GET/v1/models

List models

Every model this key can call, and nothing it cannot: the list equals what the gateway serves to you. Each OpenAI model object carries Experiential extensions: pricing (integer nano-USD per million tokens), data_policy, and the lead route's capabilities.

Where a free promotion covers a model for your organization, its <slug>:free spelling is listed right after it with every price at 0.

認証: AuthorizationヘッダーにBearer形式のAPIキー

レスポンス

  • 200

    The models this key can call.

    レスポンス
    • objectstring
    • dataarray<object>
      data
      • idstring

        The slug to send as model.

      • objectstring
      • createdinteger

        Unix seconds.

      • owned_bystring
      • context_window_tokensinteger | null

        Prompt plus maximum output. Not your input budget: subtract maximum_output_tokens.

      • maximum_output_tokensinteger | null
      • supports_toolsboolean | null
      • supports_structured_outputboolean
      • supports_reasoningboolean
      • supported_reasoning_effortsarray<string>
      • reasoning_effortstring | null

        The default effort.

      • pricingobject

        List prices of the lead route, in integer nano-USD per million tokens (1,000,000,000 = 1 USD). null means unknown, never free.

        pricing
        • input_nano_usd_per_million_tokensinteger | null
        • cached_input_nano_usd_per_million_tokensinteger | null
        • output_nano_usd_per_million_tokensinteger | null
        • cache_write_nano_usd_per_million_tokensinteger | null
      • data_policyobject

        How the providers that may serve you treat data, under your organization's policy.

        data_policy
        • zdrboolean

          Every route that may serve you retains no data.

        • zdr_on_requestboolean

          With zero-data-retention routing on, this model can still be served with every attempt bound to a retention-free upstream.

        • no_trainingboolean

          No route that may serve you trains on your data.

        • providersarray<object>
          providers
          • providerstring
          • zdrboolean
          • zdr_on_requestboolean
          • no_trainingboolean
      • uncensoredboolean

        The model carries the uncensored catalog tag.

  • 401

    The key is missing, malformed, expired or revoked.

    レスポンス
    • errorobject
      error
      • messagestring

        What went wrong and how to fix it.

      • typestring

        For example invalid_request_error, authentication_error, permission_error, rate_limit_error, insufficient_quota, api_error.

      • codestring

        The stable error code.

      • paramstring | null

        The request field at fault, when there is one.

      • refusal_reasonenum

        Present only on code: refusal.

        "cyber_policy""cbrn""content_policy""recitation""data_inspection""unspecified"
  • 429

    insufficient_quota (out of credits, over a spend limit, or the model needs a purchase) and promo_credits_now (a free promotion is used up): add credits, the message names the step. rate_limit_exceeded, free_limit_reached, admission_capacity_exceeded: wait Retry-After seconds and retry.

    レスポンス
    • errorobject
      error
      • messagestring

        What went wrong and how to fix it.

      • typestring

        For example invalid_request_error, authentication_error, permission_error, rate_limit_error, insufficient_quota, api_error.

      • codestring

        The stable error code.

      • paramstring | null

        The request field at fault, when there is one.

      • refusal_reasonenum

        Present only on code: refusal.

        "cyber_policy""cbrn""content_policy""recitation""data_inspection""unspecified"
  • 503

    gateway_unavailable, gateway_draining, unavailable_route or deadline_exceeded. Retry with backoff, honoring Retry-After when present.

    レスポンス
    • errorobject
      error
      • messagestring

        What went wrong and how to fix it.

      • typestring

        For example invalid_request_error, authentication_error, permission_error, rate_limit_error, insufficient_quota, api_error.

      • codestring

        The stable error code.

      • paramstring | null

        The request field at fault, when there is one.

      • refusal_reasonenum

        Present only on code: refusal.

        "cyber_policy""cbrn""content_policy""recitation""data_inspection""unspecified"

リクエスト

curl https://api.experientiallabs.ai/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

レスポンス

{
  "object": "list",
  "data": [
    {
      "id": "gpt-6-luna",
      "object": "model",
      "created": 0,
      "owned_by": "exp",
      "context_window_tokens": 1050000,
      "maximum_output_tokens": 128000,
      "supports_tools": true,
      "supports_structured_output": true,
      "pricing": {
        "input_nano_usd_per_million_tokens": 100000000,
        "cached_input_nano_usd_per_million_tokens": 10000000,
        "output_nano_usd_per_million_tokens": 500000000,
        "cache_write_nano_usd_per_million_tokens": 125000000
      },
      "data_policy": {
        "zdr": false,
        "zdr_on_request": false,
        "no_training": true,
        "providers": [
          {
            "provider": "openai",
            "zdr": false,
            "zdr_on_request": false,
            "no_training": true
          }
        ]
      },
      "uncensored": false
    }
  ]
}

https://api.experientiallabs.ai/v1/models