{
  "data": [
    {
      "schema_version": "2.4",
      "id": "gemma-4-26b-a4b-it",
      "name": "Autoloops: Gemma 4 26B A4B",
      "hugging_face_id": "google/gemma-4-26B-A4B-it",
      "created": 1775174400,
      "quantization": "fp8",
      "tokenizer": "Gemma",
      "description": "Google's Gemma 4 26B A4B MoE (25.8B total / ~4B active parameters) served FP8 on dedicated US GPUs, tuned for low-latency streaming: measured TTFT p95 <= 300 ms at 800 concurrent streams with prefix-cache-optimized serving. FP8 output quality benchmarked at parity with bf16 providers (median word-level similarity 1.00 on a matched suite).",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 32768,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.00000013"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.00000005"
            }
          ],
          "capacity": [
            {
              "type": "prompt",
              "unit": "token",
              "per": "minute",
              "value": 500000
            }
          ]
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 4096,
            "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": 4096,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "frequency_penalty": {
              "type": "range",
              "min": -2,
              "max": 2
            },
            "presence_penalty": {
              "type": "range",
              "min": -2,
              "max": 2
            },
            "structured_outputs": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.00000045"
            }
          ],
          "capacity": [
            {
              "type": "completion",
              "unit": "token",
              "per": "minute",
              "value": 60000
            }
          ]
        }
      ],
      "capacity": [
        {
          "type": "request",
          "unit": "request",
          "per": "minute",
          "value": 600
        }
      ],
      "is_ready": false,
      "is_free": false,
      "discount_to_user": 0,
      "openrouter": {
        "slug": "autoloops/gemma-4-26b-a4b-it"
      },
      "datacenters": [
        {
          "country_code": "US",
          "region": "us-west-2"
        }
      ],
      "deployment_region": "US",
      "compliance": {
        "zdr": true,
        "hipaa": false
      }
    },
    {
      "schema_version": "2.4",
      "id": "gemma-4-31b-it",
      "name": "Autoloops: Gemma 4 31B",
      "hugging_face_id": "google/gemma-4-31B-it",
      "created": 1775174400,
      "quantization": "nvfp4",
      "tokenizer": "Gemma",
      "description": "Google's Gemma 4 31B instruction-tuned model with image input, served on dedicated US GPUs and tuned for low-latency streaming with prefix-cache reuse across conversation turns.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 32768,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.0000002"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.00000014"
            }
          ],
          "capacity": [
            {
              "type": "prompt",
              "unit": "token",
              "per": "minute",
              "value": 500000
            }
          ]
        },
        {
          "type": "image"
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 4096,
            "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": 4096,
              "unit": "token"
            },
            "stop": {
              "type": "array",
              "max_items": 4
            },
            "seed": {
              "type": "integer"
            },
            "frequency_penalty": {
              "type": "range",
              "min": -2,
              "max": 2
            },
            "presence_penalty": {
              "type": "range",
              "min": -2,
              "max": 2
            },
            "structured_outputs": {
              "type": "boolean"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.00000045"
            }
          ],
          "capacity": [
            {
              "type": "completion",
              "unit": "token",
              "per": "minute",
              "value": 60000
            }
          ]
        }
      ],
      "capacity": [
        {
          "type": "request",
          "unit": "request",
          "per": "minute",
          "value": 600
        }
      ],
      "is_ready": false,
      "is_free": false,
      "discount_to_user": 0,
      "openrouter": {
        "slug": "autoloops/gemma-4-31b-it"
      },
      "datacenters": [
        {
          "country_code": "US",
          "region": "us-west-2"
        }
      ],
      "deployment_region": "US",
      "compliance": {
        "zdr": true,
        "hipaa": false
      }
    },
    {
      "schema_version": "2.4",
      "id": "deepseek-v4.1-flash",
      "name": "Autoloops: DeepSeek V4.1 Flash",
      "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
      "created": 1790812800,
      "quantization": "nvfp4",
      "tokenizer": "DeepSeek",
      "description": "DeepSeek V4.1 Flash with reasoning, vision, and a one-million-token context window on dedicated US GPUs.",
      "input_modalities": [
        {
          "type": "text",
          "supported_inputs": {
            "max_context_length": {
              "value": 1048448,
              "unit": "token"
            }
          },
          "pricing": [
            {
              "type": "prompt",
              "unit": "token",
              "cost_usd": "0.000000141"
            },
            {
              "type": "cached_prompt",
              "unit": "token",
              "cost_usd": "0.00000000282"
            }
          ]
        },
        {
          "type": "image",
          "max_items": 600
        }
      ],
      "output_modalities": [
        {
          "type": "text",
          "max_length": {
            "value": 384000,
            "unit": "token"
          },
          "streaming": true,
          "supported_parameters": {
            "temperature": {
              "type": "range",
              "min": 0,
              "max": 2
            },
            "max_tokens": {
              "type": "integer",
              "min": 1,
              "max": 384000,
              "unit": "token"
            },
            "seed": {
              "type": "integer"
            },
            "reasoning_effort": {
              "type": "string"
            }
          },
          "pricing": [
            {
              "type": "completion",
              "unit": "token",
              "cost_usd": "0.000000564"
            }
          ]
        }
      ],
      "is_ready": true,
      "is_free": false,
      "discount_to_user": 0,
      "openrouter": {
        "slug": "autoloops/deepseek-v4.1-flash"
      },
      "datacenters": [
        {
          "country_code": "US",
          "region": "us-west-2"
        }
      ],
      "deployment_region": "US",
      "compliance": {
        "zdr": true,
        "hipaa": false
      }
    }
  ]
}