{
  "data": [
    {
      "schema_version": "2.4",
      "id": "deepseek/deepseek-v4.1-flash",
      "name": "DeepSeek: DeepSeek V4.1 Flash",
      "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
      "created": 1789021285,
      "quantization": null,
      "description": "DeepSeek V4.1 Flash served by Redline: low-latency inference for long-context, agentic workloads.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 1048576,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.00000027"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.0000000054"
            }
          ]
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 65536,
            "unit": "token"
          },
          "streaming": true,
          "supported_parameters": {
            "temperature": {
              "type": "range",
              "min": 0,
              "max": 2
            },
            "top_p": {
              "type": "range",
              "min": 0,
              "max": 1
            },
            "max_tokens": {
              "type": "integer",
              "min": 1,
              "max": 65536,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "tools": {
              "type": "boolean"
            },
            "structured_outputs": {
              "type": "boolean"
            },
            "reasoning": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.00000108"
            },
            {
              "type": "internal_reasoning",
              "unit": "token",
              "cost_usd": "0.00000108"
            }
          ]
        }
      ],
      "is_ready": false,
      "is_free": false,
      "openrouter": {
        "slug": "deepseek/deepseek-v4.1-flash"
      },
      "deployment_region": "US"
    },
    {
      "schema_version": "2.4",
      "id": "moonshotai/kimi-k3",
      "name": "MoonshotAI: Kimi K3",
      "hugging_face_id": "moonshotai/Kimi-K3",
      "created": 1784215858,
      "quantization": null,
      "description": "Kimi K3 served by Redline: low-latency inference for long-context, agentic workloads.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 1048576,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.0000008"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.00000022"
            }
          ],
          "capacity": [
            {
              "type": "prompt",
              "unit": "token",
              "per": "minute",
              "value": 1500000
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "per": "minute",
              "value": 10000000
            }
          ]
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 65536,
            "unit": "token"
          },
          "streaming": true,
          "supported_parameters": {
            "temperature": {
              "type": "range",
              "min": 0,
              "max": 2
            },
            "top_p": {
              "type": "range",
              "min": 0,
              "max": 1
            },
            "max_tokens": {
              "type": "integer",
              "min": 1,
              "max": 65536,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "tools": {
              "type": "boolean"
            },
            "structured_outputs": {
              "type": "boolean"
            },
            "reasoning": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.0000125"
            },
            {
              "type": "internal_reasoning",
              "unit": "token",
              "cost_usd": "0.0000125"
            }
          ],
          "capacity": [
            {
              "type": "completion",
              "unit": "token",
              "per": "minute",
              "value": 300000
            }
          ]
        }
      ],
      "is_ready": false,
      "is_free": false,
      "openrouter": {
        "slug": "moonshotai/kimi-k3"
      },
      "deployment_region": "US",
      "capacity": [
        {
          "type": "request",
          "unit": "request",
          "per": "minute",
          "value": 300
        }
      ]
    },
    {
      "schema_version": "2.4",
      "id": "tencent/hy4-preview",
      "name": "Tencent: Hy4 preview",
      "hugging_face_id": "tencent/Hy4-preview",
      "created": 1787897375,
      "quantization": null,
      "description": "Hy4 preview served by Redline: low-latency inference for long-context, agentic workloads.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 1048576,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.00000075"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.000000038"
            }
          ]
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 65536,
            "unit": "token"
          },
          "streaming": true,
          "supported_parameters": {
            "temperature": {
              "type": "range",
              "min": 0,
              "max": 2
            },
            "top_p": {
              "type": "range",
              "min": 0,
              "max": 1
            },
            "max_tokens": {
              "type": "integer",
              "min": 1,
              "max": 65536,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "tools": {
              "type": "boolean"
            },
            "structured_outputs": {
              "type": "boolean"
            },
            "reasoning": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.00000225"
            },
            {
              "type": "internal_reasoning",
              "unit": "token",
              "cost_usd": "0.00000225"
            }
          ]
        }
      ],
      "is_ready": false,
      "is_free": false,
      "openrouter": {
        "slug": "tencent/hy4-preview"
      },
      "deployment_region": "US"
    },
    {
      "schema_version": "2.4",
      "id": "xiaomi/mimo-v2.6-pro",
      "name": "Xiaomi: MiMo-V2.6-Pro",
