OpenAI Responses接口兼容

Python

import os
from openai import OpenAI

client = OpenAI(
    # If environment variable is not set, replace with: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

response = client.responses.create(
    model="qwen3.7-plus",
    input="What can you do?"
)

# Get model response
# print(response.model_dump_json())
print(response.output_text)

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    // If environment variable is not set, replace with: apiKey: "sk-xxx"
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const response = await openai.responses.create({
        model: "qwen3.7-plus",
        input: "What can you do?"
    });

    // Get model response
    console.log(response.output_text);
}

main();

curl

curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-plus",
    "input": "What can you do?"
}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

# First round
response1 = client.responses.create(
    model="qwen3.7-plus",
    input="My name is John, please remember it."
)
print(f"First response: {response1.output_text}")

# Second round - use previous_response_id to link context
# The response id expires in 7 days
response2 = client.responses.create(
    model="qwen3.7-plus",
    input="Do you remember my name?",
    previous_response_id=response1.id
)
print(f"Second response: {response2.output_text}")

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    // First round
    const response1 = await openai.responses.create({
        model: "qwen3.7-plus",
        input: "My name is John, please remember it."
    });
    console.log(`First response: ${response1.output_text}`);

    // Second round - use previous_response_id to link context
    // The response id expires in 7 days
    const response2 = await openai.responses.create({
        model: "qwen3.7-plus",
        input: "Do you remember my name?",
        previous_response_id: response1.id
    });
    console.log(`Second response: ${response2.output_text}`);
}

main();

curl

# First round
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-plus",
    "input": "My name is John, please remember it."
}'

# Second round - use the id from first response as previous_response_id
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-plus",
    "input": "Do you remember my name?",
    "previous_response_id": "response_id_from_first_round"
}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

response = client.responses.create(
    model="qwen3.7-plus",
    input="9.9和9.11谁大？",
    reasoning={"effort": "medium"}
)

# 处理输出
for item in response.output:
    if item.type == "reasoning":
        print("=== 思考过程 ===")
        for summary in item.summary:
            print(summary.text)
    elif item.type == "message":
        print("\n=== 最终答案 ===")
        print(item.content[0].text)

# 查看思考 Token 数
print(f"\n思考 Token 数: {response.usage.output_tokens_details.reasoning_tokens}")

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const response = await openai.responses.create({
        model: "qwen3.7-plus",
        input: "9.9和9.11谁大？",
        reasoning: { effort: "medium" }
    });

    for (const item of response.output) {
        if (item.type === "reasoning") {
            console.log("=== 思考过程 ===");
            for (const summary of item.summary) {
                console.log(summary.text);
            }
        } else if (item.type === "message") {
            console.log("\n=== 最终答案 ===");
            console.log(item.content[0].text);
        }
    }

    // 查看思考 Token 数
    console.log(`\n思考 Token 数: ${response.usage.output_tokens_details.reasoning_tokens}`);
}

main();

curl

curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-plus",
    "input": "9.9和9.11谁大？",
    "reasoning": {"effort": "medium"}
}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

stream = client.responses.create(
    model="qwen3.7-plus",
    input="Please briefly introduce artificial intelligence.",
    stream=True
)

print("Receiving stream output:")
for event in stream:
    # print(event.model_dump_json())  # Uncomment to see raw event response
    if event.type == 'response.output_text.delta':
        print(event.delta, end='', flush=True)
    elif event.type == 'response.completed':
        print("\nStream completed")
        print(f"Total tokens: {event.response.usage.total_tokens}")

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const stream = await openai.responses.create({
        model: "qwen3.7-plus",
        input: "Please briefly introduce artificial intelligence.",
        stream: true
    });

    console.log("Receiving stream output:");
    for await (const event of stream) {
        // console.log(JSON.stringify(event));  // Uncomment to see raw event response
        if (event.type === 'response.output_text.delta') {
            process.stdout.write(event.delta);
        } else if (event.type === 'response.completed') {
            console.log("\nStream completed");
            console.log(`Total tokens: ${event.response.usage.total_tokens}`);
        }
    }
}

main();

curl

curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-plus",
    "input": "Please briefly introduce artificial intelligence.",
    "stream": true
}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

response = client.responses.create(
    model="qwen3.7-plus",
    input="Find the Alibaba Cloud website and extract key information",
    # For best results, enable all the built-in tools
    tools=[
        {"type": "web_search"},
        {"type": "code_interpreter"},
        {"type": "web_extractor"}
    ],
    reasoning={"effort": "medium"}
)

