{
  "source_url": "https://openrouter.ai/api/v1/models",
  "models": [
    {
      "id": "qwen/qwen3.8-max-prime",
      "canonical_slug": "qwen/qwen3.8-max-prime-20260923",
      "hugging_face_id": null,
      "name": "Qwen: Qwen3.8 Max Prime",
      "created": 1790191228,
      "description": "Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...",
      "context_length": 1000000,
      "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
          "text",
          "image",
          "video"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "Qwen",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0.000004",
        "completion": "0.000012",
        "input_cache_read": "0.0000005"
      },
      "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-prime-20260923/endpoints"
      },
      "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
          "xhigh",
          "high",
          "medium",
          "low",
          "minimal"
        ],
        "default_effort": "xhigh"
      }
    },
    {
      "id": "qwen/qwen3.8-omni-flash",
      "canonical_slug": "qwen/qwen3.8-omni-flash-20260918",
      "hugging_face_id": null,
      "name": "Qwen: Qwen3.8 Omni Flash",
      "created": 1789959954,
      "description": "Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...",
      "context_length": 1000000,
      "architecture": {
        "modality": "text+image+audio+video->text",
        "input_modalities": [
          "text",
          "image",
          "audio",
          "video"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "Qwen",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0.00000015",
        "completion": "0.00000047",
        "input_cache_read": "0.000000016"
      },
      "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/qwen3.8-omni-flash-20260918/endpoints"
      },
      "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supports_max_tokens": true
      }
    },
    {
      "id": "z-ai/glm-5.3-flashx",
      "canonical_slug": "z-ai/glm-5.3-flashx-20260918",
      "hugging_face_id": "",
      "name": "Z.ai: GLM 5.3 FlashX",
      "created": 1789744020,
      "description": "GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...",
      "context_length": 1048576,
      "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
          "text",
          "image",
          "video"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "Other",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0.00000037",
        "completion": "0.00000125",
        "input_cache_read": "0.00000009"
      },
      "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": null,
      "links": {
        "details": "/api/v1/models/z-ai/glm-5.3-flashx-20260918/endpoints"
      },
      "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
          "max",
          "high",
          "low"
        ],
        "default_effort": "max"
      }
    },
    {
      "id": "qwen/qwen3.8-max-0902",
      "canonical_slug": "qwen/qwen3.8-max-20260902",
      "hugging_face_id": null,
      "name": "Qwen: Qwen3.8 Max (0902)",
      "created": 1788469704,
      "description": "Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...",
      "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-20260902/endpoints"
      },
      "benchmarks": {
        "design_arena": [],
        "artificial_analysis": {
          "intelligence_index": 45.4,
          "coding_index": 76.2,
          "agentic_index": 56
        }
      },
      "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
          "xhigh",
          "high",
          "medium",
          "low",
          "minimal"
        ],
        "default_effort": "xhigh"
      }
    },
    {
      "id": "google/gemini-3.8-flash",
      "canonical_slug": "google/gemini-3.8-flash-20260902",
      "hugging_face_id": null,
      "name": "Google: Gemini 3.8 Flash",
      "created": 1788362056,
      "description": "Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.",
      "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": {},
      "supported_voices": null,
      "knowledge_cutoff": null,
      "expiration_date": null,
      "links": {
        "details": "/api/v1/models/google/gemini-3.8-flash-20260902/endpoints"
      },
      "benchmarks": {
        "design_arena": [
          {
            "arena": "agents",
            "category": "androidnative",
            "elo": 1077,
            "win_rate": 33.2,
            "rank": 31
          },
          {
            "arena": "agents",
            "category": "fullstack",
            "elo": 1242,
            "win_rate": 48.1,
            "rank": 11
          },
          {
            "arena": "agents",
            "category": "godotgamedev",
            "elo": 1273,
            "win_rate": 53,
            "rank": 5
          },
          {
            "arena": "agents",
            "category": "mobileapps",
            "elo": 1232,
            "win_rate": 54.2,
            "rank": 8
          },
          {
            "arena": "agents",
            "category": "python-pptxslides",
            "elo": 1178,
            "win_rate": 39.8,
            "rank": 19
          },
          {