      "hugging_face_id": "XiaomiMiMo/MiMo-V2.6-Pro-RL",
      "created": 1790021259,
      "quantization": null,
      "description": "MiMo-V2.6-Pro served by Redline: low-latency inference for long-context, agentic workloads.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 1050000,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.00000043"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.000000004"
            }
          ]
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 65536,
            "unit": "token"
          },
          "streaming": true,
          "supported_parameters": {
            "temperature": {
              "type": "range",
              "min": 0,
              "max": 2
            },
            "top_p": {
              "type": "range",
              "min": 0,
              "max": 1
            },
            "max_tokens": {
              "type": "integer",
              "min": 1,
              "max": 65536,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "tools": {
              "type": "boolean"
            },
            "structured_outputs": {
              "type": "boolean"
            },
            "reasoning": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.00000087"
            },
            {
              "type": "internal_reasoning",
              "unit": "token",
              "cost_usd": "0.00000087"
            }
          ]
        }
      ],
      "is_ready": false,
      "is_free": false,
      "openrouter": {
        "slug": "xiaomi/mimo-v2.6-pro"
      },
      "deployment_region": "US"
    },
    {
      "schema_version": "2.4",
      "id": "z-ai/glm-5.2",
      "name": "Z.ai: GLM 5.2",
      "hugging_face_id": "zai-org/GLM-5.2",
      "created": 1781631930,
      "quantization": null,
      "description": "GLM 5.2 served by Redline: low-latency inference for long-context, agentic workloads.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 1048576,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.00000126"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.00000023"
            }
          ]
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 65536,
            "unit": "token"
          },
          "streaming": true,
          "supported_parameters": {
            "temperature": {
              "type": "range",
              "min": 0,
              "max": 2
            },
            "top_p": {
              "type": "range",
              "min": 0,
              "max": 1
            },
            "max_tokens": {
              "type": "integer",
              "min": 1,
              "max": 65536,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "tools": {
              "type": "boolean"
            },
            "structured_outputs": {
              "type": "boolean"
            },
            "reasoning": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.00000396"
            },
            {
              "type": "internal_reasoning",
              "unit": "token",
              "cost_usd": "0.00000396"
            }
          ]
        }
      ],
      "is_ready": false,
      "is_free": false,
      "openrouter": {
        "slug": "z-ai/glm-5.2"
      },
      "deployment_region": "US"
    },
    {
      "schema_version": "2.4",
      "id": "z-ai/glm-5.3",
      "name": "Z.ai: GLM 5.3",
      "hugging_face_id": "zai-org/GLM-5.3",
      "created": 1787086655,
      "quantization": null,
      "description": "GLM 5.3 served by Redline: low-latency inference for long-context, agentic workloads.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 1048576,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.00000126"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.00000023"
            }
          ]
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 65536,
            "unit": "token"
          },
          "streaming": true,
          "supported_parameters": {
            "temperature": {
              "type": "range",
              "min": 0,
              "max": 2
            },
            "top_p": {
              "type": "range",
              "min": 0,
              "max": 1
            },
            "max_tokens": {
              "type": "integer",
              "min": 1,
              "max": 65536,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "tools": {
              "type": "boolean"
            },
            "structured_outputs": {
              "type": "boolean"
            },
            "reasoning": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.00000396"
            },
            {
              "type": "internal_reasoning",
              "unit": "token",
              "cost_usd": "0.00000396"
            }
          ]
        }
      ],
      "is_ready": false,
      "is_free": false,
      "openrouter": {
        "slug": "z-ai/glm-5.3"
      },
      "deployment_region": "US"
    },
    {
      "schema_version": "2.4",
      "id": "deepseek/deepseek-v4-pro-0813",
      "name": "DeepSeek: DeepSeek V4 Pro 0813",
      "hugging_face_id": "deepseek-ai/DeepSeek-V4-Pro-0813",
      "created": 1786549364,
      "quantization": null,
      "description": "DeepSeek V4 Pro 0813 served by Redline: low-latency inference for long-context, agentic workloads.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 1048576,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.00000119"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.000000036"
            }
          ]
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 65536,
            "unit": "token"
          },
          "streaming": true,
          "supported_parameters": {
            "temperature": {
              "type": "range",
              "min": 0,
              "max": 2
            },
            "top_p": {
              "type": "range",
              "min": 0,
              "max": 1
