> For the complete documentation index, see [llms.txt](https://docs.cherry-ai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherry-ai.com/docs/en-us/pre-basic/websearch.md).

# Web-connected Mode

{% hint style="info" %}
Online mode lets AI search for the latest content before answering, suitable for the following scenarios:

* **Time-sensitive information**: news, prices, exchange rates, etc. that happened today / this week / just now
* **Real-time data**: dynamic values such as weather, stock prices, and product inventory
* **Emerging knowledge**: newly appeared tools, concepts, technologies
  {% endhint %}

## How to enable online mode

Click the 🌐 **small globe** icon in the toolbar of the chat input box to enable online mode for the current conversation.

<figure><img src="/files/e4a71bc6ca10755c8ea2b8d2ac43992c3d29e413" alt=""><figcaption><p>Click the globe icon to enable online mode</p></figcaption></figure>

<figure><img src="/files/f8c4f2d3c7d83218146d9972c512f12d6bda3e57" alt=""><figcaption><p>Enabled status</p></figcaption></figure>

## Two technical paths for online mode

Cherry Studio through**two methods**to achieve online mode, and it automatically decides based on the model you choose:

### Path 1: The model's built-in online capability (recommended)

Some large model providers**natively integrate search capabilities**. These models will display a**small globe icon 🌐**.

. After enabling online mode for the conversation, AI directly calls the model's own search capability,**without any additional configuration**.

<figure><img src="/files/6a3150600cb0e5767c3141e50f65abbb635907e1" alt=""><figcaption><p>The small globe icon after the model name</p></figcaption></figure>

in `Settings → Model Services` can also be used to tell them apart.

<figure><img src="/files/51ae70af198f681193f5651d5532d4c506d1b2f6" alt=""><figcaption></figcaption></figure>

**Known models/providers that support native online mode**:

* Google Gemini (some versions)
* OpenRouter (all models supported)
* Tencent Hunyuan
* Zhipu AI
* Alibaba Cloud Bailian (some models)
* xAI Grok

{% hint style="info" %}
There are also a few models that can access the internet even if no small globe icon is shown (depending on the provider's configuration). For example, [the kind of situation introduced in Volcano Engine's online access integration](/docs/en-us/pre-basic/websearch/volcengine.md) .
{% endhint %}

### Path 2: Through an external search service (for models without online capability)

If the model you choose does not have built-in online mode (as is the case for most open-source/classic models), Cherry Studio will**call the configured external search service**and feed the search results to the model as context.

Open `Settings → Web Search` Add and enable any search service. Cherry Studio has built-in support for:

| Search service            | Type          | Notes                                                                                                                                     |
| ------------------------- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| **Tavily**                | Cloud         | A well-established option; the free quota is enough for everyday use [→ Registration tutorial](/docs/en-us/pre-basic/websearch/tavily.md) |
| **Bocha**                 | Cloud         | Friendly to access from China; good results in Chinese scenarios                                                                          |
| **Exa**                   | Cloud         | Academic / technical content-oriented                                                                                                     |
| **Exa MCP**               | Cloud         | Exa's MCP interface version                                                                                                               |
| **Zhipu (Zhipu AI)**      | Cloud         | Zhipu's own search API                                                                                                                    |
| **Querit**                | Cloud         | Friendly to access from China                                                                                                             |
| **SearXNG**               | Self-hosted   | Open-source metasearch engine, can be fully localized [→ Deployment tutorial](/docs/en-us/pre-basic/websearch/searxng.md)                 |
| **Google / Bing / Baidu** | Local browser | Open the browser search page directly,**without reading the content back to AI**, only as an aid for finding information                  |

#### First-time enabling Tavily (the most common zero-config choice)

1. After clicking 🌐 in the chat box, if no external search service has been configured yet, a popup will prompt you
2. Click **Go to Settings** → Go to web search configuration
3. Select Tavily, click **Get Secret Key** Go to the Tavily official website to register
4. Create an API Key in the Tavily console
5. Copy the Key back into Cherry Studio

<figure><img src="/files/b27c8e64eb13e2b00e05ae8804a2fd1568025a5c" alt=""><figcaption><p>Popup: Go to settings</p></figcaption></figure>

<figure><img src="/files/81660fc8f5c3132063dfbeddc1ab0f9427490332" alt=""><figcaption><p>Click Get Secret Key</p></figcaption></figure>

<figure><img src="/files/81660fc8f5c3132063dfbeddc1ab0f9427490332" alt=""><figcaption><p>Go to get the Secret Key</p></figcaption></figure>

<figure><img src="/files/5e2d01d57ce544e6f8bd459c46d8036f01064336" alt=""><figcaption><p>Copy API Key</p></figcaption></figure>

<figure><img src="/files/93b9f0755aac3172bd6f7a070f83dfdb1388f401" alt=""><figcaption><p>Paste API Key</p></figcaption></figure>

See the detailed registration process at [Tavily online access login and registration tutorial](/docs/en-us/pre-basic/websearch/tavily.md).

{% hint style="warning" %}
Tavily's free quota has a monthly call limit; after exceeding it, payment is required. If you plan to use it heavily for a long time, it is recommended to switch to [local SearXNG deployment](/docs/en-us/pre-basic/websearch/searxng.md) or other options such as Bocha.
{% endhint %}

## Search result blacklist

Don't want some unreliable websites to appear in the search results? Refer to [web search blacklist configuration](/docs/en-us/pre-basic/websearch/blacklist.md) to block them.

## Free online mode

If you don't want to spend a penny and still want to use search capabilities, see [Free online mode](/docs/en-us/pre-basic/websearch/free-search.md).

## How it works

No matter which path is used, the conversation flow is:

1. You ask "What's the weather in Shanghai today?"
2. Cherry Studio sends the question to the search service first
3. The search service returns N relevant web page summaries
4. Cherry Studio pastes these summaries into the prompt and sends them to the AI model
5. AI answers you based on real-time data

<figure><img src="/files/aa5be8d0f8f779ce2dd7c0732147ca13423b6791" alt=""><figcaption><p>Example of online search results</p></figcaption></figure>

<figure><img src="/files/0cc40491403bac347d3a12dc3e94780f53f7dcdb" alt=""><figcaption><p>Example of an online answer</p></figcaption></figure>

***

### 💡 Get help and submit feedback

If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to [Feedback and Suggestions](/docs/en-us/question-contact/suggestions.md) the official channels provided there.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.cherry-ai.com/docs/en-us/pre-basic/websearch.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.