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

# OpenAI BYOK

> Set up a runner LLM integration that uses your OpenAI API key

<Note>Available for Enterprise organizations where OpenAI model routing is enabled. [Contact sales](https://ona.com/contact/sales) to learn more.</Note>

Use OpenAI BYOK when your organization wants OpenAI model requests to use your OpenAI API key or OpenAI-compatible endpoint.

This page covers organization-level runner configuration. To connect a user's ChatGPT plan for Codex, see [Connect Codex to ChatGPT](/ona/integrations/configure-codex).

## Prerequisites

* Your organization has OpenAI model routing enabled.
* You have an enterprise runner configured in Ona.
* The runner can reach your OpenAI or OpenAI-compatible endpoint over HTTPS.
* You have an OpenAI API key or the credentials required by your OpenAI-compatible endpoint.

## Add the integration with the UI

1. Go to the [Runners settings page](https://app.ona.com/settings/runners).
2. Select the runner where you want to configure OpenAI BYOK.
3. Scroll to **LLM Providers**.
4. Click **Configure**.
5. Select **OpenAI**.
6. Use the **OpenAI** model option.
7. Use `https://api.openai.com/v1` for direct OpenAI, or enter your OpenAI-compatible endpoint.
8. Paste the API key into **API Key**.
9. Click **Create Integration**.

<img src="https://mintcdn.com/gitpod-13c83c2b/6AE6QOjt97Jfm39Y/images/openai-llm-integration.png?fit=max&auto=format&n=6AE6QOjt97Jfm39Y&q=85&s=3ee916c8203179c464c04ce13c83ab40" alt="OpenAI LLM integration form showing endpoint URL, API key, and OpenAI model fields" width="674" height="630" data-path="images/openai-llm-integration.png" />

## Add the integration with the CLI

```bash theme={null}
gitpod runner config llm-integration create <runner-id> SUPPORTED_MODEL_OPENAI_AUTO https://api.openai.com/v1 <openai-api-key>
```

For an OpenAI-compatible endpoint, replace `https://api.openai.com/v1` with your endpoint URL.

To verify the integration:

```bash theme={null}
gitpod runner config llm-integration list
```

## Verify the integration

1. Create a new environment with the configured runner.
2. Start an agent that uses OpenAI model routing.
3. Confirm that the agent can answer a simple code question.

## Troubleshooting

<Accordion title="OpenAI is not shown">
  OpenAI BYOK is available only when OpenAI model routing is enabled for your organization. Contact your account manager if you expect this option to be available.
</Accordion>

<Accordion title="Authentication fails">
  Verify that the API key is active and has access to the OpenAI endpoint you configured. If you use an OpenAI-compatible endpoint, confirm that the endpoint expects the same bearer-token authentication format.
</Accordion>

<Accordion title="Requests do not reach a custom endpoint">
  Confirm that the runner can reach the endpoint over HTTPS. If the runner is in a private network, check outbound routing, firewall rules, and any proxy configuration required by your network.
</Accordion>