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

Path Parameters

model anyrequired

The code of the model to invoke. You can use any model group provided by the following platforms:
hunyuan-exp: Hunyuan trial edition
deepseek: Trial edition


You can also specify any custom model group configured in the console.

path stringrequired

The request path defined by the model provider, for example v1/chat/completions

application/json

Body

required

Refer to the documentation of each model for the parameters required in the request body.

object

Responses

200

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

Response Headers

• X-Request-Id string

  Request ID

application/json

Schema

Schema

property name* any

Example (from schema)

{
  "created": 1723618716,
  "id": "xxx",
  "model": "hunyuan",
  "version": "202403121316",
  "choices": [
    {
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "I am an AI assistant developed by Tencent. How can I help you today?"
      }
    }
  ],
  "search_info": {
    "mindmap": {}
  },
  "processes": {},
  "usage": {
    "prompt_tokens": 11,
    "completion_tokens": 14,
    "total_tokens": 25
  }
}

text/event-stream

Schema

Schema

string

400

Request failed

Response Headers

• X-Request-Id string

  Request ID

application/json

Schema

Schema

code string

Error code

message string

Error message

requestId string

Request ID

Example (from schema)

{
  "code": "string",
  "message": "string",
  "requestId": "string"
}

AIModelConfigMissing

Missing required configuration for calling the model, such as token or clientID (400)

{
  "code": "AI_MODEL_CONFIG_MISSING",
  "message": "xxx",
  "requestId": "xxx"
}

AIModelParamInvalid

Invalid parameters provided when calling the model (400)

{
  "code": "AI_MODEL_PARAM_INVALID",
  "message": "xxx",
  "requestId": "xxx"
}

AIModelRequestFailed

Request to the model failed (400)

{
  "code": "AI_MODEL_REQUEST_FAILED",
  "message": "xxx",
  "requestId": "xxx"
}

404

Request failed

Response Headers

• X-Request-Id string

  Request ID

application/json

Schema

Schema

code string

Error code

message string

Error message

requestId string

Request ID

Example (from schema)

{
  "code": "string",
  "message": "string",
  "requestId": "string"
}

FeatureNotConfigured

The large model feature is not enabled (404)

{
  "code": "ENV_FEATURE_NOT_CONFIGURED",
  "message": "xxx",
  "requestId": "xxx"
}

AIModelNotFound

The specified model was not found (404)

{
  "code": "AI_MODEL_NOT_FOUND",
  "message": "xxx",
  "requestId": "xxx"
}

default

Common error information, see https://docs.cloudbase.net/error-code/service for details

Response Headers

• X-Request-Id string

  Request ID

application/json

Schema

Schema

code string

Error code

message string

Error message

requestId string

Request ID

Example (from schema)

{
  "code": "string",
  "message": "string",
  "requestId": "string"
}

InvalidHost

Invalid request address

{
  "code": "INVALID_HOST",
  "message": "xxx",
  "requestId": "xxx"
}

Loading...