> 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/moonshot.md).

# Moonshot AI (Kimi)

Moonshot AI is a well-known domestic large-model team, and its flagship product is **Kimi**, with **ultra-long context**(up to 2 million Chinese characters) as its strength, suitable for feeding large chunks of documents/code to let AI help you process them.

## Get API Key

* Go to [Moonshot Open Platform](https://platform.moonshot.cn/) Register account
* Enter `API Key Management` Create `sk-...` key
* Top up any amount to activate (minimum is very small)

## Configure in Cherry Studio

* After enabling it `Settings → Model Services`, find **Moonshot AI** Provider to enter the details page
* Fill in `sk-...` key
* API address defaults to `https://api.moonshot.cn`
* Click **Get model list**

## Recommended usage

| Model                | Suitable scenarios                           |
| -------------------- | -------------------------------------------- |
| `moonshot-v1-8k`     | Short context, cheap and fast                |
| `moonshot-v1-32k`    | Medium context, enough for everyday use      |
| `moonshot-v1-128k`   | Long context, document analysis, code review |
| `kimi-k2-* / k2.5-*` | Latest flagship, stronger reasoning ability  |

## Suitable scenarios

* **Ultra-long PDF / document analysis**: Moonshot's long-context advantage is most obvious
* **Large code review**: Can fit the complete file at once without splitting
* **Summarizing an entire e-book**: Long-context models save the hassle of manual slicing

{% hint style="info" %}

* Moonshot's "context caching" feature can significantly reduce token usage in repeated conversations; refer to its official documentation
* Kimi has its own chat interface on the web, but connecting via Cherry Studio API lets you use Cherry Studio's assistant, knowledge base, MCP tools, and other extensions
  {% endhint %}

***

### Get help and submit feedback

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


---

# 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/moonshot.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.