Web search with large models - Alibaba Cloud Model Studio

The training data for large language models has a knowledge cutoff date, preventing them from answering real-time questions. Enabling web search lets the model retrieve real-time data and accurately answer time-sensitive questions, such as stock prices, weather forecasts, and breaking news.

Usage

You can enable web search using the four API calls below, each requiring different parameters.

For web search with models such as qwen3.7-max, use the web search feature of the Responses API.

OpenAI-compatible: Responses API

Add the web_search tool to the tools parameter to enable web search.

The Responses API supports only some models. For the supported models, see Web search with Responses API.

# Import dependencies and create a client...
response = client.responses.create(
    model="qwen3.8-max",
    input="Hangzhou weather",
    tools=[
        {"type": "web_search"},
        {"type": "web_extractor"},
        {"type": "code_interpreter"}
    ],
    extra_body={"enable_thinking": True}
)

OpenAI-compatible: Chat Completions API

Set enable_search: true to enable web search.

# Import dependencies and create a client...
completion = client.chat.completions.create(
    # Use a model that supports web search.
    model="qwen-plus",
    messages=[{"role": "user", "content": "What is the weather in Hangzhou tomorrow?"}],
    # Since enable_search is not a standard OpenAI parameter, pass it via extra_body when using the Python SDK. For the Node.js SDK, pass it as a top-level parameter.
    extra_body={"enable_search": True}
)

DashScope

Set enable_search: true to enable web search.

# Import dependencies...
response = dashscope.Generation.call(
    # If the DASHSCOPE_API_KEY environment variable is not set, replace the next line with your Model Studio API key (e.g., api_key="sk-xxx",).
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Use a model that supports web search.
    model="qwen-plus",
    messages=[{"role": "user", "content": "What is the weather in Hangzhou tomorrow?"}],
    # Enable web search
    enable_search=True,
    result_format="message"
)

Anthropic-compatible

Add the Anthropic server-side web search tool (name set to web_search) to the tools parameter to enable web search. The endpoint is https://{WorkspaceId}.{region}.maas.aliyuncs.com/apps/anthropic.

This method targets Anthropic official clients such as Claude Code. In those clients, a plain natural-language question triggers web search with no extra configuration.

When you call the API directly with the Anthropic SDK or over HTTP, pass the client identifier x-anthropic-billing-header: cc_entrypoint=cli; in system. Otherwise web search does not take effect.

About the tool version: The date suffix in type (for example web_search_20250305) is determined by the version of the Anthropic official client, and a newer client may send a different dated version. Model Studio identifies the tool by its category and does not validate the date suffix, so you do not need to pin type to a specific version. Simply pass the value your client actually sends.

# Import dependencies and create the client...
message = client.messages.create(
    model="qwen3.8-max",
    max_tokens=2048,
    # Pass the client identifier
    system=[{"type": "text", "text": "x-anthropic-billing-header: cc_entrypoint=cli;"}],
    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
        }
    ]
)

The retrieval process is returned as server_tool_use (search request) and web_search_tool_result (search results) content blocks. The number of searches is reported in usage.server_tool_use.web_search_requests.

Web search with multimodal models

The Qwen3.8 Max, Flash, and open-source series, Qwen3.7-Flash, Qwen3.7-Plus, the Qwen3.6 series, and the Qwen3.5 series (including qwen3.5-plus, qwen3.5-flash, the qwen3.5-omni series, and Qwen open-source models) accept multimodal input (images, video) and are multimodal models.

Search strategy support varies by series: the qwen3.5-omni series supports only the agent strategy; qwen3.8-max, qwen3.8-max-0902, qwen3.8-flash, qwen3.8-2.4t-a95b, and qwen3.8-27b do not support the agent strategy on the multimodal API (use the default turbo or max)—to run Qwen3.8 with agent-style retrieval, use Web search with the Responses API; other models listed in this section support the turbo, max, and agent strategies. Call these models through the multimodal API (the multimodal-generation endpoint): use MultiModalConversation in both Python and Java, not Generation (the text-generation endpoint), which is for text-only models. For the basics of calling multimodal models, see the Visual reasoning and Image and video understanding topics.

