Create a response

import os
from openai import OpenAI

client = OpenAI(
    # If the environment variable is not set, replace the following line with your Model Studio API Key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)

response = client.responses.create(
    model="qwen3.8-max",
    input="What can you do?"
)

# Get the model's response
print(response.output_text)

import OpenAI from "openai";

const openai = new OpenAI({
    // If the environment variable is not set, replace the following line with your Model Studio API Key: apiKey: "sk-xxx"
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const response = await openai.responses.create({
        model: "qwen3.8-max",
        input: "What can you do?"
    });

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

main();

curl -X POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.8-max",
    "input": "What can you do?"
}'

import os
from openai import OpenAI

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

stream = client.responses.create(
    model="qwen3.8-max",
    input="Briefly introduce artificial intelligence.",
    stream=True
)

print("Receiving stream output:")
for event in stream:
    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}")

import OpenAI from "openai";

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

async function main() {
    const stream = await openai.responses.create({
        model: "qwen3.8-max",
        input: "Briefly introduce artificial intelligence.",
        stream: true
    });

    console.log("Receiving stream output:");
    for await (const event of stream) {
        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 -X POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
--no-buffer \
-d '{
    "model": "qwen3.8-max",
    "input": "Briefly introduce artificial intelligence.",
    "stream": true
}'

import os
from openai import OpenAI

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

# First turn
response1 = client.responses.create(
    model="qwen3.8-max",
    input="My name is John. Please remember it."
)
print(f"First response: {response1.output_text}")

# Second turn - use previous_response_id to link context. The response ID is valid for 7 days.
response2 = client.responses.create(
    model="qwen3.8-max",
    input="Do you remember my name?",
    previous_response_id=response1.id
)
print(f"Second response: {response2.output_text}")

import OpenAI from "openai";

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

async function main() {
    // First turn
    const response1 = await openai.responses.create({
        model: "qwen3.8-max",
        input: "My name is John. Please remember it."
    });
    console.log(`First response: ${response1.output_text}`);

    // Second turn - use previous_response_id to link context. The response ID is valid for 7 days.
    const response2 = await openai.responses.create({
        model: "qwen3.8-max",
        input: "Do you remember my name?",
        previous_response_id: response1.id
    });
    console.log(`Second response: ${response2.output_text}`);
}

main();

import os
from openai import OpenAI

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

response = client.responses.create(
    model="qwen3.8-max",
    input="Find the Alibaba Cloud official website and extract key information from its homepage.",
    # For best results, we recommend enabling the built-in tools.
    tools=[
        {"type": "web_search"},
        {"type": "code_interpreter"},
        {"type": "web_extractor"}
    ],
)

# Uncomment the following line to view the intermediate output.
# print(response.output)
print(response.output_text)

import OpenAI from "openai";

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

async function main() {
    const response = await openai.responses.create({
        model: "qwen3.8-max",
        input: "Find the Alibaba Cloud official website and extract key information from its homepage.",
        tools: [
            { type: "web_search" },
            { type: "code_interpreter" },
            { type: "web_extractor" }
        ]
    });

    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 content: ${item.content[0].text}`);
        }
    }
}

main();

curl -X POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.8-max",
    "input": "Find the Alibaba Cloud official website and extract key information from its homepage.",
    "tools": [
        {
            "type": "web_search"
        },
        {
            "type": "code_interpreter"
        },
        {
            "type": "web_extractor"
        }
    ]
}'

from openai import OpenAI
import json
import os
import random

# Initialize the client.
client = OpenAI(
    # If the environment variable is not set, replace the following line with your Model Studio API Key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)
# Simulate a user question.
USER_QUESTION = "What's the weather like in Beijing?"
# Define the list of tools.
tools = [
    {
        "type": "function",
        "name": "get_current_weather",
        "description": "Useful for getting the weather in a specific city.",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city or district, such as Beijing or Hangzhou.",
                }
            },
            "required": ["location"],
        },
    }
]

# Simulate the weather query tool.
def get_current_weather(arguments):
    weather_conditions = ["sunny", "cloudy", "rainy"]
    random_weather = random.choice(weather_conditions)
    location = arguments["location"]
    return f"Today in {location} it is {random_weather}."

