# Connect Cherry Studio

https://omnimodel.me/apps/cherry-studio

> Desktop client for many models, with assistant presets and a local knowledge base.

## Use cases

Good for using several models on the desktop: set up assistant presets for different tasks, switch models within a chat to compare answers, and query a local knowledge base.

## Tips

Create a separate key for this client and limit its allowed models, so its usage is easy to track.

## If it cannot connect

1. Use `https://omnimodel.me/v1` as the API host, without `/chat/completions`.
2. The key starts with `key_` and is not paused or revoked; `auth.invalid_key` means the key cannot be used.
3. The model ID matches the [catalog](/catalog) and is in the key's allowed models.
4. `billing.insufficient_credit` means the balance is too low; see [common errors](/docs/errors?lang=en) for more.

## Setup

1. Open Settings → Model Providers and add an OpenAI-compatible provider.
2. Fill in the API host and key below, then run the connectivity check.
3. Add the model ID under Models and pick it in a new conversation.

## Settings

- API host：`https://omnimodel.me/v1`
- API key：`YOUR_API_KEY`
- Model：`MODEL_ID`

## FAQ

### Can I add several models?

Yes. Add each model ID under the same OpenAI-compatible provider and switch between them in a chat.

### Which models does the local knowledge base use?

It needs an embedding model; pick one tagged Embedding in the catalog and add it to the provider.