Calling the multimodal models above with Generation (the text-generation endpoint) returns 400 url error, please check url. Use MultiModalConversation (the multimodal-generation endpoint) instead.In the Java SDK, MultiModalConversationParam provides enableSearch(true) to enable web search, but does not provide a searchOptions() method. Inject the search strategy and other options through the generic parameter("search_options", ...) method. In Python, MultiModalConversation.call accepts search_options directly.Web search on multimodal models requires streaming calls (use streamCall in Java, or set stream=True in Python); otherwise the request returns a Non-streaming mode does not support Web Search error.

Python

import os
import dashscope
from dashscope import MultiModalConversation
# The following uses the Singapore region. Replace {WorkspaceId} with your actual workspace ID; the configuration differs by region.
dashscope.base_http_api_url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1"
responses = MultiModalConversation.call(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Use a multimodal model that supports web search.
    model="qwen3.5-plus",
    messages=[{"role": "user", "content": [{"text": "What is the weather in Hangzhou today?"}]}],
    # The multimodal API accepts enable_search and search_options directly.
    enable_search=True,
    search_options={
        # The qwen3.5-omni series requires agent. On the multimodal API the Qwen3.8 series does not support agent; keep the default.
        "search_strategy": "agent",
        "enable_source": True,
    },
    # Streaming is required when web search is enabled for multimodal models.
    stream=True,
    incremental_output=True,
)
for response in responses:
    print(response.output.choices[0].message.content)

Java

// dashscope SDK version >= 2.19.0
import java.util.Arrays;
import java.util.Collections;
import io.reactivex.Flowable;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.aigc.generation.SearchOptions;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.utils.Constants;

public class Main {
    // The following uses the Singapore region. Replace {WorkspaceId} with your actual workspace ID; the configuration differs by region.
    static { Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1"; }
    public static void main(String[] args) throws Exception {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMsg = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(Collections.singletonMap("text", "What is the weather in Hangzhou today?")))
                .build();
        SearchOptions searchOptions = SearchOptions.builder()
                // For multimodal models, the search strategy must be set to agent.
                .searchStrategy("agent")
                .enableSource(true)
                .build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // Use a multimodal model that supports web search.
                .model("qwen3.5-plus")
                .messages(Arrays.asList(userMsg))
                // Native method: enable web search.
                .enableSearch(true)
                // MultiModalConversationParam does not provide a searchOptions() method; inject search_options via the generic parameter() method.
                .parameter("search_options", searchOptions)
                .incrementalOutput(true)
                .build();
        // Streaming is required when web search is enabled for multimodal models.
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(message ->
                System.out.print(message.getOutput().getChoices().get(0).getMessage().getContent()));
    }
}

Supported models

The following models support web search. Models with multimodal input (the Qwen3.8 series, Qwen3.7-Flash/Plus, the Qwen3.6 series, the Qwen3.5 series, and Qwen open-source models) must be called through the multimodal API. See Web search with multimodal models.

