Skip to main content

Invoke Large Model Service

POST 

/v1/ai/:model/:path

When additional path segments are required to call a model, append the path parameter, for example v1/chat/completions. Refer to the documentation for each model for the exact path definitions.

Streaming Output (server-sent events)

When streaming output is enabled, explicitly set Accept: text/event-stream in the request header; otherwise the request will time out after 60 seconds.

Request

Responses

Returned when the model call succeeds (the business result may still indicate an error)

Response Headers
    X-Request-Id

    Request ID