{
  "currency": "USD",
  "unit": "million_tokens",
  "updated": "2026-09-07T09:09:41.295Z",
  "models": [
    {
      "slug": "llama-3-1-8b",
      "modelId": "meta-llama/Llama-3.1-8B-Instruct",
      "input": 0.03,
      "output": 0.05,
      "context": 131072,
      "nativeContext": 131072,
      "quantization": "Not verified",
      "license": "Llama 3.1 Community",
      "contextKind": "native",
      "pricingStatus": "configured"
    },
    {
      "slug": "deepseek-v4-flash",
      "modelId": "deepseek-ai/DeepSeek-V4-Flash",
      "input": 0.09,
      "output": 0.18,
      "context": 131072,
      "nativeContext": 1048576,
      "quantization": "Not verified",
      "license": "MIT",
      "contextKind": "published",
      "pricingStatus": "configured"
    },
    {
      "slug": "gemma-3-27b",
      "modelId": "google/gemma-3-27b-it",
      "input": 0.1,
      "output": 0.15,
      "context": 131072,
      "nativeContext": 131072,
      "quantization": "Not verified",
      "license": "Gemma Terms of Use",
      "contextKind": "native",
      "pricingStatus": "configured"
    },
    {
      "slug": "mistral-small-3",
      "modelId": "mistralai/Mistral-Small-24B-Instruct-2501",
      "input": 0.1,
      "output": 0.2,
      "context": 32768,
      "nativeContext": 32768,
      "quantization": "Not verified",
      "license": "Apache 2.0",
      "contextKind": "native",
      "pricingStatus": "configured"
    },
    {
      "slug": "qwen3-coder-next",
      "modelId": "Qwen/Qwen3-Coder-Next",
      "input": 0.12,
      "output": 0.8,
      "context": 131072,
      "nativeContext": 262144,
      "quantization": "Not verified",
      "license": "Apache 2.0",
      "contextKind": "native",
      "pricingStatus": "configured"
    },
    {
      "slug": "hermes-4-70b",
      "modelId": "NousResearch/Hermes-4-70B",
      "input": 0.13,
      "output": 0.4,
      "context": 131072,
      "nativeContext": 131072,
      "quantization": "Not verified",
      "license": "Meta Llama Community",
      "contextKind": "published",
      "pricingStatus": "configured"
    },
    {
      "slug": "mistral-small-4",
      "modelId": "mistralai/Mistral-Small-4-119B-2603",
      "input": 0.15,
      "output": 0.6,
      "context": 131072,
      "nativeContext": 262144,
      "quantization": "Not verified",
      "license": "Apache 2.0",
      "contextKind": "published",
      "pricingStatus": "configured"
    },
    {
      "slug": "qwen3-32b",
      "modelId": "Qwen/Qwen3-32B",
      "input": 0.15,
      "output": 0.2,
      "context": 131072,
      "nativeContext": 32768,
      "quantization": "Not verified",
      "license": "Apache 2.0",
      "contextKind": "native",
      "pricingStatus": "configured"
    },
    {
      "slug": "dolphin-mistral-24b-venice-edition",
      "modelId": "dphn/Dolphin-Mistral-24B-Venice-Edition",
      "input": 0.2,
      "output": 0.9,
      "context": 131072,
      "nativeContext": 131072,
      "quantization": "Not verified",
      "license": "Apache 2.0",
      "contextKind": "published",
      "pricingStatus": "configured"
    },
    {
      "slug": "qwen3-235b-a22b",
      "modelId": "Qwen/Qwen3-235B-A22B-Instruct-2507",
      "input": 0.2,
      "output": 0.6,
      "context": 131072,
      "nativeContext": 262144,
      "quantization": "Not verified",
      "license": "Apache 2.0",
      "contextKind": "native",
      "pricingStatus": "configured"
    },
    {
      "slug": "deepseek-v3",
      "modelId": "deepseek-ai/DeepSeek-V3-0324",
      "input": 0.25,
      "output": 0.85,
      "context": 131072,
      "nativeContext": 131072,
      "quantization": "Not verified",
      "license": "MIT",
      "contextKind": "native",
      "pricingStatus": "configured"
    },
    {
      "slug": "llama-3-3-70b",
      "modelId": "meta-llama/Llama-3.3-70B-Instruct",
      "input": 0.35,
      "output": 0.4,
      "context": 131072,
      "nativeContext": 131072,
      "quantization": "Not verified",
      "license": "Llama 3.3 Community",
      "contextKind": "native",
      "pricingStatus": "configured"
    },
    {
      "slug": "deepseek-r1",
      "modelId": "deepseek-ai/DeepSeek-R1-0528",
      "input": 0.5,
      "output": 2.15,
      "context": 131072,
      "nativeContext": 131072,
      "quantization": "Not verified",
      "license": "MIT",
      "contextKind": "native",
      "pricingStatus": "configured"
    },
    {
      "slug": "mixtral-8x22b",
      "modelId": "mistralai/Mixtral-8x22B-Instruct-v0.1",
      "input": 0.6,
      "output": 0.6,
      "context": 65536,
      "nativeContext": 65536,
      "quantization": "Not verified",
      "license": "Apache 2.0",
      "contextKind": "native",
      "pricingStatus": "configured"
    },
    {
      "slug": "llama-3-1-405b",
      "modelId": "meta-llama/Llama-3.1-405B-Instruct",
      "input": 1.2,
      "output": 1.2,
      "context": 131072,
      "nativeContext": 131072,
      "quantization": "Not verified",
      "license": "Llama 3.1 Community",
      "contextKind": "native",
      "pricingStatus": "configured"
    }
  ],
  "dedicated": [
    [
      "L40S",
      "48 GB",
      520
    ],
    [
      "A100",
      "80 GB",
      990
    ],
    [
      "H100 SXM",
      "80 GB",
      1690
    ],
    [
      "H200",
      "141 GB",
      2290
    ],
    [
      "2 × H100",
      "160 GB",
      3210
    ],
    [
      "8 × H100",
      "640 GB",
      12170
    ]
  ],
  "services": [
    [
      "Embeddings",
      "1M tokens",
      0.008
    ],
    [
      "Reranking",
      "per request",
      null
    ],
    [
      "Audio transcription",
      "minute",
      0.003
    ],
    [
      "Image generation",
      "image",
      0.02
    ]
  ]
}