            },
            "max_tokens": {
              "type": "integer",
              "min": 1,
              "max": 65536,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "tools": {
              "type": "boolean"
            },
            "structured_outputs": {
              "type": "boolean"
            },
            "reasoning": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.00000356"
            },
            {
              "type": "internal_reasoning",
              "unit": "token",
              "cost_usd": "0.00000356"
            }
          ]
        }
      ],
      "is_ready": false,
      "is_free": false,
      "openrouter": {
        "slug": "deepseek/deepseek-v4-pro-0813"
      },
      "deployment_region": "US"
    },
    {
      "schema_version": "2.4",
      "id": "xiaomi/mimo-v2.6-flash",
      "name": "Xiaomi: MiMo-V2.6-Flash",
      "hugging_face_id": "XiaomiMiMo/MiMo-V2.6-Flash-RL",
      "created": 1790021264,
      "quantization": null,
      "description": "MiMo-V2.6-Flash served by Redline: low-latency inference for long-context, agentic workloads.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 1050000,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.00000014"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.000000003"
            }
          ]
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 65536,
            "unit": "token"
          },
          "streaming": true,
          "supported_parameters": {
            "temperature": {
              "type": "range",
              "min": 0,
              "max": 2
            },
            "top_p": {
              "type": "range",
              "min": 0,
              "max": 1
            },
            "max_tokens": {
              "type": "integer",
              "min": 1,
              "max": 65536,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "tools": {
              "type": "boolean"
            },
            "structured_outputs": {
              "type": "boolean"
            },
            "reasoning": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.00000028"
            },
            {
              "type": "internal_reasoning",
              "unit": "token",
              "cost_usd": "0.00000028"
            }
          ]
        }
      ],
      "is_ready": false,
      "is_free": false,
      "openrouter": {
        "slug": "xiaomi/mimo-v2.6-flash"
      },
      "deployment_region": "US"
    },
    {
      "schema_version": "2.4",
      "id": "qwen/qwen3.8-flash",
      "name": "Qwen: Qwen3.8 Flash",
      "hugging_face_id": "Qwen/Qwen3.8-Flash-Next",
      "created": 1787773060,
      "quantization": null,
      "description": "Qwen3.8 Flash served by Redline: low-latency inference for long-context, agentic workloads.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 1000000,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.00000015"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.000000016"
            }
          ]
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 65536,
            "unit": "token"
          },
          "streaming": true,
          "supported_parameters": {
            "temperature": {
              "type": "range",
              "min": 0,
              "max": 2
            },
            "top_p": {
              "type": "range",
              "min": 0,
              "max": 1
            },
            "max_tokens": {
              "type": "integer",
              "min": 1,
              "max": 65536,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "tools": {
              "type": "boolean"
            },
            "structured_outputs": {
              "type": "boolean"
            },
            "reasoning": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.00000047"
            },
            {
              "type": "internal_reasoning",
              "unit": "token",
              "cost_usd": "0.00000047"
            }
          ]
        }
      ],
      "is_ready": false,
      "is_free": false,
      "openrouter": {
        "slug": "qwen/qwen3.8-flash"
      },
      "deployment_region": "US"
    },
    {
      "schema_version": "2.4",
      "id": "z-ai/glm-5.3-flash",
      "name": "Z.ai: GLM 5.3 Flash",
      "hugging_face_id": "zai-org/GLM-5.3-Flash",
      "created": 1787752741,
      "quantization": null,
      "description": "GLM 5.3 Flash served by Redline: low-latency inference for long-context, agentic workloads.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 1048576,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.00000013"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.000000027"
            }
          ]
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 65536,
            "unit": "token"
          },
          "streaming": true,
          "supported_parameters": {
            "temperature": {
              "type": "range",
              "min": 0,
              "max": 2
            },
            "top_p": {
              "type": "range",
              "min": 0,
              "max": 1
            },
            "max_tokens": {
              "type": "integer",
              "min": 1,
              "max": 65536,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "tools": {
              "type": "boolean"
            },
            "structured_outputs": {
              "type": "boolean"
            },
            "reasoning": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.00000045"
            },
            {
              "type": "internal_reasoning",
              "unit": "token",
              "cost_usd": "0.00000045"
            }
          ]
        }
      ],
      "is_ready": false,
      "is_free": false,
      "openrouter": {
        "slug": "z-ai/glm-5.3-flash"
      },
      "deployment_region": "US"
    }
  ]
}