> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aiohub.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Cherry Studio

> Configure AIOHub as a model provider in Cherry Studio.

[Cherry Studio](https://www.cherry-ai.com) is a multi-model desktop chat client for Linux, macOS, and Windows.

## Prerequisites

* [Cherry Studio](https://www.cherry-ai.com/download) installed
* An [AIOHub API key](/en/account/create-token)

## Setup

<Steps>
  <Step title="Add a model provider">
    Open **Settings** -> **Model Provider**, then create a new provider:

    | Field         | Value                    |
    | ------------- | ------------------------ |
    | Provider name | AIOHub                   |
    | Provider Type | OpenAI API               |
    | API Key       | `sk-your-api-key`        |
    | API Host      | `https://api.aiohub.org` |
  </Step>

  <Step title="Select models">
    Open **Models** -> **Manage**, then enable the models you want to use.
  </Step>

  <Step title="Verify connection">
    Use the **Check** button to verify the provider connection.
  </Step>

  <Step title="Start chatting">
    Open **Assistant**, create or edit an assistant, and select the configured model.
  </Step>
</Steps>

<Note>This page follows Cherry Studio's OpenAI API Provider fields. If you choose an Anthropic, Gemini, or Responses provider type in Cherry Studio, the required Base URL and visible models follow that protocol. Verify that basic chat works first, then switch provider types if needed.</Note>

## Image models

AIOHub publicly supports OpenAI Images generation and editing endpoints. Whether Cherry Studio's image features work depends on whether the selected model and the API key's group support image generation or editing.

If you only want to test GPT image generation in the browser, use [Imagine](/en/clients/imagine).

## Troubleshooting

<AccordionGroup>
  <Accordion title="Connection check fails">
    Confirm the API Host includes `https://` and the API key is valid.
  </Accordion>

  <Accordion title="Model list is empty">
    Confirm the Provider Type is **OpenAI API**, then manually enable or add the models you want to use.
  </Accordion>
</AccordionGroup>