Singapore

Qwen
- Qwen3.8 series: qwen3.8-max, qwen3.8-max-0902, qwen3.8-flash, qwen3.8-2.4t-a95b, qwen3.8-27b (search_strategy: agent is not supported; for agent-style retrieval, use the web_search tool through the Responses API)
- Qwen3.7 series: qwen3.7-max, qwen3.7-max-preview, qwen3.7-max-2026-05-17 and later snapshots, qwen3.7-plus, qwen3.7-plus-2026-05-26 and later snapshots, qwen3.7-flash, qwen3.7-flash-2026-07-15 and later snapshots
- Qwen3.6 series: qwen3.6-max-preview, qwen3.6-plus, qwen3.6-plus-2026-04-02 and later snapshots, qwen3.6-flash, qwen3.6-flash-2026-04-16 and later snapshots, qwen3.6-27b, qwen3.6-35b-a3b
- Qwen3.5 series: qwen3.5-plus, qwen3.5-plus-2026-02-15 and later snapshots, qwen3.5-flash, qwen3.5-flash-2026-02-23 and later snapshots, qwen3.5-27b, qwen3.5-35b-a3b, qwen3.5-122b-a10b, qwen3.5-397b-a17b
- Qwen3-Max: qwen3-max, qwen3-max-2025-09-23 and later snapshots
- Qwen-Omni: qwen3.8-omni-flash, qwen3.5-omni-plus, qwen3.5-omni-plus-2026-03-15, qwen3.5-omni-flash, qwen3.5-omni-flash-2026-03-15 (the search strategy must be set to agent)
- Qwen-Omni-Realtime: qwen3.8-omni-flash-realtime, qwen3.5-omni-plus-realtime, qwen3.5-omni-plus-realtime-2026-03-15, qwen3.5-omni-flash-realtime, qwen3.5-omni-flash-realtime-2026-03-15 (the search strategy must be set to agent)
Third-party models
- DeepSeek: deepseek-v4-pro, deepseek-v4-pro-0813, deepseek-v4-flash, deepseek-v4-flash-0731, deepseek-v3.2 (the deepseek-v4 series also supports the Responses API)
- GLM: glm-5.2 (supported only by the Responses API)
- Kimi: kimi-k3 (supported only by the Responses API)

China (Beijing)

Qwen
- Qwen3.8 series: qwen3.8-max, qwen3.8-max-0902, qwen3.8-flash, qwen3.8-2.4t-a95b, qwen3.8-27b (search_strategy: agent is not supported; for agent-style retrieval, use the web_search tool through the Responses API)
- Qwen3.7 series: qwen3.7-max, qwen3.7-max-2026-05-20 and later snapshots, qwen3.7-plus, qwen3.7-plus-2026-05-26 and later snapshots, qwen3.7-flash, qwen3.7-flash-2026-07-15 and later snapshots
- Qwen3.6 series: qwen3.6-max-preview, qwen3.6-plus, qwen3.6-plus-2026-04-02 and later snapshots, qwen3.6-flash, qwen3.6-flash-2026-04-16 and later snapshots, qwen3.6-27b, qwen3.6-35b-a3b
- Qwen3.5 series: qwen3.5-plus, qwen3.5-plus-2026-02-15 and later snapshots, qwen3.5-flash, qwen3.5-flash-2026-02-23 and later snapshots, qwen3.5-27b, qwen3.5-35b-a3b, qwen3.5-122b-a10b, qwen3.5-397b-a17b
- Qwen3-Max: qwen3-max, qwen3-max-2025-09-23 and later snapshots
- Qwen-Max: qwen-max and later snapshots
- Qwen-Plus: qwen-plus, qwen-plus-latest, qwen-plus-2025-07-14 and later snapshots
- Qwen-Flash: qwen-flash, qwen-flash-2025-07-28 and later snapshots
- Qwen-Turbo: qwen-turbo
- QwQ: qwq-plus (supports only the default search strategy; search_strategy cannot be set)
- Qwen-Omni: qwen3.8-omni-flash, qwen3.5-omni-plus, qwen3.5-omni-plus-2026-03-15, qwen3.5-omni-flash, qwen3.5-omni-flash-2026-03-15 (the search strategy must be set to agent)
- Qwen-Omni-Realtime: qwen3.8-omni-flash-realtime, qwen3.5-omni-plus-realtime, qwen3.5-omni-plus-realtime-2026-03-15, qwen3.5-omni-flash-realtime, qwen3.5-omni-flash-realtime-2026-03-15 (the search strategy must be set to agent)
- Role-playing: qwen-plus-character, qwen-flash-character (the agent strategy is not supported)
Qwen-Max, Qwen-Plus, and Qwen-Flash models released after July 2025 automatically support web search.
Third-party models
- DeepSeek: deepseek-v4-pro, deepseek-v4-pro-0813, deepseek-v4-flash, deepseek-v4-flash-0731, deepseek-v3.2, deepseek-v3.2-exp, deepseek-v3.1, deepseek-r1-0528, deepseek-r1, deepseek-v3 (the deepseek-v4 series also supports the Responses API)
- GLM: glm-5.2 (supported only by the Responses API)
- Kimi: Moonshot-Kimi-K2-Instruct, kimi-k3 (kimi-k3 supported only by the Responses API)

Global

The following models are supported in the US (Virginia), China (Hong Kong), Japan (Tokyo), and Germany (Frankfurt) regions. In China (Hong Kong), Japan (Tokyo), and Germany (Frankfurt), you must call them from a workspace whose service deployment scope is Global. For more information, see Regions and access domains.