            "arena": "agents",
            "category": "webapps",
            "elo": 1230,
            "win_rate": 46.1,
            "rank": 11
          },
          {
            "arena": "models",
            "category": "3d",
            "elo": 1311,
            "win_rate": 50.5,
            "rank": 14
          },
          {
            "arena": "models",
            "category": "asciiart",
            "elo": 1284,
            "win_rate": 53.6,
            "rank": 10
          },
          {
            "arena": "models",
            "category": "codecategories",
            "elo": 1311,
            "win_rate": 51.3,
            "rank": 11
          },
          {
            "arena": "models",
            "category": "dataviz",
            "elo": 1271,
            "win_rate": 50.5,
            "rank": 25
          },
          {
            "arena": "models",
            "category": "gamedev",
            "elo": 1321,
            "win_rate": 52,
            "rank": 10
          },
          {
            "arena": "models",
            "category": "svg",
            "elo": 1290,
            "win_rate": 53.6,
            "rank": 9
          },
          {
            "arena": "models",
            "category": "uicomponent",
            "elo": 1322,
            "win_rate": 53.3,
            "rank": 11
          },
          {
            "arena": "models",
            "category": "website",
            "elo": 1308,
            "win_rate": 51,
            "rank": 10
          }
        ],
        "artificial_analysis": {
          "intelligence_index": 40.9,
          "coding_index": 76.3,
          "agentic_index": 40.2
        }
      },
      "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
          "high",
          "medium",
          "low"
        ],
        "default_effort": "medium"
      }
    },
    {
      "id": "google/gemini-3.8-flash:batch",
      "canonical_slug": "google/gemini-3.8-flash-20260902",
      "hugging_face_id": null,
      "name": "Google: Gemini 3.8 Flash (batch)",
      "created": 1788362056,
      "description": "Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.",
      "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": {},
      "supported_voices": null,
      "knowledge_cutoff": null,
      "expiration_date": null,
      "links": {
        "details": "/api/v1/models/google/gemini-3.8-flash-20260902/endpoints"
      },
      "benchmarks": {
        "design_arena": [
          {
            "arena": "agents",
            "category": "androidnative",
            "elo": 1077,
            "win_rate": 33.2,
            "rank": 31
          },
          {
            "arena": "agents",
            "category": "fullstack",
            "elo": 1242,
            "win_rate": 48.1,
            "rank": 11
          },
          {
            "arena": "agents",
            "category": "godotgamedev",
            "elo": 1273,
            "win_rate": 53,
            "rank": 5
          },
          {
            "arena": "agents",
            "category": "mobileapps",
            "elo": 1232,
            "win_rate": 54.2,
            "rank": 8
          },
          {
            "arena": "agents",
            "category": "python-pptxslides",
            "elo": 1178,
            "win_rate": 39.8,
            "rank": 19
          },
          {
            "arena": "agents",
            "category": "webapps",
            "elo": 1230,
            "win_rate": 46.1,
            "rank": 11
          },
          {
            "arena": "models",
            "category": "3d",
            "elo": 1311,
            "win_rate": 50.5,
            "rank": 14
          },
          {
            "arena": "models",
            "category": "asciiart",
            "elo": 1284,
            "win_rate": 53.6,
            "rank": 10
          },
          {
            "arena": "models",
            "category": "codecategories",
            "elo": 1311,
            "win_rate": 51.3,
            "rank": 11
          },
          {
            "arena": "models",
            "category": "dataviz",
            "elo": 1271,
            "win_rate": 50.5,
            "rank": 25
          },
          {
            "arena": "models",
            "category": "gamedev",
            "elo": 1321,
            "win_rate": 52,
            "rank": 10
          },
          {
            "arena": "models",
            "category": "svg",
            "elo": 1290,
            "win_rate": 53.6,
            "rank": 9
          },
          {
            "arena": "models",
            "category": "uicomponent",
            "elo": 1322,
            "win_rate": 53.3,
            "rank": 11
          },
          {
            "arena": "models",
            "category": "website",
            "elo": 1308,
            "win_rate": 51,
            "rank": 10
          }
        ],
        "artificial_analysis": {
          "intelligence_index": 40.9,
          "coding_index": 76.3,
          "agentic_index": 40.2
        }
      },
      "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
          "high",
          "medium",
          "low"
        ],
        "default_effort": "medium"
      }
    },
