OpenAI-compatible - Responses

Python

import os
from openai import OpenAI

client = OpenAI(
    # If an environment variable is not set, replace with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)

response = client.responses.create(
    model="qwen3.7-plus",
    input="你能做些什么？"
)

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

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    # If an environment variable is not set, replace with your Model Studio API key: apiKey: "sk-xxx"
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const response = await openai.responses.create({
        model: "qwen3.7-plus",
        input: "你能做些什么？"
    });

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

main();

Curl

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-plus",
    "input": "你能做些什么？"
}'

Python

import os
from openai import OpenAI

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

# First round
response1 = client.responses.create(
    model="qwen3.7-plus",
    input="My name is Alice, 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://dashscope.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    // First round
    const response1 = await openai.responses.create({
        model: "qwen3.7-plus",
        input: "My name is Alice, 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://dashscope.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 Alice, please remember it."
}'

# Second round - use the id from the first response as previous_response_id
curl -X POST https://dashscope.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://dashscope.aliyuncs.com/compatible-mode/v1",
)

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

# Process the output
for item in response.output:
    if item.type == "reasoning":
        print("=== Thinking Process ===")
        for summary in item.summary:
            print(summary.text)
    elif item.type == "message":
        print("\n=== Final Answer ===")
        print(item.content[0].text)

# Check the thinking token count
print(f"\nThinking token count: {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://dashscope.aliyuncs.com/compatible-mode/v1"
});

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

    for (const item of response.output) {
        if (item.type === "reasoning") {
            console.log("=== Thinking Process ===");
            for (const summary of item.summary) {
                console.log(summary.text);
            }
        } else if (item.type === "message") {
            console.log("\n=== Final Answer ===");
            console.log(item.content[0].text);
        }
    }

    // Check the thinking token count
    console.log(`\nThinking token count: ${response.usage.output_tokens_details.reasoning_tokens}`);
}

main();

Curl

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-plus",
    "input": "Which is larger, 9.9 or 9.11?",
    "reasoning": {"effort": "medium"}
}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope.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 the raw event response
    if event.type == 'response.output_text.delta':
        # Print the text delta in real time
        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://dashscope.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 the 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://dashscope.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://dashscope.aliyuncs.com/compatible-mode/v1",
)

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

# Uncomment the following line 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://dashscope.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 from the homepage",
        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://dashscope.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 from the homepage",
    "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://dashscope.aliyuncs.com/compatible-mode/v1",
    # Enable session cache via default_headers
    default_headers={"x-dashscope-session-cache": "enable"}
)

# Construct a long text exceeding 1024 tokens to trigger cache creation.
# (If the initial prompt is under 1024 tokens, the server creates the cache once the total context exceeds this threshold.)
long_context = "Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence." * 50

# First request
response1 = client.responses.create(
    model="qwen3.7-plus",
    input=long_context + "\n\nBased on the background knowledge above, briefly introduce the random forest algorithm in machine learning.",
)
print(f"First response: {response1.output_text}")

# Second request: Link the context using previous_response_id. The server manages the cache automatically.
response2 = client.responses.create(
    model="qwen3.7-plus",
    input="What are the main differences between it and GBDT?",
    previous_response_id=response1.id,
)
print(f"Second response: {response2.output_text}")

# Check the cache hit status
usage = response2.usage
print(f"Input tokens: {usage.input_tokens}")
print(f"Cached tokens: {usage.input_tokens_details.cached_tokens}")

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1",
    // Enable session cache via defaultHeaders
    defaultHeaders: {"x-dashscope-session-cache": "enable"}
});

// Construct a long text exceeding 1024 tokens to trigger cache creation.
// (If the initial prompt is under 1024 tokens, the server creates the cache once the total context exceeds this threshold.)
const longContext = "Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence.".repeat(50);

async function main() {
    // First request
    const response1 = await openai.responses.create({
        model: "qwen3.7-plus",
        input: longContext + "\n\nBased on the background knowledge above, briefly introduce the random forest algorithm in machine learning, including its basic principles and use cases."
    });
    console.log(`First response: ${response1.output_text}`);

    // Second request: Link the context using previous_response_id. The server manages the cache automatically.
    const response2 = await openai.responses.create({
        model: "qwen3.7-plus",
        input: "What are the main differences between it and GBDT?",
        previous_response_id: response1.id
    });
    console.log(`Second response: ${response2.output_text}`);

    // Check the cache hit status
    console.log(`Input tokens: ${response2.usage.input_tokens}`);
    console.log(`Cached tokens: ${response2.usage.input_tokens_details.cached_tokens}`);
}

main();

curl

# First request
# The 'input' text must exceed 1024 tokens to trigger cache creation.
curl -X POST https://dashscope.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": "Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence. Artificial intelligence is an important branch of computer science that focuses on the research and development of theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence.\n\nBased on the background knowledge above, briefly introduce the random forest algorithm in machine learning, including its basic principles and use cases."
}'

# Second request - Set 'previous_response_id' to the 'id' from the first response.
curl -X POST https://dashscope.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": "What are the main differences between it and GBDT?",
    "previous_response_id": "id_from_first_response"
}'

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://dashscope.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://dashscope.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 - you need to implement tools 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 - you need to implement tools 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://dashscope.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"}]
}'