Conversations | Qwen Cloud

The Conversations API automatically manages multi-turn context across devices and sessions. Use it with the Responses API to inject historical context without manual synchronization.

Prerequisites

Get an API key and export it as an environment variable. When using the OpenAI SDK, install the SDK.

Service endpoints

base_url for the SDK: https://dashscope-intl.aliyuncs.com/api/v2/apps/protocols/compatible-mode/v1 HTTP base endpoint: https://dashscope-intl.aliyuncs.com/api/v2/apps/protocols/compatible-mode/v1/conversations

Endpoints

Endpoint	Description
Create conversation	Create a conversation with optional initial message items
Retrieve conversation	Retrieve a conversation by ID
Update conversation	Update a conversation's metadata
Delete conversation	Delete a conversation
Create items	Add message items to a conversation
List items	List message items in a conversation
Retrieve item	Retrieve a message item by ID
Delete item	Delete a message item

Use conversations in the Responses API

Pass the conversation parameter to the Responses API to maintain context across turns.

Do not pass both previous_response_id and conversation. They are mutually exclusive.

Python
Node.js

import os
from openai import OpenAI

client = OpenAI(
  api_key=os.getenv("DASHSCOPE_API_KEY"),
  base_url="https://dashscope-intl.aliyuncs.com/api/v2/apps/protocols/compatible-mode/v1",
)

conversation = client.conversations.create(
  items=[
    {
      "type": "message",
      "role": "system",
      "content": "Alice, a gentle and resilient woman, was born in Singapore. She is 20 years old, and her hobbies are music and chess.",
    }
  ]
)

response1 = client.responses.create(
  conversation=conversation.id, model="qwen3.6-plus", input="How old is Alice?"
)
print(f"First response: {response1.output_text}")

response2 = client.responses.create(
  conversation=conversation.id, model="qwen3.6-plus", input="What are her hobbies?"
)
print(f"Second response: {response2.output_text}")

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.DASHSCOPE_API_KEY,
  baseURL: "https://dashscope-intl.aliyuncs.com/api/v2/apps/protocols/compatible-mode/v1",
});

const conversation = await client.conversations.create({
  items: [
    {
      type: "message",
      role: "system",
      content: "Alice, a gentle and resilient woman, was born in Singapore. She is 20 years old, and her hobbies are music and chess."
    }
  ]
});

const response1 = await client.responses.create({
  conversation: conversation.id,
  model: "qwen3.6-plus",
  input: "How old is Alice?"
});
console.log("First response:", response1.output_text);

const response2 = await client.responses.create({
  conversation: conversation.id,
  model: "qwen3.6-plus",
  input: "What are her hobbies?"
});
console.log("Second response:", response2.output_text);

Limitations

Maximum 20 items per items array in create and add operations.
Maximum 16 metadata key-value pairs (keys: max 64 chars, values: max 512 chars).

​Prerequisites

​Service endpoints

​Endpoints

​Use conversations in the Responses API

​Limitations

Prerequisites

Service endpoints

Endpoints

Use conversations in the Responses API

Limitations