    {
      "id": "qwen/qwen3.8-flash",
      "canonical_slug": "qwen/qwen3.8-flash-20260826",
      "hugging_face_id": "Qwen/Qwen3.8-Flash-Next",
      "name": "Qwen: Qwen3.8 Flash",
      "created": 1787773060,
      "description": "Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.",
      "context_length": 1000000,
      "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
          "text",
          "image",
          "video"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "Qwen",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0.00000015",
        "completion": "0.00000047",
        "input_cache_read": "0.000000016",
        "input_cache_write": "0.0000002"
      },
      "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/qwen3.8-flash-20260826/endpoints"
      },
      "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supports_max_tokens": true
      }
    },
    {
      "id": "z-ai/glm-5.3-flash",
      "canonical_slug": "z-ai/glm-5.3-flash-20260826",
      "hugging_face_id": "zai-org/GLM-5.3-Flash",
      "name": "Z.ai: GLM 5.3 Flash",
      "created": 1787752741,
      "description": "GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...",
      "context_length": 1048576,
      "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
          "text",
          "image",
          "video"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "Other",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0.00000015",
        "completion": "0.0000005",
        "input_cache_read": "0.00000003"
      },
      "top_provider": {
        "context_length": 1048575,
        "max_completion_tokens": 943717,
        "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",
        "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
      },
      "supported_voices": null,
      "knowledge_cutoff": null,
      "expiration_date": null,
      "links": {
        "details": "/api/v1/models/z-ai/glm-5.3-flash-20260826/endpoints"
      },
      "benchmarks": {
        "design_arena": [
          {
            "arena": "models",
            "category": "3d",
            "elo": 1334,
            "win_rate": 56.8,
            "rank": 11
          },
          {
            "arena": "models",
            "category": "asciiart",
            "elo": 1276,
            "win_rate": 54.8,
            "rank": 12
          },
          {
            "arena": "models",
            "category": "codecategories",
            "elo": 1289,
            "win_rate": 49.5,
            "rank": 17
          },
          {
            "arena": "models",
            "category": "dataviz",
            "elo": 1272,
            "win_rate": 50.5,
            "rank": 24
          },
          {
            "arena": "models",
            "category": "gamedev",
            "elo": 1294,
            "win_rate": 47.3,
            "rank": 17
          },
          {
            "arena": "models",
            "category": "svg",
            "elo": 1290,
            "win_rate": 57.1,
            "rank": 10
          },
          {
            "arena": "models",
            "category": "uicomponent",
            "elo": 1325,
            "win_rate": 55,
            "rank": 10
          },
          {
            "arena": "models",
            "category": "website",
            "elo": 1279,
            "win_rate": 48.5,
            "rank": 22
          }
        ],
        "artificial_analysis": {
          "intelligence_index": 41.8,
          "coding_index": 71.5,
          "agentic_index": 50.9
        }
      },
      "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
          "max",
          "high",
          "low"
        ],
        "default_effort": "max"
      }
    },
    {
      "id": "z-ai/glm-5.3-flash:batch",
      "canonical_slug": "z-ai/glm-5.3-flash-20260826",
      "hugging_face_id": "zai-org/GLM-5.3-Flash",
      "name": "Z.ai: GLM 5.3 Flash (batch)",
      "created": 1787752741,
      "description": "GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...",
      "context_length": 1048576,
      "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
          "text",
          "image",
          "video"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "Other",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0.00000006",
        "completion": "0.0000002",
        "input_cache_read": "0.000000012"
      },
      "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 131072,
        "is_moderated": false
      },
      "per_request_limits": null,
      "supported_parameters": [
        "frequency_penalty",
        "include_reasoning",
        "logit_bias",
        "max_tokens",
        "min_p",
        "presence_penalty",
        "reasoning",
        "reasoning_effort",
        "repetition_penalty",
        "response_format",
        "seed",
        "stop",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_k",
        "top_p"
      ],
      "default_parameters": {
        "temperature": 1,
        "top_p": 0.95
      },
      "supported_voices": null,
      "knowledge_cutoff": null,
      "expiration_date": null,
      "links": {
        "details": "/api/v1/models/z-ai/glm-5.3-flash-20260826/endpoints"
