Skip to main content

Invoke Large Model Service

POST 

/v1/ai/:model/:path

When invoking large models, if you need to pass an additional path, you can append the path parameter, such as v1/chat/completions. Refer to the documentation of each large model for specific path definitions.

Streaming Output (server-sent events)

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

Request

Path Parameters

    model anyrequired

    The model code to be invoked, which can be any one of the model groups provided by the following platforms:
    hunyuan-exp: Hunyuan Trial
    deepseek: Trial
    or enter any other custom model group configured on the console.

    path stringrequired

    The invocation path for the large model, such as v1/chat/completions

Body

required

Refer to the documentation of each large model for passing request parameters.

    object

Responses

When invoking large models is successful, it returns (not necessarily the correct result).

Response Headers
  • X-Request-Id string

    Request ID

Schema
    property name* any
Loading...