Copy

This document describes the input and output parameters for invoking Alibaba Cloud Bailian workflow applications through the DashScope API.

Prerequisites

Before you begin, ensure you have completed the following steps:

Create an application: Go to Application Management to create a Bailian workflow application and obtain your app_id.
Obtain an API Key: Retrieve your API Key from API Key Management and configure it as an environment variable.
Install the SDK (optional): If using an SDK, install the corresponding DashScope SDK for your programming language.

Invocation Methods

HTTP API Call Endpoint: POST https://dashscope.aliyuncs.com/api/v1/apps/{APP_ID}/completion
Replace {APP_ID} with your actual application ID.
SDK Call The Python and Java SDKs are preconfigured with the correct endpoint.

Request Body

Parameter	Type	Required	Description
app_id	string	Yes	Application identifier. Found on the application card in Application Management.
prompt	string	Yes	User’s input instruction. For HTTP calls, include this inside the `input` object.
session_id	string	No	Session identifier for conversation history. When provided, the request automatically includes previously stored conversation history from the cloud.
workspace	string	No	Business workspace identifier. Required only when invoking applications deployed under a sub-workspace.
stream	boolean	No	Whether to return responses in streaming mode. Default: `false`.
incremental_output	boolean	No	Whether to enable incremental output in streaming mode. Default: `false`.
biz_params	object	No	Custom parameters passed to the workflow application.

Code Examples

import os
from http import HTTPStatus
from dashscope import Application

response = Application.call(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    app_id='APP_ID',  # Replace with your actual app ID
    prompt='Hello')

if response.status_code != HTTPStatus.OK:
    print(f'request_id={response.request_id}')
    print(f'code={response.status_code}')
    print(f'message={response.message}')
else:
    print(response.output.text)

Response Object

Parameter	Type	Description
status_code	integer	HTTP status code. `200` indicates success.
request_id	string	Unique identifier for this API call.
code	string	Error code; empty on success.
message	string	Detailed error message; ignored on success.
output	object	Result of the invocation.
usage	object	Token usage and model information for this request.

output Properties

Parameter	Type	Description
text	string	Model-generated response content.
finish_reason	string	Reason for completion. `stop` indicates natural termination.
session_id	string	Unique identifier for the current conversation session.

usage Properties

Parameter	Type	Description
models	array	Information about models used in this request.
models[].model_id	string	Model ID.
models[].input_tokens	integer	Number of input tokens consumed.
models[].output_tokens	integer	Number of output tokens generated.

QPM Limits

The default QPM (queries per minute) limit per application is 15,000.

Error Codes

If the API call fails and returns an error, refer to the Error Code Documentation for troubleshooting.

​Prerequisites

​Invocation Methods

​Request Body

​Code Examples

​Response Object

​output Properties

​usage Properties

​QPM Limits

​Error Codes