Qwen
- Qwen3.8 series: qwen3.8-max, qwen3.8-max-0902, qwen3.8-flash
- Qwen-Omni: qwen3.8-omni-flash (set the Chat Completions search strategy to agent; the Responses API is also supported)

Quick start

The following examples show how to query stock information using web search.

OpenAI compatible

Set enable_search=True to enable web search. For qwen3.8-omni-flash, also set search_options={"search_strategy": "agent"}. When using the Responses API, configure tools=[{"type": "web_search"}] instead. See Web search with the Responses API.

The OpenAI-compatible protocol does not support returning search sources in the response.

Python

import os
from openai import OpenAI

client = OpenAI(
    # If the environment variable is not set, provide your Model Studio API key directly, for example: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # The following configuration is for the Asia Pacific SE 1 (Singapore) region. Replace {WorkspaceId} with your workspace ID. Configurations differ by region.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)
completion = client.chat.completions.create(
    model="qwen-plus",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the stock price of Alibaba?"},
    ],
    extra_body={
        "enable_search": True,
        "search_options": {
            # Specify the web search strategy. Only 'agent' is supported.
            "search_strategy": "agent"
        }
    }
)
print(completion.choices[0].message.content)

Sample response

According to the latest market data, Alibaba's stock price in different markets is as follows:

*   US Stock (BABA): The latest price is approximately 159.84 USD.
*   Hong Kong Stock (09988.HK): The latest price is approximately 158.00 HKD.

Please note that stock prices fluctuate in real time, and this information is for reference only.

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY,
    // The following configuration is for the Asia Pacific SE 1 (Singapore) region. Replace {WorkspaceId} with your workspace ID. Configurations differ by region.
    baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
});

async function main() {
    const completion = await openai.chat.completions.create({
        model: "qwen-plus",
        messages: [
            { role: "user", content: "What is the stock price of Alibaba?" }
        ],
        enable_search: true,
        search_options: {
            // Specify the web search strategy. Only 'agent' is supported.
            search_strategy: "agent"
        }
    });
    console.log(completion.choices[0].message.content);
}

main();

Sample response

According to the latest market data, Alibaba's stock price in different markets is as follows:

*   US Stock (BABA): The latest price is approximately 159.84 USD.
*   Hong Kong Stock (09988.HK): The latest price is approximately 158.00 HKD.

Please note that stock prices fluctuate in real time, and this information is for reference only.

curl

# The following configuration is for the Asia Pacific SE 1 (Singapore) region. Replace {WorkspaceId} with your workspace ID. Configurations differ by region.
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": "qwen-plus",
    "messages": [
        {
            "role": "user",
            "content": "What is the stock price of Alibaba?"
        }
    ],
    "enable_search": true,
    "search_options": {
        "search_strategy": "agent"
    }
}'

DashScope

The DashScope protocol supports setting enable_source to true to include search sources in the response.

Python

import os
import dashscope
# The following configuration is for the Asia Pacific SE 1 (Singapore) region. Replace {WorkspaceId} with your workspace ID. Configurations differ by region.
dashscope.base_http_api_url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1"

response = dashscope.Generation.call(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen-plus",
    messages=[{"role": "user", "content": "Alibaba stock price"}],
    enable_search=True,
    search_options={
        # The web search strategy. Only 'agent' is currently supported.
        "search_strategy": "agent",
        "enable_source": True # Specifies whether to return search sources.
    },
    result_format="message",
)
print("="*20 + "search results" + "="*20)
for web in response.output.search_info["search_results"]:
    print(f"[{web['index']}]: [{web['title']}]({web['url']})")
print("="*20 + "response content" + "="*20)
print(response.output.choices[0].message.content)