# Uncomment the line below to see the intermediate output
# print(response.output)
print(response.output_text)

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const response = await openai.responses.create({
        model: "qwen3.7-plus",
        input: "Find the Alibaba Cloud website and extract key information",
        tools: [
            { type: "web_search" },
            { type: "code_interpreter" },
            { type: "web_extractor" }
        ],
        reasoning: { effort: "medium" }
    });

    for (const item of response.output) {
        if (item.type === "reasoning") {
            console.log("Model is thinking...");
        } else if (item.type === "web_search_call") {
            console.log(`Search query: ${item.action.query}`);
        } else if (item.type === "web_extractor_call") {
            console.log("Extracting web content...");
        } else if (item.type === "message") {
            console.log(`Response: ${item.content[0].text}`);
        }
    }
}

main();

curl

curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-plus",
    "input": "Find the Alibaba Cloud website and extract key information",
    "tools": [
        {
            "type": "web_search"
        },
        {
            "type": "code_interpreter"
        },
        {
            "type": "web_extractor"
        }
    ],
    "reasoning": {"effort": "medium"}
}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
    # 通过 default_headers 开启 Session 缓存
    default_headers={"x-dashscope-session-cache": "enable"}
)

# 构造超过 1024 Token 的长文本，确保能触发缓存创建（若未达到1024 Token，后续累积对话上下文超过1024 Token时将触发缓存创建）
long_context = "人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。" * 50

# 第一轮对话
response1 = client.responses.create(
    model="qwen3.7-plus",
    input=long_context + "\n\n基于以上背景知识，请简短介绍机器学习中的随机森林算法。",
)
print(f"第一轮回复: {response1.output_text}")

# 第二轮对话：通过 previous_response_id 关联上下文，缓存由服务端自动处理
response2 = client.responses.create(
    model="qwen3.7-plus",
    input="它和 GBDT 有什么主要区别？",
    previous_response_id=response1.id,
)
print(f"第二轮回复: {response2.output_text}")

# 查看缓存命中情况
usage = response2.usage
print(f"输入 Token: {usage.input_tokens}")
print(f"缓存命中 Token: {usage.input_tokens_details.cached_tokens}")

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
    // 通过 defaultHeaders 开启 Session 缓存
    defaultHeaders: {"x-dashscope-session-cache": "enable"}
});

// 构造超过 1024 Token 的长文本，确保能触发缓存创建（若未达到1024 Token，后续累积对话上下文超过1024 Token时将触发缓存创建）
const longContext = "人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。".repeat(50);

async function main() {
    // 第一轮对话
    const response1 = await openai.responses.create({
        model: "qwen3.7-plus",
        input: longContext + "\n\n基于以上背景知识，请简短介绍机器学习中的随机森林算法，包括基本原理和应用场景。"
    });
    console.log(`第一轮回复: ${response1.output_text}`);

    // 第二轮对话：通过 previous_response_id 关联上下文，缓存由服务端自动处理
    const response2 = await openai.responses.create({
        model: "qwen3.7-plus",
        input: "它和 GBDT 有什么主要区别？",
        previous_response_id: response1.id
    });
    console.log(`第二轮回复: ${response2.output_text}`);

    // 查看缓存命中情况
    console.log(`输入 Token: ${response2.usage.input_tokens}`);
    console.log(`缓存命中 Token: ${response2.usage.input_tokens_details.cached_tokens}`);
}

main();

curl

# 第一轮对话
# 请将 input 替换为超过 1024 Token 的长文本，以确保触发缓存创建
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-H "x-dashscope-session-cache: enable" \
-d '{
    "model": "qwen3.7-plus",
    "input": "人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。人工智能是计算机科学的一个重要分支，致力于研究和开发能够模拟、延伸和扩展人类智能的理论、方法、技术及应用系统。\n\n基于以上背景知识，请简短介绍机器学习中的随机森林算法，包括基本原理和应用场景。"
}'

# 第二轮对话 - 使用上一轮返回的 id 作为 previous_response_id
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-H "x-dashscope-session-cache: enable" \
-d '{
    "model": "qwen3.7-plus",
    "input": "它和 GBDT 有什么主要区别？",
    "previous_response_id": "第一轮返回的响应id"
}'

Python

# Chat Completions API
completion = client.chat.completions.create(
    model="qwen3.7-plus",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)
print(completion.choices[0].message.content)

