Web search

​

Enable web search

import os
from openai import OpenAI

client = OpenAI(
  api_key=os.getenv("DASHSCOPE_API_KEY"),
  base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
  model="qwen3-max",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "How is Alibaba's stock price?"},
  ],
  extra_body={
    "enable_search": True,
    "search_options": {
      "search_strategy": "agent"
    }
  }
)
print(completion.choices[0].message.content)

from openai import OpenAI
import os

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

response = client.responses.create(
  model="qwen3-max-2026-01-23",
  input="Singapore weather",
  tools=[{"type": "web_search"}],
  extra_body={"enable_thinking": True}
)

print(response.output_text)

usage = response.usage
if hasattr(usage, 'x_tools') and usage.x_tools:
  print(f"Web search count: {usage.x_tools.get('web_search', {}).get('count', 0)}")

import os
import dashscope
dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1"

response = dashscope.Generation.call(
  api_key=os.getenv("DASHSCOPE_API_KEY"),
  model="qwen3-max",
  messages=[{"role": "user", "content": "Alibaba stock price"}],
  enable_search=True,
  search_options={
    "search_strategy": "agent",
    "enable_source": True
  },
  result_format="message",
)
for web in response.output.search_info["search_results"]:
  print(f"[{web['index']}]: [{web['title']}]({web['url']})")
print(response.output.choices[0].message.content)

[1]: [Alibaba (BABA) Stock Price, Quotes, Chart - East Money](https://wap.eastmoney.com/quote/stock/106.BABA.html)
[2]: [Alibaba (BABA) US Stock Quotes - Sina Finance](https://gu.sina.cn/quotes/us/BABA)
[3]: [Alibaba (BABA) Latest Stock Price - Investing.com](https://cn.investing.com/equities/alibaba)

According to the latest market data, Alibaba's stock prices are:
* US stocks (BABA): ~$160.40
* HK stocks (09988.HK): ~HK$158.10
Note that stock prices fluctuate in real time; this information is for reference only.

# Import dependencies and create the client...
message = client.messages.create(
    model="qwen3.8-max",
    max_tokens=2048,
    messages=[{"role": "user", "content": "What will the weather in Hangzhou be like tomorrow?"}],
    tools=[
        {
            # The date suffix depends on the client version. The value below is the one current Claude Code sends.
            "type": "web_search_20250305",
            "name": "web_search",
            # Optional. Maximum number of searches per request.
            "max_uses": 8
        }
    ]
)

​

Web search with multimodal models

import os
import dashscope
from dashscope import MultiModalConversation
dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1"
responses = MultiModalConversation.call(
  api_key=os.getenv("DASHSCOPE_API_KEY"),
  model="qwen3.5-plus",
  messages=[{"role": "user", "content": [{"text": "What is the weather in Hangzhou today?"}]}],
  enable_search=True,
  search_options={
    # The qwen3.5-omni series requires agent. The Qwen3.8 series does not support agent; keep the default.
    "search_strategy": "agent",
    "enable_source": True,
  },
  stream=True,
  incremental_output=True,
)
for response in responses:
  print(response.output.choices[0].message.content)

​

Supported models

​

Search strategies

• turbo (default) -- Balances response speed and search quality. Suitable for most scenarios.
• max -- Uses a more comprehensive search strategy and may call multiple search engines for more thorough results, but the response time may be longer.
• agent -- Calls the web search tool and the model multiple times for multi-round information retrieval and integration. Suitable for complex queries and English scenarios. Applies to the Qwen3-Max series (qwen3-max, qwen3-max-2025-09-23 and later snapshots), the Qwen3.5 series (including open-source models and the Omni series), the Qwen3.6 series, and the Qwen3.7 series. Streaming calls are required when calling through the text endpoint. The Qwen3.8 series does not support the agent strategy. When enabled, only enable_source: true (returning search sources) is supported; other web search features are unavailable. Each invocation is billed additionally, see Billing.
• agent_max -- Supports reading full web pages with the web extractor tool on top of the agent strategy. Only available on qwen3-max and qwen3-max-2026-01-23 in thinking mode. When enabled, only enable_source: true is supported; other web search features are unavailable. Each invocation is billed additionally, see Billing.

​

Read search results

​

Get search sources

The Responses API does not support the enable_source, enable_citation, or citation_format parameters, and does not insert [1] citation markers into the response content. To use citation markers, use the DashScope API.

# Extract search sources from the response above
print("=" * 20 + "Search sources" + "=" * 20)
for item in response.output:
    if item.type == "web_search_call":
        for i, source in enumerate(item.action.sources, start=1):
            print(f"[{i}] {source.url}")

​

Billing

• Model call fees: The web content from the web search is added to the prompt, which increases the number of input tokens for the model. You are charged based on the standard pricing of the model. For more information about pricing, see Pricing.
• Search call fees (per 1,000 calls):
  When using the Responses API, the web search tool is billed at the same rate as the agent strategy.
  The prices listed below are list prices. For current promotions and discounted pricing, visit the Model Marketplace.

  Strategy (search_strategy)	What it does	Fee
  agent (default)	Model searches the web as needed	$10.00
  agent_max	Searches + reads full pages via web extractor	$10.00 for search; web extractor is free for a limited time

​

Error codes