Sample response

====================search results====================
[1]: [Alibaba(BABA) Stock Price_Quote_Chart - East Money](https://wap.eastmoney.com/quote/stock/106.BABA.html)
[2]: [Alibaba(BABA)_US Stock Quote_Today's Price & Chart_Sina Finance](https://gu.sina.cn/quotes/us/BABA)
[3]: [Alibaba(BABA) Stock Latest Price, Real-time Chart, Price Analysis & Prediction](https://cn.investing.com/equities/alibaba)
[4]: [Alibaba－W (9988.HK) Stock Price, News, Quote & History - Yahoo Finance](https://hk.finance.yahoo.com/quote/9988.HK/)
[5]: [Alibaba(BABA) Stock Price_Quote_Discussion - Xueqiu](https://xueqiu.com/S/BABA)
[6]: [Alibaba(BABA) Stock Price, Market Cap, Real-time Quote, Chart, Financials - Moomoo](https://www.moomoo.com/hans/stock/BABA-US)
[7]: [Alibaba Group Holding Limited (BABA) Stock Price, News, Quote ...](https://finance.yahoo.com/quote/BABA/)
[8]: [Alibaba - Tencent Securities](https://gu.qq.com/usBABA.N)
[9]: [W(09988) Stock Price, Market Cap, Real-time Quote, Chart, Financials - Alibaba - Moomoo](https://www.moomoo.com/hans/stock/09988-HK)
====================response content====================
According to the latest market data, Alibaba's stock price information is as follows:

*   :
    *   Today's opening price: 160.98 USD
    *   Yesterday's closing price: 160.80 USD
    *   Today's high: 161.19 USD
    *   Today's low: 156.20 USD

*   :
    *   Latest quote is approximately: 158.00 - 158.10 HKD
    *   Today's opening price: 156.50 HKD
    *   Previous trading day's closing price: 162.00 HKD
    *   Today's trading range: 156.30 - 158.40 HKD

Java

import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.aigc.generation.SearchOptions;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.utils.Constants;
import com.alibaba.dashscope.common.Role;
import java.util.Arrays;

public class Main {
    // The following configuration is for the Asia Pacific SE 1 (Singapore) region. Replace {WorkspaceId} with your workspace ID. Configurations differ by region.
    static {Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";}
    public static void main(String[] args) {
        Generation gen = new Generation();
        Message userMsg = Message.builder()
                .role(Role.USER.getValue())
                .content("Alibaba's stock price")
                .build();

        SearchOptions searchOptions = SearchOptions.builder()
                // Specify the web search strategy. Only 'agent' is supported.
                .searchStrategy("agent")
                // Specifies whether to return search sources.
                .enableSource(true)
                .build();

        GenerationParam param = GenerationParam.builder()
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-max")
                .messages(Arrays.asList(userMsg))
                .resultFormat(GenerationParam.ResultFormat.MESSAGE)
                .enableSearch(true)
                .searchOptions(searchOptions)
                .build();
        try {
            GenerationResult result = gen.call(param);
            System.out.println("=".repeat(20)+"search results"+"=".repeat(20));
            System.out.println(result.getOutput().getSearchInfo().getSearchResults());
            System.out.println("=".repeat(20)+"response content"+"=".repeat(20));
            System.out.println(result.getOutput().getChoices().get(0).getMessage().getContent());
        } catch (Exception e) {
            System.out.println("Error: " + e.getMessage());
        }
    }
}

