# Connect Open WebUI

https://omnimodel.me/apps/open-webui

> Self-hosted web UI that can serve local inference and a relay endpoint side by side.

## Use cases

Good if you already run local inference: use local models and this platform's models side by side in one web UI.

## 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. Go to Settings → Connections and add an OpenAI API connection.
2. Fill in the API host and key below, then save.
3. Refresh the model list and pick a model.

## Settings

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

## FAQ

### Why is a model missing from the list?

Open WebUI fetches GET /v1/models, which shows only models your key can call. Check the key's allowed models and refresh.

### Can I use it alongside local models?

Yes. Add the platform as an OpenAI-compatible connection; your local connections are unaffected.