standard_completions_model_features.json5

// curl -H "Authorization: Bearer ..." "https://$BASE_URL/models/features"
{
  "host_fingerprint": "provider", // should be a unique string for the host or router (e.g. deepseek, openrouter, litellm)
  "data": [
    {
      // Required
      "id": "provider/model",
      "name": "Provider: Model",
      // should either match host_fingerprint if this is a primary provider (ie deepseek) or match the host_fingerprint of
      // the upstream provider, if this is a router. i.e., this string should never be "litellm"
      "provider": "provider",
      "created": 1690502400,
      "input_modalities": ["text", "image", "audio"],
      "output_modalities": ["text", "image"],
      "quantization": "fp8",
      "context_length": 1000000,
      "max_output_length": 128000,
      "pricing": {
        "text": {
          "input_token": "0.000008",
          "output_token": "0.000024"
        },
        "image": {
          "input_token": "0",
          "output_token": "0"
        },
        "audio": {
          "input_token": "0"
        }
        // should we also have cache here? or as a multiplier? or per-modality?
      },
      "supported_sampling_parameters": ["temperature", "stop"],
      "supported_features": [
        "tools",
        "json_mode",
        "structured_outputs",
        "web_search",
        "reasoning",
        "logprobs",
        "assistant_prefix",
      ],
      // e.g., if a chat model can also be queried in completion mode. base models would only support "completions"
      "supported_endpoints": ["completions", "chat_completions"],
      "max_logprobs": 20,
      // Optional extra data, ie provider-specific, or for openrouter
      "extra": {
        "openrouter": {},
      },
    }
  ]
}

Ah, that's a good point. Hm.

Really price is a tensor of modality x reasoning x caching :-)