2025-01-25/endpoints"
   }
  },
  {
   "id": "deepseek/deepseek-r1",
   "canonical_slug": "deepseek/deepseek-r1",
   "hugging_face_id": "deepseek-ai/DeepSeek-R1",
   "name": "DeepSeek: R1",
   "created": 1737381095,
   "description": "DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....",
   "context_length": 64000,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "DeepSeek",
    "instruct_type": "deepseek-r1"
   },
   "pricing": {
    "prompt": "0.0000007",
    "completion": "0.0000025"
   },
   "top_provider": {
    "context_length": 64000,
    "max_completion_tokens": 16000,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "max_tokens",
    "presence_penalty",
    "reasoning",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_k",
    "top_p"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": "2024-07-31",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/deepseek/deepseek-r1/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": 18.6,
     "coding_index": 24.6,
     "agentic_index": 3.1
    }
   },
   "reasoning": {
    "mandatory": true
   }
  },
  {
   "id": "openrouter/auto",
   "canonical_slug": "openrouter/auto",
   "hugging_face_id": null,
   "name": "Auto Router",
   "created": 1699401600,
   "description": "Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,...",
   "context_length": 2000000,
   "architecture": {
    "modality": "text+image+file+audio+video->text+image",
    "input_modalities": [
     "text",
     "image",
     "audio",
     "file",
     "video"
    ],
    "output_modalities": [
     "text",
     "image"
    ],
    "tokenizer": "Router",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "-1",
    "completion": "-1"
   },
   "top_provider": {
    "context_length": null,
    "max_completion_tokens": null,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "prediction",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_a",
    "top_k",
    "top_logprobs",
    "top_p",
    "web_search_options"
   ],
   "default_parameters": {
    "temperature": null,
    "top_p": null,
    "top_k": null,
    "frequency_penalty": null,
    "presence_penalty": null,
    "repetition_penalty": null
   },
   "supported_voices": null,
   "knowledge_cutoff": null,
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openrouter/auto/endpoints"
   }
  },
  {
   "id": "openai/gpt-4",
   "canonical_slug": "openai/gpt-4",
   "hugging_face_id": null,
   "name": "OpenAI: GPT-4",
   "created": 1685232000,
   "description": "OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...",
   "context_length": 8191,
   "architecture": {
    "modality": "text->text",
    "input_modalities": [
     "text"
    ],
    "output_modalities": [
     "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
   },
   "pricing": {
    "prompt": "0.00003",
    "completion": "0.00006"
   },
   "top_provider": {
    "context_length": 8191,
    "max_completion_tokens": 4096,
    "is_moderated": false
   },
   "per_request_limits": null,
   "supported_parameters": [
    "frequency_penalty",
    "logit_bias",
    "logprobs",
    "max_completion_tokens",
    "max_tokens",
    "presence_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_logprobs",
    "top_p"
   ],
   "default_parameters": {},
   "supported_voices": null,
   "knowledge_cutoff": "2021-09-30",
   "expiration_date": null,
   "links": {
    "details": "/api/v1/models/openai/gpt-4/endpoints"
   },
   "benchmarks": {
    "design_arena": [],
    "artificial_analysis": {
     "intelligence_index": null,
     "coding_index": 13.1,
     "agentic_index": null
    }
   }
  }
 ]
}