> 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/zhong-wen-fan-ti/pre-basic/providers/deepseek.md).

# DeepSeek

DeepSeek 係國內主流大模型廠商之一，以 V3 / R1 系列喺編程同推理任務上有口皆碑，而且價錢親民。

## 拎 API Key

* 去 [DeepSeek 平台](https://platform.deepseek.com/) 註冊帳號
* `API 金鑰` → `建立 API Key`，複製 `sk-...` 密鑰
* 增值任何金額（最低 ¥1 即可開通）

## 喺 Cherry Studio 設置

* 打開 `設定 → 模型服務`，搵到 **deepseek** Provider 入去詳情頁
* **API 密鑰** 填入 `sk-...`
* **API 地址** 預設 `https://api.deepseek.com`，唔使修改
* 撳 **獲取模型列表**

## 推薦用法

| 模型                  | 適合場景                                 |
| ------------------- | ------------------------------------ |
| `deepseek-chat`     | 通用對話，性價比極高                           |
| `deepseek-reasoner` | 數學、程式碼、複雜推理。注意輸出會帶 `<thinking>` 思考區塊 |

## 同全局記憶嘅配搭

DeepSeek 自家冇嵌入模型。如果你要用 [全局記憶](/docs/zhong-wen-fan-ti/advanced-basic/memory.md) 或者知識庫：

* 嵌入模型建議用其他 Provider 嘅（例如 [硅基流動](/docs/zhong-wen-fan-ti/pre-basic/providers/siliconcloud.md) 嘅 `bge-m3` 或者 [OpenAI](/docs/zhong-wen-fan-ti/pre-basic/providers/openai.md) 嘅 `text-embedding-3-small`）
* 對話模型仍然可以用 DeepSeek

{% hint style="info" %}

* DeepSeek 價錢按 token 計費，快取命中可大幅減價（參考佢官方文件）
* `deepseek-reasoner` 嘅思考內容預設會渲染喺對話入面，可喺 [對話設定](/docs/zhong-wen-fan-ti/cherry-studio/preview/chat.md#dui-hua-she-zhi) 中切換「思考內容自動摺疊」
  {% endhint %}

***

### 💡 獲取幫助同提交反饋

如果您喺配置或使用過程中遇到任何疑問、Bug 或有功能改進建議，請參考 [反饋同建議](/docs/zhong-wen-fan-ti/question-contact/suggestions.md) 入面提供嘅官方渠道。


---

# 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:

```
GET https://docs.cherry-ai.com/docs/zhong-wen-fan-ti/pre-basic/providers/deepseek.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.