# Wrap the model response function.
def get_response(input_data):
    response = client.responses.create(
        model="qwen3.8-max",
        input=input_data,
        tools=tools,
    )
    return response

# Maintain the conversation context.
conversation = [{"role": "user", "content": USER_QUESTION}]

response = get_response(conversation)
function_calls = [item for item in response.output if item.type == "function_call"]
# If no tool call is needed, output the content directly.
if not function_calls:
    print(f"Final assistant response: {response.output_text}")
else:
    # Enter the tool-calling loop.
    while function_calls:
        for fc in function_calls:
            func_name = fc.name
            arguments = json.loads(fc.arguments)
            print(f"Calling tool [{func_name}] with arguments: {arguments}")
            # Execute the tool.
            tool_result = get_current_weather(arguments)
            print(f"Tool returned: {tool_result}")
            # Append the tool call and its result to the context as a pair.
            conversation.append(
                {
                    "type": "function_call",
                    "name": fc.name,
                    "arguments": fc.arguments,
                    "call_id": fc.call_id,
                }
            )
            conversation.append(
                {
                    "type": "function_call_output",
                    "call_id": fc.call_id,
                    "output": tool_result,
                }
            )
        # Call the model again with the full context.
        response = get_response(conversation)
        function_calls = [
            item for item in response.output if item.type == "function_call"
        ]
    print(f"Final assistant response: {response.output_text}")

import OpenAI from "openai";

// Initialize the client.
const openai = new OpenAI({
  // If the environment variable is not set, replace the following line with your Model Studio API Key: apiKey: "sk-xxx",
  apiKey: process.env.DASHSCOPE_API_KEY,
  baseURL:
    "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
});

// Define the list of tools.
const tools = [
  {
    type: "function",
    name: "get_current_weather",
    description: "Useful for getting the weather in a specific city.",
    parameters: {
      type: "object",
      properties: {
        location: {
          type: "string",
          description: "The city or district, such as Beijing or Hangzhou.",
        },
      },
      required: ["location"],
    },
  },
];

// Simulate the weather query tool.
const getCurrentWeather = (args) => {
  const weatherConditions = ["sunny", "cloudy", "rainy"];
  const randomWeather =
    weatherConditions[Math.floor(Math.random() * weatherConditions.length)];
  const location = args.location;
  return `Today in ${location} it is ${randomWeather}.`;
};

// Wrap the model response function.
const getResponse = async (inputData) => {
  const response = await openai.responses.create({
    model: "qwen3.8-max",
    input: inputData,
    tools: tools,
  });
  return response;
};

const main = async () => {
  const userQuestion = "What's the weather like in Beijing?";

  // Maintain the conversation context.
  const conversation = [{ role: "user", content: userQuestion }];

  let response = await getResponse(conversation);
  let functionCalls = response.output.filter(
    (item) => item.type === "function_call"
  );
  // If no tool call is needed, output the content directly.
  if (functionCalls.length === 0) {
    console.log(`Final assistant response: ${response.output_text}`);
  } else {
    // Enter the tool-calling loop.
    while (functionCalls.length > 0) {
      for (const fc of functionCalls) {
        const funcName = fc.name;
        const args = JSON.parse(fc.arguments);
        console.log(`Calling tool [${funcName}] with arguments:`, args);
        // Execute the tool.
        const toolResult = getCurrentWeather(args);
        console.log(`Tool returned: ${toolResult}`);
        // Append the tool call and its result to the context as a pair.
        conversation.push({
          type: "function_call",
          name: fc.name,
          arguments: fc.arguments,
          call_id: fc.call_id,
        });
        conversation.push({
          type: "function_call_output",
          call_id: fc.call_id,
          output: toolResult,
        });
      }
      // Call the model again with the full context.
      response = await getResponse(conversation);
      functionCalls = response.output.filter(
        (item) => item.type === "function_call"
      );
    }
    console.log(`Final assistant response: ${response.output_text}`);
  }
};

