Web extractor - Alibaba Cloud Model Studio: Central de Documentação do Alibaba Cloud

Os LLMs não acessam diretamente os dados de páginas da web. O web extractor acessa uma URL e extrai seu conteúdo para o modelo.

Uso

Você pode chamar o web extractor de três maneiras. Os parâmetros obrigatórios variam conforme o método:

OpenAI-compatible - Responses API

Adicione web_search e web_extractor ao parâmetro tools.

Ao usar qwen3-max-2026-01-23 , defina enable_thinking como true .

Para obter maior precisão em problemas matemáticos ou de análise de dados, ative também a ferramenta code_interpreter .

# Import dependencies and create a client...
response = client.responses.create(
    model="qwen3.7-max",
    input="Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content",
    tools=[
        # To enable web extraction, also enable the web search tool
        {"type": "web_search"},
        {"type": "web_extractor"},
        {"type": "code_interpreter"}
    ],
    extra_body={
      # Thinking mode must be enabled
      "enable_thinking": True
    }
)

print(response.output_text)

OpenAI-compatible - Chat Completions API

Defina enable_search como true e search_strategy como agent_max. Defina também enable_thinking como true.

A saída sem streaming não é compatível.

# Import dependencies and create a client...
completion = client.chat.completions.create(
    model="qwen3.7-max",
    messages=[{"role": "user", "content": "Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content"}],
    extra_body={
        "enable_thinking": True,
        "enable_search": True,
        "search_options": {"search_strategy": "agent_max"}
    },
    stream=True
)

DashScope

Defina enable_search como true e search_strategy como agent_max. Defina também enable_thinking como true.

A saída sem streaming não é compatível.

from dashscope import Generation

response = Generation.call(
    model="qwen3.7-max",
    messages=[{"role": "user", "content": "Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content"}],
    enable_search=True,
    search_options={"search_strategy": "agent_max"},
    enable_thinking=True,
    result_format="message",
    stream=True,
    incremental_output=True
)

Modelos compatíveis

Modelos recomendados

Responses API

Qwen-Max: qwen3.8-max-preview (apenas Token Plan), série Qwen3.7-Max

Qwen-Plus: série Qwen3.7-Plus, série Qwen3.6-Plus, série Qwen3.5-Plus

Chat Completions API / DashScope

Qwen-Max (modo de raciocínio): série Qwen3-Max
Qwen-Plus: série Qwen3.6-Plus, série Qwen3.5-Plus

Outros modelos

Os modelos abaixo também são compatíveis com esta ferramenta, mas podem não apresentar o mesmo desempenho dos modelos recomendados.

Qwen-Flash: série Qwen3.6-Flash, série Qwen3.5-Flash
Série open-source Qwen3.6 (exceto qwen3.6-27b)
Série open-source Qwen3.5

Primeiros passos

Este exemplo chama o web extractor pela Responses API para resumir um documento técnico.

Você deve obter uma chave de API e configurá-la como variável de ambiente .

Python

import os
from openai import OpenAI

client = OpenAI(
    # If the environment variable is not configured, replace the next line with api_key="sk-xxx", using your Model Studio API key.
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Singapore region. Replace {WorkspaceId} with your actual Workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
)

response = client.responses.create(
    model="qwen3.7-max",
    input="Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content",
    tools=[
        {
            "type": "web_search"
        },
        {
            "type": "web_extractor"
        },
        {
            "type": "code_interpreter"
        }
    ],
    extra_body = {
        "enable_thinking": True
    }
)
# Uncomment the following line to view intermediate process outputs
# print(response.output)
print("="*20+"Response Content"+"="*20)
print(response.output_text)
# Print the number of tool calls
usage = response.usage
print("="*20+"Tool Call Count"+"="*20)
if hasattr(usage, 'x_tools') and usage.x_tools:
    print(f"\nWeb extraction count: {usage.x_tools.get('web_extractor', {}).get('count', 0)}")

Node.js

import OpenAI from "openai";
import process from 'process';

const openai = new OpenAI({
    // If the environment variable is not configured, replace the next line with apiKey: "sk-xxx", using your Model Studio API key.
    apiKey: process.env.DASHSCOPE_API_KEY,
    // Singapore region. Replace {WorkspaceId} with your actual Workspace ID. URLs vary by region.
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const response = await openai.responses.create({
        model: "qwen3.7-max",
        input: "Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content",
        tools: [
            { type: "web_search" },
            { type: "web_extractor" },
            { type: "code_interpreter" }
        ],
        enable_thinking: true
    });

    console.log("====================Response Content====================");
    console.log(response.output_text);

    // Print the number of tool calls
    console.log("====================Tool Call Count====================");
    if (response.usage && response.usage.x_tools) {
        console.log(`Web extraction count: ${response.usage.x_tools.web_extractor?.count || 0}`);
        console.log(`Web search count: ${response.usage.x_tools.web_search?.count || 0}`);
    }
    // Uncomment the following line to view intermediate process outputs
    // console.log(JSON.stringify(response.output[0], null, 2));
}

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-max",
    "input": "Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content",
    "tools": [
        {"type": "web_search"},
        {"type": "web_extractor"},
        {"type": "code_interpreter"}
    ],
    "enable_thinking": true
}'

Exemplo de saída:

====================Response Content====================
Based on the official Alibaba Cloud Model Studio documentation, I have summarized the core content of the **code interpreter** feature for you:

## 1. Feature Positioning

...

