> 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/zi-ding-yi-fu-wu-shang.md).
# Custom providers
Cherry Studio not only integrates mainstream AI model services, but also gives you powerful customization capabilities. Through **Custom AI Service Providers** feature, you can easily connect to any AI model you need.
## Why do you need custom AI service providers?
* **Flexibility:** No longer limited to the preset provider list, freely choose the AI model that best suits your needs.
* **Diversity:** Try AI models from various platforms and discover their unique strengths.
* **Controllability:** Directly manage your API keys and access URLs to ensure security and privacy.
* **Customization:** Connect to privately deployed models to meet the needs of specific business scenarios.
## How do you add a custom AI service provider?
With just a few simple steps, you can add your custom AI service provider in Cherry Studio:
1. **Open Settings:** In the left navigation bar of the Cherry Studio interface, click "Settings" (gear icon).
2. **Go to Model Services:** On the Settings page, select the "Model Services" tab.
3. **Add Provider:** On the "Model Services" page, you will see a list of existing providers. Click the "+ Add Provider" button below the list to open the "Add Custom Provider" dialog.
4. **Fill in the information:** In the dialog, you need to fill in the following information:
* **Provider Name:** Give your custom provider an easily recognizable name (for example: MyCustomOpenAI).
* **API Key** The API key you obtained from your provider.
* **Endpoint settings** By default, you can add **OpenAI** and **Anthdropic** endpoints. You can also click "More Settings" to add **OpenAI Responses**,**Gemini**,**Image Generation Base URL** and **Image Editing Base URL**. Cherry Studio will send requests to the endpoint.
{% hint style="warning" %}
Be sure to refer to the official documentation provided by your AI service provider to obtain the correct API endpoint and key.
{% endhint %}
{% hint style="info" %}
You can also choose "Create from preset" in "More Settings", suitable for Coding Plan integration, multiple account management, or project isolation; endpoints and API Key can be configured independently.
{% endhint %}
6. **Save configuration:** After filling everything in, click the "Add" button to save your configuration.
## Configure custom AI service provider
After adding it, you need to find the provider you just added in the list and configure it in detail:
1. **Enabled status** In the custom provider list, an enabled custom provider will show a green dot on the right. You can turn this provider on or off in the upper-right corner of the provider page.
2. **Model management:**
* Click the "Get model list" button and Cherry Studio will try to fetch the model list from your provider. After a successful fetch, you can add and delete models.
* Click the "+" button to manually add the model ID you want to use under this provider. For example `gpt-5.6-sol`,`gemini-3.7-flash` and so on.
* If you are not sure of the exact model name, please refer to the official documentation provided by your AI service provider.
* You can click the "-" on the right of a model to delete it, and click the settings button to edit the model's name, type, price, and other data.
## Get started
After completing the above configuration, you can select your custom AI service provider and model in Cherry Studio's chat interface and start conversing with AI!
## Using vLLM as a custom AI service provider
vLLM is a fast and easy-to-use LLM inference library similar to Ollama. The following are the steps to integrate vLLM into Cherry Studio:
1. **Install vLLM:** Follow the official vLLM documentation () to install vLLM.
```sh
pip install vllm # if you use pip
uv pip install vllm # if you use uv
```
2. **Start the vLLM service:** Start the service using the OpenAI-compatible interface provided by vLLM. There are mainly two ways, as follows:
* Use `vllm.entrypoints.openai.api_server` to start
```sh
python -m vllm.entrypoints.openai.api_server --model gpt2
```
* Use `uvicorn` to start
```sh
vllm --model gpt2 --served-model-name gpt2
```
Make sure the service starts successfully and listens on the default port `8000` . Of course, you can also use the parameter `--port` to specify the port number for the vLLM service.
3. **Add the vLLM provider in Cherry Studio:**
* Follow the steps described earlier to add a new custom AI service provider in Cherry Studio.
* **Provider Name:** `vLLM`
* **Provider type:** Select `OpenAI`.
4. **Configure the vLLM provider:**
* **API Key:** Since vLLM does not require an API key, you can leave this field blank or fill in any content.
* **API Address:** Fill in the API address of the vLLM service. By default, the address is: `http://localhost:8000/`(if you use a different port, modify it accordingly).
* **Model management:** Add the model name loaded in vLLM. In the example run above, you should enter `python -m vllm.entrypoints.openai.api_server --model gpt2` here `gpt2`
5. **Start chatting:** Now, you can select the vLLM provider and `gpt2` model in Cherry Studio and start conversing with the LLM powered by vLLM!
## Tips and tricks
* **Read the documentation carefully:** Before adding a custom provider, be sure to carefully read the official documentation of the AI service provider you are using to understand key information such as API keys, access URLs, and model names.
* **Check the API key:** Use the "Check" button to quickly verify whether the API key is valid, avoiding issues caused by an incorrect key.
* **Pay attention to the API address:** Different AI service providers and models may have different API addresses, so be sure to enter the correct one.
* **Add models as needed:** Please only add the models you will actually use to avoid adding too many unnecessary models.
***
### 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) official channels provided in.
---
# 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/zi-ding-yi-fu-wu-shang.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.
%20(5).png?alt=media)
%20(5)%20(1).png?alt=media)
%20(5).png?alt=media)