# Connect n8n

https://omnimodel.me/apps/n8n

> General automation platform; its built-in OpenAI node accepts a custom endpoint.

## Use cases

Good for calling models from general automations: use the built-in OpenAI node pointed at this platform to generate, classify or summarize text in any flow.

## Tips

Workflows call models in bulk and unattended. Set a monthly spend limit on the key and watch the failure rate in [usage](/docs/usage?lang=en).

## 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. Create an OpenAI credential with the API key and base URL below.
2. Add an OpenAI node to the workflow and select that credential.
3. Set the model field to the model ID you want.

## Settings

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

## FAQ

### Will frequent triggers get rate limited?

Exceeding the rate or concurrency limit returns 429. Enable retries on the node and keep concurrency down.

### Can I see what one flow costs?

Give the flow its own key, then filter usage by that key.