NEAR AI Cloud: List all models (Admin only)

GET /v1/admin/models List all models (Admin only) Returns a paginated list of all models in the system. By default, only active models are returned. Use include_inactive=true to also include disabled models.

Parameters:

• limit (query, integer): Maximum number of models to return (default: 100).
• offset (query, integer): Number of models to skip (default: 0).
• include_inactive (query, boolean): Whether to include inactive (disabled) models (default: false).

Responses: 200: Models retrieved successfully

• limit (integer, int64, required)
• models (array of object, required)
  • cacheReadCostPerToken: one of option 1: null DecimalPrice: object
  • costPerImage (object, required): Decimal price for API responses The system uses a fixed scale of 9 (nano-dollars = 1 billionth of a dollar). The scale field is included in responses for client convenience.
    • amount (integer, int64, required)
    • currency (string, required)
    • scale (integer, int64, required)
  • createdAt (string, date-time, required)
  • inputCostPerToken (object, required)
    • amount (integer, int64, required)
    • currency (string, required)
    • scale (integer, int64, required)
  • isActive (boolean, required)
  • metadata (object, required): Model metadata.
    • aliases (array of string)
    • architecture: one of
    • attestationSupported (boolean, required): Whether this model supports TEE attestation.
    • contextLength (integer, int32, required)
    • datacenters (array of object): Datacenters the model runs in (OpenRouter datacenters), e.g. [{ "country_code": "US" }]. Omitted when unset.
    • deprecationDate (string): OpenRouter deprecation_date: planned deprecation date as an ISO 8601 string. Omitted when there is no planned deprecation.
    • huggingFaceId (string): HuggingFace identifier (OpenRouter hugging_face_id).
    • inferenceUrl (string): Base URL for the model's inference endpoint.
    • isReady (boolean): OpenRouter is_ready: stored/exposed verbatim. Omitted when unset.
    • maxOutputLength (integer, int32): Maximum output tokens per response (OpenRouter max_output_length).
    • modelDescription (string, required)
    • modelDisplayName (string, required)
    • modelIcon (string)
    • openrouterSlug (string): OpenRouter openrouter.slug override (lowercase author/slug). Omitted when unset. On public GET /v1/models this surfaces as the nested openrouter: { slug } object; the admin view exposes the raw value.
    • ownedBy (string, required)
    • providerConfig: JSON config for external providers (backend, base_url, etc.).
    • providerType (string, required): Provider type: "vllm" (TEE-enabled) or "external" (3rd party).
    • quantization (string): Quantization label (int4/int8/fp4/fp6/fp8/fp16/bf16/fp32).
    • supportedFeatures (array of string): Feature capabilities (OpenRouter supported_features).
    • supportedSamplingParameters (array of string): Sampling parameters accepted by the model (OpenRouter supported_sampling_parameters).
    • verifiable (boolean, required)
  • modelId (string, required)
  • outputCostPerToken (object, required)
    • amount (integer, int64, required)
    • currency (string, required)
    • scale (integer, int64, required)
  • updatedAt (string, date-time, required)
• offset (integer, int64, required)
• total (integer, int64, required) 401: Unauthorized 500: Internal server error