Sample response

====================search results====================
[SearchInfo.SearchResult(siteName=null, icon=null, index=1, title=Alibaba(BABA) Stock Price_Quote_Chart - East Money, url=https://wap.eastmoney.com/quote/stock/106.BABA.html), SearchInfo.SearchResult(siteName=null, icon=null, index=2, title=Alibaba(BABA)_US Stock Quote_Today's Price & Chart_Sina Finance, url=https://gu.sina.cn/quotes/us/BABA), SearchInfo.SearchResult(siteName=null, icon=null, index=3, title=Alibaba(BABA) Stock Latest Price, Real-time Chart, Price Analysis & Prediction, url=https://cn.investing.com/equities/alibaba), SearchInfo.SearchResult(siteName=null, icon=null, index=4, title=Alibaba(BABA) Stock Price_Quote_Discussion - Xueqiu, url=https://xueqiu.com/S/BABA), SearchInfo.SearchResult(siteName=null, icon=null, index=5, title=Alibaba－W (9988.HK) Stock Price, News, Quote & History - Yahoo Finance, url=https://hk.finance.yahoo.com/quote/9988.HK/), SearchInfo.SearchResult(siteName=null, icon=null, index=6, title=Alibaba(BABA) Stock Price, Market Cap, Real-time Quote, Chart, Financials - Moomoo, url=https://www.moomoo.com/hans/stock/BABA-US), SearchInfo.SearchResult(siteName=null, icon=null, index=7, title=Alibaba Group Holding Limited (BABA) - Yahoo Finance, url=https://finance.yahoo.com/quote/BABA/), SearchInfo.SearchResult(siteName=null, icon=null, index=8, title=Alibaba - Tencent Securities, url=https://gu.qq.com/usBABA.N), SearchInfo.SearchResult(siteName=null, icon=null, index=9, title=W(09988) Stock Price, Market Cap, Real-time Quote, Chart, Financials - Alibaba - Moomoo, url=https://www.moomoo.com/hans/stock/09988-HK)]
====================response content====================
According to the latest market data, the stock price for Alibaba is as follows:

*   : The latest price is approximately .
*   : The latest price is approximately .

Please note that stock prices fluctuate in real time, and this information is for reference only.

curl

# The following configuration is for the Asia Pacific SE 1 (Singapore) region. Replace {WorkspaceId} with your workspace ID. Configurations differ by region.
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 "Content-Type: application/json" \
-d '{
    "model": "qwen-plus",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": "Alibaba's stock price"
            }
        ]
    },
    "parameters": {
        "enable_search": true,
        "search_options": {
            "search_strategy": "agent",
            "enable_source": true
        },
        "result_format": "message"
    }
}'

Sample response

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "content": "Based on the latest market data, Alibaba's stock price differs because it is listed on both US and Hong Kong stock exchanges:\n\n*   : The latest price is approximately .\n    *   Today's opening price: 160.98 USD\n    *   Today's price range: 156.20 - 161.19 USD\n\n*   : The latest price is approximately .\n    *   Today's opening price: 156.50 HKD\n    *   Today's price range: 156.30 - 158.40 HKD\n\nPlease note that stock prices fluctuate in real time, and this information is for reference only.",
          "role": "assistant"
        }
      }
    ],
    "search_info": {
      "search_results": [
        {
          "index": 1,
          "title": "Alibaba(BABA) Stock Price_Quote_Chart - East Money",
          "url": "https://wap.eastmoney.com/quote/stock/106.BABA.html"
        },
        {
          "index": 2,
          "title": "Alibaba(BABA)_US Stock Quote_Today's Price & Chart_Sina Finance",
          "url": "https://gu.sina.cn/quotes/us/BABA"
        },
        {
          "index": 3,
          "title": "Alibaba－W (9988.HK) Stock Price, News, Quote & History - Yahoo Finance",
          "url": "https://hk.finance.yahoo.com/quote/9988.HK/"
        },
        {
          "index": 4,
          "title": "Alibaba(BABA) Stock Latest Price, Real-time Chart, Price Analysis & Prediction",
          "url": "https://cn.investing.com/equities/alibaba"
        },
        {
          "index": 5,
          "title": "Alibaba(BABA) Stock Price_Quote_Discussion - Xueqiu",
          "url": "https://xueqiu.com/S/BABA"
        },
        {
          "index": 6,
          "title": "Alibaba(BABA) Stock Price, Market Cap, Real-time Quote, Chart, Financials - Moomoo",
          "url": "https://www.moomoo.com/hans/stock/BABA-US"
        },
        {
          "index": 7,
          "title": "W(09988) Stock Price, Market Cap, Real-time Quote, Chart, Financials - Alibaba - Moomoo",
          "url": "https://www.moomoo.com/hans/stock/09988-HK"
        },
        {
          "index": 8,
          "title": "Alibaba Group Holding Limited (BABA) Stock Price, News, Quote & History",
          "url": "https://hk.finance.yahoo.com/quote/BABA/"
        },
        {
          "index": 9,
          "title": "Alibaba - Tencent Securities",
          "url": "https://gu.qq.com/usBABA.N"
        }
      ]
    }
  },
  "usage": {
    "input_tokens": 2004,
    "output_tokens": 203,
    "plugins": {
      "search": {
        "count": 1,
        "strategy": "agent"
      }
    },
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "total_tokens": 2207
  },
  "request_id": "45c231d2-811e-4e04-a361-f2c1909f1dd9"
}

