List enabled inference models

GET

https://api.islo.dev/inference/models

GET

/inference/models

curl https://api.islo.dev/inference/models \
     -H "Authorization: Bearer <api_key>"

{
  "models": [
    {
      "id": "string",
      "upstream_model_id": "string",
      "upstream_provider": "fireworks",
      "display_name": "string",
      "aliases": [
        "string"
      ],
      "client_apis": [
        "openai_chat_completions"
      ],
      "enabled": true,
      "input_cents_per_1m_tokens": "string",
      "cached_input_cents_per_1m_tokens": "string",
      "cache_write_input_cents_per_1m_tokens": "string",
      "output_cents_per_1m_tokens": "string",
      "pricing_tiers": [
        {
          "input_cents_per_1m_tokens": "string",
          "cached_input_cents_per_1m_tokens": "string",
          "output_cents_per_1m_tokens": "string",
          "min_input_tokens": 0,
          "max_input_tokens": 1,
          "cache_write_input_cents_per_1m_tokens": "string"
        }
      ]
    }
  ],
  "effort": {
    "levels": [
      {
        "harness": "codex",
        "model": "string",
        "levels": [
          "string"
        ],
        "label": "string"
      }
    ],
    "aliases": [
      {
        "harness": "codex",
        "id": "string",
        "model": "string",
        "effort": "string"
      }
    ]
  }
}

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Response

Successful Response

modelslist of objectsOptional

effortobjectOptional

Everything about reasoning effort, in one place.

Deliberately not on InferenceModelCatalogEntry: that row exists for gateway egress allowlisting, alias rewriting and billing, and effort is a harness CLI concern with no bearing on any of them.

Errors

401

Unauthorized Error

422

Unprocessable Entity Error