INinference-gateway
Proxy

Proxy PATCH request to provider

Changed on

Proxy PATCH request to provider The request body depends on the specific provider and endpoint being called. If you decide to use this approach, please follow the provider-specific documentations.

patch/proxy/{provider}/{path}

Request

  • Base URL
    http://localhost:8080
  • URL
    http://localhost:8080/proxy/{provider}/{path}
  • Auth
    HTTP bearer

Request body

modelstring
temperaturenumber float

Response

ProviderResponse depends on the specific provider and endpoint being called If you decide to use this approach, please follow the provider-specific documentations.

ProviderSpecificResponse required

Provider-specific response format. Examples:

OpenAI GET /v1/models?provider=openai response:

{
  "provider": "openai",
  "object": "list",
  "data": [
    {
      "id": "gpt-4",
      "object": "model",
      "created": 1687882410,
      "owned_by": "openai",
      "served_by": "openai"
    }
  ]
}

Anthropic GET /v1/models?provider=anthropic response:

{
  "provider": "anthropic",
  "object": "list",
  "data": [
    {
      "id": "gpt-4",
      "object": "model",
      "created": 1687882410,
      "owned_by": "openai",
      "served_by": "openai"
    }
  ]
}

Changes