// Start the program.
main().catch(console.error);

import os
from openai import OpenAI

client = OpenAI(
    # If you have not configured an environment variable, replace the next line with: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)

response = client.responses.create(
    model="qwen3.5-ocr",
    input=[
        {
            "role": "user",
            "content": [
                {
                    "type": "input_file",
                    "file_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260616/qmycjl/1506.02640v5.pdf",
                },
                {
                    "type": "input_text",
                    "text": "Read all the text in the file.",
                },
            ],
        }
    ],
    extra_body={
        "ocr_options": {}
    },
)

print(response.output_text)

import OpenAI from 'openai';

const client = new OpenAI({
    // If you have not configured an environment variable, replace the next line with: apiKey: "sk-xxx"
    apiKey: process.env.DASHSCOPE_API_KEY,
    baseURL: "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
});

async function main() {
    const response = await client.responses.create({
        model: "qwen3.5-ocr",
        input: [{
            role: "user",
            content: [{
                type: "input_file",
                file_url: "https://example.com/your-document.pdf"
            }]
        }],
        ocr_options: { task: "document_parsing" }
    });

    // Get the custom task result
    console.log(response.output[0].content[0].ocr_result);
}

main();

curl -X POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/responses \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.5-ocr",
    "input": [
        {
            "role": "user",
            "content": [
                {
                    "type": "input_file",
                    "file_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260616/qmycjl/1506.02640v5.pdf"
                },
                {
                    "type": "input_text",
                    "text": "Read all the text in the file."
                }
            ]
        }
    ],
    "ocr_options": {}
}'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
    # Enable the session cache via default_headers.
    default_headers={"x-dashscope-session-cache": "enable"}
)

# Construct a long text over 1024 tokens to trigger cache creation.
# If not, caching is triggered when the cumulative context exceeds 1024 tokens.
long_context = "Artificial intelligence (AI) is a major branch of computer science, dedicated to researching and developing theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence." * 50

# First turn
response1 = client.responses.create(
    model="qwen3.8-max",
    input=long_context + "\n\nBased on this context, briefly introduce the Random Forest algorithm in machine learning.",
)
print(f"First response: {response1.output_text}")

# Second turn: Link context using previous_response_id. The cache is handled automatically by the server.
response2 = client.responses.create(
    model="qwen3.8-max",
    input="What are the main differences between it and GBDT?",
    extra_body={"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.prompt_tokens_details.cached_tokens}")

import OpenAI from "openai";

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

// Construct a long text over 1024 tokens to trigger cache creation.
// If not, caching is triggered when the cumulative context exceeds 1024 tokens.
const longContext = "Artificial intelligence (AI) is a major branch of computer science, dedicated to researching and developing theories, methods, technologies, and application systems that can simulate, extend, and expand human intelligence.".repeat(50);

async function main() {
    // First turn
    const response1 = await openai.responses.create({
        model: "qwen3.8-max",
        input: longContext + "\n\nBased on this context, briefly introduce the Random Forest algorithm in machine learning, including its basic principles and applications."
    });
    console.log(`First response: ${response1.output_text}`);

    // Second turn: Link context using previous_response_id. The cache is handled automatically by the server.
    const response2 = await openai.responses.create({
        model: "qwen3.8-max",
        input: "What are the main differences between it and GBDT?",
        extra_body: { previous_response_id: response1.id }
    } as any);
    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.prompt_tokens_details.cached_tokens}`);
}

main();

# First turn
# Repeat the long text 50 times to ensure it exceeds 1024 tokens and triggers cache creation.
curl -X POST https://{WorkspaceId}.cn-beijing.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": "qwen3.8-max",
    "input": "Artificial intelligence (AI) is a major branch of computer science..."
}'

# Second turn - use the ID from the previous response as previous_response_id.
curl -X POST https://{WorkspaceId}.cn-beijing.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": "qwen3.8-max",
    "input": "What are the main differences between it and GBDT?",
    "previous_response_id": ""
}'