> 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/settings/default-models.md). # Default Model Settings Cherry Studio needs to "pick a model to use" in many scenarios (for example, helping you name a conversation, optimize prompts, translate, generate images), and it’s impossible to ask you "which model to use" every time.**Default model settings** That is, to tell Cherry Studio:**Which model to use when I don't specify it**. > Note: these are models used by the "behind-the-scenes helpers",**they can be different from the model used to chat with you**. The main chat model is set separately in each assistant.

Default models (① is the section title): below, choose one for each of the four default models: Default Assistant / Quick / Translate / Draw

## What do the 4 default models handle respectively? ### Default assistant model * **Who uses it**: when an assistant hasn’t specified its own model, this model is used automatically * **How to choose**: choose a conversation model you use often, that is stable and reasonably priced ### Quick model * **Who uses it**:**Conversation naming**,**Search keyword extraction** and other lightweight internal tasks that don’t require top-tier intelligence * **How to choose**: use **cheap and fast** model is fine; it’s recommended to choose a lightweight model, not a reasoning model ### Translation model * **Who uses it**: message translation in chat boxes, translation page;[Text selection assistant](/docs/en-us/cherry-studio/preview/selection-assistant.md) translation operations in * **How to choose**: ordinary conversation models are fine; if you do a lot of Chinese-English translation, DeepSeek or Claude series works better ### Painting model * **Who uses it**: the model used by default for image generation (drawing) * **How to choose**: choose an image generation model you have already configured (e.g. the qwen-image series) ## Recommendation in one sentence If you don’t want to go into details, just fill it in as below: | Field | Recommended | | ----------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | | Default assistant model | Your most frequently used conversation model | | Quick model | A cheap, fast lightweight model | | Translation model | Any conversation model that can follow instructions works (you can also choose a dedicated translation model, such as the qwen-mt series) | | Painting model | The image generation model you have already configured | If you’re unsure, just leave everything at the default. After using it for a while, if you find something isn’t enough, come back and adjust it. *** ### 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/settings/default-models.md?ask=&goal= ``` `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.