Models API

UsageGuard supports a large number of models that can be used to generate content using our Unified Inference API. You can use the Models API to list all available models and their capabilities.

We are continuing to add more models and modalities as we grow and with customers feedback, please check back often.

GET/v1/management/models

List Available Models

Retrieve a list of all available AI models. Use this to see which models you can use for inference and their capabilities.

Request Headers

  • Name
    Authorization
    Type
    string
    Description

    Bearer token for authentication. Format: 'Bearer your-token-here'

  • Name
    traceparent
    Type
    string
    Description

    OpenTelemetry trace parent for distributed tracing

  • Name
    tracestate
    Type
    string
    Description

    OpenTelemetry trace state information

Query Parameters

  • Name
    page
    Type
    integer
    Description

    Page number for pagination. Defaults to 1.

  • Name
    pageSize
    Type
    integer
    Description

    Number of items per page. Defaults to 10.

Response Properties

  • Name
    items
    Type
    array
    Description

    Array of available models

    • Name
      modelId
      Type
      string
      Description

      Unique identifier for the model

    • Name
      displayName
      Type
      string
      Description

      Human-readable name of the model

    • Name
      provider
      Type
      string
      Description

      The provider of the model (e.g., OpenAI, Anthropic)

    • Name
      capabilities
      Type
      array
      Description

      List of capabilities supported by the model

    • Name
      isEnabled
      Type
      boolean
      Description

      Whether the model is currently available for use

    • Name
      isPremium
      Type
      boolean
      Description

      Whether this is a premium model

    • Name
      maxTokens
      Type
      integer
      Description

      Maximum number of tokens the model can process

    • Name
      contextWindow
      Type
      integer
      Description

      Maximum context window size in tokens

  • Name
    page
    Type
    integer
    Description

    Current page number

  • Name
    pageSize
    Type
    integer
    Description

    Number of items per page

  • Name
    totalCount
    Type
    integer
    Description

    Total number of available models

Request

GET
/v1/management/models
curl -X GET https://api.usageguard.com/v1/management/models?page=1&pageSize=10 \
  -H "Authorization: Bearer {token}" \
  -H "traceparent: {traceparent}" \
  -H "tracestate: {tracestate}"

Response

{
  "items": [
    {
      "modelId": "openai-gpt4",
      "displayName": "GPT-4",
      "provider": "OpenAI",
      "capabilities": ["text-generation", "chat", "streaming"],
      "isEnabled": true,
      "isPremium": true,
      "maxTokens": 8192,
      "contextWindow": 8192
    }
  ],
  "page": 1,
  "pageSize": 10,
  "totalCount": 1
}

401: Unauthorized

{
  "error": "Unauthorized",
  "message": "Invalid or expired token"
}

403: Forbidden

{
  "error": "Forbidden",
  "message": "Insufficient permissions"
}

Was this page helpful?