Base URL
Authentication
Every request must include a bearer token in theAuthorization header.
Endpoints
See Deploy a model and Run inference for full request and response schemas.
Content type
All request bodies must be JSON withContent-Type: application/json. Responses are always JSON, including error responses.
Rate limits
Rate limits are applied per API key. You can inspect current usage in the response headers of any successful call:
When you exceed the limit, the API returns
429 Too Many Requests. Retry with exponential backoff.
Errors
Errors return a JSON body with acode and message. See Errors for the full list of error codes.