Web extractor - Alibaba Cloud Model Studio

Uso

Existem três formas de chamar o web extractor. Os parâmetros obrigatórios variam conforme o método:

OpenAI-compatible - Responses API
OpenAI-compatible - Chat Completions API
DashScope

Adicione web_search e web_extractor ao parâmetro tools.

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

Para 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="qwen3.8-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)

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

A saída sem streaming não é suportada.

# Import dependencies and create a client...
completion = client.chat.completions.create(
    model="qwen3-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
)

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

A saída sem streaming não é suportada.

from dashscope import Generation

response = Generation.call(
    model="qwen3-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 suportados

Modelos recomendados

Responses API
Chat Completions API / DashScope

Qwen-Max: série Qwen3,8-Max, série Qwen3,7-MaxQwen-Plus: série Qwen3,7-Plus, série Qwen3,6-Plus, série Qwen3,5-PlusDeepSeek: deepseek-v4-flash, deepseek-v4-flash-0731, deepseek-v4-proGLM: glm-5.2Série open-source Qwen3,8

Outros modelos

Os modelos abaixo também suportam esta ferramenta, mas podem não ter o mesmo desempenho dos modelos recomendados. O suporte está disponível apenas pela Responses API.

Qwen-Flash: série Qwen3,7-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.

É necessário get an API key e configure it as an environment variable .

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="qwen3.8-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)}")

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 obter o status intermediário da execução das ferramentas.

OpenAI-compatible - Responses API
OpenAI-compatible - Chat Completions API
DashScope

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="qwen3.8-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)}")

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-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)

O SDK Java não é suportado.

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-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

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: incluem extração da web e busca na web.
- Tarifa de busca na web por 1.000 chamadas:
  - Região China (Beijing): $0.57341.
  - Região Singapore: $10,00.
- O web extractor é gratuito por tempo limitado.

​Uso

​Modelos suportados

​Modelos recomendados

​Outros modelos

​Primeiros passos

​Saída com streaming