Web search with Responses API

You can enable web search by adding the web_search tool to the tools array of the tools parameter.

This feature is supported only for the following models: the Qwen3.8 Max, Flash, and open-source series, and qwen3.8-omni-flash; the Qwen3.7 and Qwen3.5 series models (including open-source models, but not Omni models), the Qwen3.6-Plus and Qwen3.6-Flash series, and qwen3.6-35b-a3b; qwen3-max and qwen3-max-2026-01-23; deepseek-v4-flash, deepseek-v4-flash-0731, deepseek-v4-pro, deepseek-v4-pro-0813; glm-5.2; and kimi-k3.

When enabled through the web_search tool, the model performs agent-style multi-turn retrieval — it can autonomously call web_search (and optionally web_extractor / code_interpreter) multiple times within a single response.

qwen3.8-max, qwen3.8-max-0902, qwen3.8-flash, qwen3.8-2.4t-a95b, and qwen3.8-27b do not support the agent value of search_strategy on the Chat Completions API. To use agent-style multi-turn retrieval with Qwen3.8, use the Responses API web_search tool documented in this section.

The Responses API does not use the search_strategy parameter. Whether web search is triggered — and whether the model performs multiple search rounds — is determined solely by attaching the web_search tool and by the model's own decisions. A search_options.search_strategy value passed to the Responses API is silently ignored and does not trigger a search.

For models that support these tools, enable web_search, web_extractor, and code_interpreter together. For qwen3.8-omni-flash, the only supported built-in tool is web_search.

For usage instructions, code examples, and migration guides for the Responses API, see OpenAI-compatible - Responses.

python

from openai import OpenAI
import os

client = OpenAI(
    # If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # This configuration is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. Configurations 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="What is the weather in Singapore tomorrow?",
    tools=[
        {"type": "web_search"},
        {"type": "web_extractor"},
        {"type": "code_interpreter"}
    ],
    extra_body={"enable_thinking": True}
)

print("="*20 + "Response content" + "="*20)
print(response.output_text)

print("="*20 + "Tool call trace" + "="*20)
# Agent-style multi-turn retrieval: the model may call web_search multiple times
for item in response.output:
    t = getattr(item, "type", None)
    if t == "web_search_call":
        q = getattr(getattr(item, "action", None), "query", "")
        print(f"[web_search_call] query={q}")
    elif t == "web_extractor_call":
        print(f"[web_extractor_call]")

print("="*20 + "Source citations" + "="*20)
for item in response.output:
    if getattr(item, "type", None) == "message":
        for part in item.content:
            for ann in getattr(part, "annotations", []) or []:
                if getattr(ann, "type", None) == "url_citation":
                    print(f"- {ann.title}: {ann.url}")

print("="*20 + "Tool call count" + "="*20)
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)}")

javascript

import OpenAI from "openai";

const openai = new OpenAI({
    // If you have not configured an environment variable, replace the following line with your Model Studio API key: apiKey: "sk-xxx",
    apiKey: process.env.DASHSCOPE_API_KEY,
    // This configuration is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. Configurations 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: "qwen3.8-max",
        input: "What is the weather in Singapore tomorrow?",
        tools: [
            { type: "web_search" },
            { type: "web_extractor" },
            { type: "code_interpreter" }
        ],
        enable_thinking: true
    });

