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

# DeepSeek

DeepSeek is one of the mainstream domestic large-model providers. Its V3 / R1 series is well known for coding and reasoning tasks, and it is affordable.

## Get API Key

* Go to [DeepSeek Platform](https://platform.deepseek.com/) Register account
* `API Keys` → `Create API Key`, copy `sk-...` key
* Top up any amount (you can activate it with as little as ¥1)

## Configure in Cherry Studio

* After opening `Settings → Model Services`, find **deepseek** Provider to enter the details page
* **API key** Enter `sk-...`
* **API Address** By default `https://api.deepseek.com`, no need to modify
* Click **Get model list**

## Recommended usage

| Model               | Suitable scenarios                                                                           |
| ------------------- | -------------------------------------------------------------------------------------------- |
| `deepseek-chat`     | General chat, extremely cost-effective                                                       |
| `deepseek-reasoner` | Math, code, complex reasoning. Note that the output will include `<thinking>` thinking block |

## Native web search

Models in DeepSeek that support web connectivity can directly use the provider's native web search. When selecting a model, check whether there is a 🌐 icon next to its name; the specific support scope may change with provider updates, so it is not recommended to judge based only on the model name.

After turning on 🌐 in the conversation, if \[Settings] → \[Web Search] has \[Prefer configured search service] enabled, Cherry Studio will prioritize the configured search service; only after disabling this option will it prioritize the model's native web connectivity. See Web Connectivity Mode for details.

## Combination with global memory

DeepSeek itself does not have embedding models. If you want to use a knowledge base:

* It is recommended to use embedding models from another provider (for example [SiliconFlow](/docs/en-us/pre-basic/providers/siliconcloud.md) of `bge-m3` or [OpenAI](/docs/en-us/pre-basic/providers/openai.md) of `text-embedding-3-small`)
* You can still use DeepSeek for the chat model

{% hint style="info" %}

* DeepSeek charges by token, and cache hits can greatly reduce costs (refer to its official documentation)
* `deepseek-reasoner` The reasoning content will be rendered in the conversation by default, and can be [Chat settings](/docs/en-us/cherry-studio/preview/chat.md#dui-hua-she-zhi) toggle "Auto-collapse reasoning content" in
  {% endhint %}

***

### 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) for the official channels provided.


---

# 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.cherryai.com.cn/docs/en-us/pre-basic/providers/deepseek.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.