> **Document Source**: Alibaba Cloud Model Studio official documentation - [Qwen Code Interpreter](https://www.alibabacloud.com/help/en/model-studio/qwen-code-interpreter) and [Assistant API Code Interpreter](https://www.alibabacloud.com/help/en/model-studio/code-interpreter) (Updated: December 2025)
====================Tool Call Count====================

Web extraction count: 1

Saída com streaming

A extração da web pode ser demorada. Ative a saída com streaming para receber resultados intermediários em tempo real.

Use a Responses API para recuperar o status intermediário da execução das ferramentas.

OpenAI-compatible - Responses API

Python

import os
from openai import OpenAI

client = OpenAI(
    # If the environment variable is not configured, replace the next line with api_key="sk-xxx" (not recommended), using your Model Studio API key.
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Singapore region. Replace {WorkspaceId} with your actual Workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
)

stream = client.responses.create(
    model="qwen3.7-max",
    input="Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content",
    tools=[
        {"type": "web_search"},
        {"type": "web_extractor"},
        {"type": "code_interpreter"}
    ],
    stream=True,
    extra_body={"enable_thinking": True}
)

reasoning_started = False
output_started = False

for chunk in stream:
    # Print the thinking process
    if chunk.type == 'response.reasoning_summary_text.delta':
        if not reasoning_started:
            print("="*20 + "Thinking Process" + "="*20)
            reasoning_started = True
        print(chunk.delta, end='', flush=True)
    # Print when tool call is complete
    elif chunk.type == 'response.output_item.done':
        if hasattr(chunk, 'item') and hasattr(chunk.item, 'type'):
            if chunk.item.type == 'web_extractor_call':
                print("\n" + "="*20 + "Tool Call" + "="*20)
                print(chunk.item.goal)
                print(chunk.item.output)
            elif chunk.item.type == 'reasoning':
                reasoning_started = False
    # Print the response content
    elif chunk.type == 'response.output_text.delta':
        if not output_started:
            print("\n" + "="*20 + "Response Content" + "="*20)
            output_started = True
        print(chunk.delta, end='', flush=True)
    # When the response is complete, print the number of tool calls
    elif chunk.type == 'response.completed':
        print("\n" + "="*20 + "Tool Call Count" + "="*20)
        usage = chunk.response.usage
        if hasattr(usage, 'x_tools') and usage.x_tools:
            print(f"Web extraction count: {usage.x_tools.get('web_extractor', {}).get('count', 0)}")
            print(f"Web search count: {usage.x_tools.get('web_search', {}).get('count', 0)}")

Node.js

import OpenAI from "openai";
import process from 'process';

const openai = new OpenAI({
    // If the environment variable is not configured, replace the next line with apiKey: "sk-xxx", using your Model Studio API key.
    apiKey: process.env.DASHSCOPE_API_KEY,
    // Singapore region. Replace {WorkspaceId} with your actual Workspace ID. URLs vary by region.
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const stream = await openai.responses.create({
        model: "qwen3.7-max",
        input: "Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content",
        tools: [
            { type: "web_search" },
            { type: "web_extractor" },
            { type: "code_interpreter" }
        ],
        stream: true,
        enable_thinking: true
    });

    let reasoningStarted = false;
    let outputStarted = false;

    for await (const chunk of stream) {
        // Print the thinking process
        if (chunk.type === 'response.reasoning_summary_text.delta') {
            if (!reasoningStarted) {
                console.log("====================Thinking Process====================");
                reasoningStarted = true;
            }
            process.stdout.write(chunk.delta);
        }
        // Print when tool call is complete
        else if (chunk.type === 'response.output_item.done') {
            if (chunk.item && chunk.item.type === 'web_extractor_call') {
                console.log("\n" + "====================Tool Call====================");
                console.log(chunk.item.goal);
                console.log(chunk.item.output);
            } else if (chunk.item && chunk.item.type === 'reasoning') {
                reasoningStarted = false;
            }
        }
        // Print the response content
        else if (chunk.type === 'response.output_text.delta') {
            if (!outputStarted) {
                console.log("\n" + "====================Response Content====================");
                outputStarted = true;
            }
            process.stdout.write(chunk.delta);
        }
        // When the response is complete, print the number of tool calls
        else if (chunk.type === 'response.completed') {
            console.log("\n" + "====================Tool Call Count====================");
            const usage = chunk.response.usage;
            if (usage && usage.x_tools) {
                console.log(`Web extraction count: ${usage.x_tools.web_extractor?.count || 0}`);
                console.log(`Web search count: ${usage.x_tools.web_search?.count || 0}`);
            }
        }
    }
}

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-max",
    "input": "Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content",
    "tools": [
        {"type": "web_search"},
        {"type": "web_extractor"},
        {"type": "code_interpreter"}
    ],
    "enable_thinking": true,
    "stream": true
}'