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

    console.log("====================Tool call trace====================");
    // Agent-style multi-turn retrieval: the model may call web_search multiple times
    for (const item of response.output) {
        if (item.type === "web_search_call") {
            console.log(`[web_search_call] query=${item.action?.query || ""}`);
        } else if (item.type === "web_extractor_call") {
            console.log("[web_extractor_call]");
        }
    }

    console.log("====================Source citations====================");
    for (const item of response.output) {
        if (item.type === "message") {
            for (const part of item.content || []) {
                for (const ann of part.annotations || []) {
                    if (ann.type === "url_citation") {
                        console.log(`- ${ann.title}: ${ann.url}`);
                    }
                }
            }
        }
    }

    console.log("====================Tool call count====================");
    console.log(`Web search count: ${response.usage?.x_tools?.web_search?.count || 0}`);
}

main();

bash

# This configuration is for the Singapore region. Replace {WorkspaceId} with your actual workspace ID. Configurations vary by region.
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": "qwen3.8-max",
    "input": "What is the weather in Singapore tomorrow?",
    "tools": [
        {"type": "web_search"},
        {"type": "web_extractor"},
        {"type": "code_interpreter"}
    ],
    "enable_thinking": true
}'

Sample response output (agent-style multi-turn retrieval)

For a query such as "What is the weather in Singapore tomorrow?", the model performs multiple retrieval rounds within a single response. The output array contains multiple web_search_call (and optionally web_extractor_call) items interleaved with reasoning and the final message:

{
    "output": [
        { "type": "reasoning", "..." : "..." },
        { "type": "web_search_call", "action": { "query": "Singapore weather tomorrow" } },
        { "type": "reasoning", "..." : "..." },
        { "type": "web_extractor_call", "..." : "..." },
        { "type": "web_search_call", "action": { "query": "Singapore 7-day forecast" } },
        { "type": "reasoning", "..." : "..." },
        { "type": "message", "content": [ /* final answer with url_citation annotations */ ] }
    ],
    "usage": {
        "x_tools": { "web_search": { "count": 2 } }
    }
}

The presence of multiple web_search_call items and x_tools.web_search.count > 1 confirms agent-style multi-turn retrieval — the model decided on its own to refine the query and search again.

Get search sources

After a web search runs, the search sources are returned in the response. They appear in the element whose type is web_search_call within the output array, and its action.sources field is the list of source links. You can extract them from the response in the example above as follows:

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

NoteThe web search described in this topic refers to the model's built-in web search feature, which is billed as described below and does not include a free call quota. It is separate from the Web Search MCP service offered in the Model Studio MCP marketplace, and the two are billed independently: the Web Search MCP service provides a free quota of 2,000 calls for all users, after which it is billed at CNY 29 per 1,000 calls. For more information, see Add web search MCP.

Charges for web search consist of two components:

model call fees: The web search feature appends retrieved web content to the prompt, increasing the number of input tokens. These tokens are billed at the model's standard rate. For pricing details, see the Model Studio console. When you use the Responses API, the web search tool is billed at the same rate as the agent policy.
search policy fees:
- agent policy:
  - The fee per 1,000 calls is as follows:
    - For the China (Beijing), US (Virginia), China (Hong Kong), Japan (Tokyo), and Germany (Frankfurt) regions: $0.573411.
    - For the Singapore region: $10.00.
- agent_max policy (Limited-time offer):
  This policy covers both the web search and the web extractor tool.
  - Fee per 1,000 calls for the web search tool:
    - For the China (Beijing), US (Virginia), China (Hong Kong), Japan (Tokyo), and Germany (Frankfurt) regions: $0.573411.
    - For the Singapore region: $10.00.
  - The web extractor tool is free for a limited time.

Error messages

To troubleshoot errors, see Error codes.