# Connect Cursor

https://omnimodel.me/apps/cursor

> AI code editor whose chat models can be pointed at a custom endpoint.

## Use cases

Good for chat-driven coding, explanations and refactoring in the editor by pointing Cursor's chat models at this platform. Tab completion still uses Cursor's own models.

## Tips

Coding prompts tend to be long, so pick a long-context model and set a daily spend limit on the key to keep long tasks in check.

## 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 → Models and expand OpenAI API Key.
2. Paste the key, tick Override OpenAI Base URL, and set the API host.
3. Add the model ID to the list and hit Verify.

## Settings

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

> Built-in features such as Tab completion stay on Cursor's own models; overriding the base URL does not change how they are billed.

## FAQ

### Does Tab completion use the platform's models?

No. The custom endpoint applies only to chat models; Tab completion keeps using Cursor's own models.

### Why does it say the model is unavailable?

Make sure the model ID matches the catalog and is in the key's allowed models.