OpenAI-compatible - Chat Completions API

Python

import os
from openai import OpenAI

client = OpenAI(
    # If the environment variable is not configured, replace the next line with api_key="sk-xxx" (not recommended), using your Model Studio API key.
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Singapore region. Replace {WorkspaceId} with your actual Workspace ID. URLs vary by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
)

stream = client.chat.completions.create(
    model="qwen3.7-max",
    messages=[
        {"role": "user", "content": "Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content"}
    ],
    extra_body={
        "enable_thinking": True,
        "enable_search": True,
        "search_options": {"search_strategy": "agent_max"}
    },
    stream=True
)

reasoning_started = False
output_started = False

for chunk in stream:
    if chunk.choices:
        delta = chunk.choices[0].delta
        # Print the thinking process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content:
            if not reasoning_started:
                print("="*20 + "Thinking Process" + "="*20)
                reasoning_started = True
            print(delta.reasoning_content, end='', flush=True)
        # Print the response content
        if delta.content:
            if not output_started:
                print("\n" + "="*20 + "Response Content" + "="*20)
                output_started = True
            print(delta.content, end='', flush=True)

Node.js

import OpenAI from "openai";
import process from 'process';

const openai = new OpenAI({
    // If the environment variable is not configured, replace the next line with apiKey: "sk-xxx", using your Model Studio API key.
    apiKey: process.env.DASHSCOPE_API_KEY,
    // Singapore region. Replace {WorkspaceId} with your actual Workspace ID. URLs vary by region.
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const stream = await openai.chat.completions.create({
        model: "qwen3.7-max",
        messages: [
            { role: "user", content: "Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content" }
        ],
        enable_thinking: true,
        enable_search: true,
        search_options: { search_strategy: "agent_max" },
        stream: true
    });

    let reasoningStarted = false;
    let outputStarted = false;

    for await (const chunk of stream) {
        if (chunk.choices && chunk.choices.length > 0) {
            const delta = chunk.choices[0].delta;
            // Print the thinking process
            if (delta.reasoning_content) {
                if (!reasoningStarted) {
                    console.log("====================Thinking Process====================");
                    reasoningStarted = true;
                }
                process.stdout.write(delta.reasoning_content);
            }
            // Print the response content
            if (delta.content) {
                if (!outputStarted) {
                    console.log("\n" + "====================Response Content====================");
                    outputStarted = true;
                }
                process.stdout.write(delta.content);
            }
        }
    }
}

main();

curl

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-max",
    "messages": [
        {"role": "user", "content": "Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content"}
    ],
    "enable_thinking": true,
    "enable_search": true,
    "search_options": {"search_strategy": "agent_max"},
    "stream": true
}'

DashScope

O SDK Java não é compatível.

Python

import os
import dashscope
from dashscope import Generation

# If the environment variable is not configured, replace the next line with dashscope.api_key = "sk-xxx", using your Model Studio API key.
dashscope.api_key = os.getenv("DASHSCOPE_API_KEY")
# Singapore region. Replace {WorkspaceId} with your actual Workspace ID. URLs vary by region.
dashscope.base_http_api_url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1"

response = Generation.call(
    model="qwen3.7-max",
    messages=[
        {"role": "user", "content": "Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content"}
    ],
    enable_search=True,
    search_options={"search_strategy": "agent_max"},
    enable_thinking=True,
    result_format="message",
    stream=True,
    incremental_output=True
)

reasoning_started = False
output_started = False

for chunk in response:
    if chunk.status_code == 200:
        message = chunk.output.choices[0].message

        # Print the thinking process
        if hasattr(message, 'reasoning_content') and message.reasoning_content:
            if not reasoning_started:
                print("="*20 + "Thinking Process" + "="*20)
                reasoning_started = True
            print(message.reasoning_content, end='', flush=True)

        # Print the response content
        if hasattr(message, 'content') and message.content:
            if not output_started:
                print("\n" + "="*20 + "Response Content" + "="*20)
                output_started = True
            print(message.content, end='', flush=True)
    else:
        print(f"\nRequest failed: code={chunk.code}, message={chunk.message}")
        break

curl

curl -X POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "X-DashScope-SSE: enable" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.7-max",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": "Please visit the official Alibaba Cloud Model Studio documentation for the code interpreter and summarize its main content"
            }
        ]
    },
    "parameters": {
        "enable_thinking": true,
        "enable_search": true,
        "search_options": {
            "search_strategy": "agent_max"
        },
        "result_format": "message"
    }
}'

Faturamento

O faturamento inclui:

Taxas de chamada do modelo: O conteúdo extraído da página da web é adicionado ao prompt, aumentando a contagem de tokens de entrada. Esses tokens são cobrados à tarifa padrão do modelo. Para detalhes de preços, consulte o console do Model Studio.
Taxas de chamada de ferramentas: Inclui extração da web e busca na web.
- Taxas de busca na web por 1.000 chamadas:
  - Escopos de implantação na China continental e Global: $0,57341.
  - Escopo de implantação internacional: $10,00.
- O web extractor é gratuito por tempo limitado.