      },
      "benchmarks": {
        "design_arena": [
          {
            "arena": "models",
            "category": "3d",
            "elo": 1334,
            "win_rate": 56.8,
            "rank": 11
          },
          {
            "arena": "models",
            "category": "asciiart",
            "elo": 1276,
            "win_rate": 54.8,
            "rank": 12
          },
          {
            "arena": "models",
            "category": "codecategories",
            "elo": 1289,
            "win_rate": 49.5,
            "rank": 17
          },
          {
            "arena": "models",
            "category": "dataviz",
            "elo": 1272,
            "win_rate": 50.5,
            "rank": 24
          },
          {
            "arena": "models",
            "category": "gamedev",
            "elo": 1294,
            "win_rate": 47.3,
            "rank": 17
          },
          {
            "arena": "models",
            "category": "svg",
            "elo": 1290,
            "win_rate": 57.1,
            "rank": 10
          },
          {
            "arena": "models",
            "category": "uicomponent",
            "elo": 1325,
            "win_rate": 55,
            "rank": 10
          },
          {
            "arena": "models",
            "category": "website",
            "elo": 1279,
            "win_rate": 48.5,
            "rank": 22
          }
        ],
        "artificial_analysis": {
          "intelligence_index": 41.8,
          "coding_index": 71.5,
          "agentic_index": 50.9
        }
      },
      "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
          "max",
          "high",
          "low"
        ],
        "default_effort": "max"
      }
    },
    {
      "id": "qwen/qwen3.8-27b",
      "canonical_slug": "qwen/qwen3.8-27b-20260814",
      "hugging_face_id": "Qwen/Qwen3.8-27B",
      "name": "Qwen: Qwen3.8 27B",
      "created": 1786722910,
      "description": "Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...",
      "context_length": 1000000,
      "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
          "text",
          "image",
          "video"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "Qwen",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0.00000042",
        "completion": "0.000003",
        "input_cache_read": "0.000000085"
      },
      "top_provider": {
        "context_length": 1000000,
        "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": 1,
        "top_p": 0.95,
        "top_k": 20
      },
      "supported_voices": null,
      "knowledge_cutoff": null,
      "expiration_date": null,
      "links": {
        "details": "/api/v1/models/qwen/qwen3.8-27b-20260814/endpoints"
      },
      "benchmarks": {
        "design_arena": [],
        "artificial_analysis": {
          "intelligence_index": 33.7,
          "coding_index": 68.1,
          "agentic_index": 45.8
        }
      },
      "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
          "xhigh",
          "medium",
          "low"
        ],
        "default_effort": "xhigh"
      }
    },
    {
      "id": "qwen/qwen3.8-27b:free",
      "canonical_slug": "qwen/qwen3.8-27b-20260814",
      "hugging_face_id": "Qwen/Qwen3.8-27B",
      "name": "Qwen: Qwen3.8 27B (free)",
      "created": 1786722910,
      "description": "Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...",
      "context_length": 262144,
      "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
          "text",
          "image",
          "video"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "Qwen",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0",
        "completion": "0"
      },
      "top_provider": {
        "context_length": 262144,
        "max_completion_tokens": 235929,
        "is_moderated": false
      },
      "per_request_limits": null,
      "supported_parameters": [
        "frequency_penalty",
        "include_reasoning",
        "max_tokens",
        "presence_penalty",
        "reasoning",
        "reasoning_effort",
        "repetition_penalty",
        "stop",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "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/qwen3.8-27b-20260814/endpoints"
      },
      "benchmarks": {
        "design_arena": [],
        "artificial_analysis": {
          "intelligence_index": 33.7,
          "coding_index": 68.1,
          "agentic_index": 45.8
        }
      },
      "reasoning": {
        "mandatory": false,
        "default_enabled": true,
        "supported_efforts": [
          "xhigh",
          "medium",
          "low"
        ],
        "default_effort": "xhigh"
      }
    },
    {
      "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": 1000000,
        "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": 39.9,
          "coding_index": 71.9,
          "agentic_index": 50.1
        }
      },
      "reasoning": {
        "mandatory": true,
        "default_enabled": true,
        "supported_efforts": [
          "xhigh",
          "medium",
          "low"
        ],
        "default_effort": "xhigh"
      }
    }
  ]
}