# Responses API - can use the same message format
response = client.responses.create(
    model="qwen3.7-plus",
    input=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.output_text)

# Responses API - or use a more concise format
response = client.responses.create(
    model="qwen3.7-plus",
    input="Hello!"
)
print(response.output_text)

Node.js

// Chat Completions API
const completion = await client.chat.completions.create({
    model: "qwen3.7-plus",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        { role: "user", content: "Hello!" }
    ]
});
console.log(completion.choices[0].message.content);

// Responses API - can use the same message format
const response = await client.responses.create({
    model: "qwen3.7-plus",
    input: [
        { role: "system", content: "You are a helpful assistant." },
        { role: "user", content: "Hello!" }
    ]
});
console.log(response.output_text);

// Responses API - or use a more concise format
const response2 = await client.responses.create({
    model: "qwen3.7-plus",
    input: "Hello!"
});
console.log(response2.output_text);

curl

# Chat Completions API
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-plus",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
}'

# Responses API - use a more concise format
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-plus",
    "input": "Hello!"
}'

Python

# Chat Completions - manual message history management
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is the capital of France?"}
]
res1 = client.chat.completions.create(
    model="qwen3.7-plus",
    messages=messages
)

# Manually add response to history
messages.append(res1.choices[0].message)
messages.append({"role": "user", "content": "What is its population?"})

res2 = client.chat.completions.create(
    model="qwen3.7-plus",
    messages=messages
)

# Responses API - automatic linking with previous_response_id
res1 = client.responses.create(
    model="qwen3.7-plus",
    input="What is the capital of France?"
)

# Just pass the previous response ID
res2 = client.responses.create(
    model="qwen3.7-plus",
    input="What is its population?",
    previous_response_id=res1.id
)

Node.js

// Chat Completions - manual message history management
let messages = [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "What is the capital of France?" }
];
const res1 = await client.chat.completions.create({
    model: "qwen3.7-plus",
    messages
});

// Manually add response to history
messages = messages.concat([res1.choices[0].message]);
messages.push({ role: "user", content: "What is its population?" });

const res2 = await client.chat.completions.create({
    model: "qwen3.7-plus",
    messages
});

// Responses API - automatic linking with previous_response_id
const res1 = await client.responses.create({
    model: "qwen3.7-plus",
    input: "What is the capital of France?"
});

// Just pass the previous response ID
const res2 = await client.responses.create({
    model: "qwen3.7-plus",
    input: "What is its population?",
    previous_response_id: res1.id
});

Python

# Chat Completions - need to implement tool functions yourself
def web_search(query):
    # Need to implement web search logic yourself
    import requests
    r = requests.get(f"https://api.example.com/search?q={query}")
    return r.json().get("results", [])

completion = client.chat.completions.create(
    model="qwen3.7-plus",
    messages=[{"role": "user", "content": "Who is the current president of France?"}],
    functions=[{
        "name": "web_search",
        "description": "Search the web for information",
        "parameters": {
            "type": "object",
            "properties": {"query": {"type": "string"}},
            "required": ["query"]
        }
    }]
)

# Responses API - use built-in tools directly
response = client.responses.create(
    model="qwen3.7-plus",
    input="Who is the current president of France?",
    tools=[{"type": "web_search"}]  # Enable web search directly
)
print(response.output_text)

Node.js

// Chat Completions - need to implement tool functions yourself
async function web_search(query) {
    const fetch = (await import('node-fetch')).default;
    const res = await fetch(`https://api.example.com/search?q=${query}`);
    const data = await res.json();
    return data.results;
}

const completion = await client.chat.completions.create({
    model: "qwen3.7-plus",
    messages: [{ role: "user", content: "Who is the current president of France?" }],
    functions: [{
        name: "web_search",
        description: "Search the web for information",
        parameters: {
            type: "object",
            properties: { query: { type: "string" } },
            required: ["query"]
        }
    }]
});

// Responses API - use built-in tools directly
const response = await client.responses.create({
    model: "qwen3.7-plus",
    input: "Who is the current president of France?",
    tools: [{ type: "web_search" }]  // Enable web search directly
});
console.log(response.output_text);

curl

# Chat Completions - need to implement tools yourself
# Example of calling an external search API
curl https://api.example.com/search \
  -G \
  --data-urlencode "q=current president of France" \
  --data-urlencode "key=$SEARCH_API_KEY"

# Responses API - use built-in tools directly
curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-plus",
    "input": "Who is the current president of France?",
    "tools": [{"type": "web_search"}]
}'