> For the complete documentation index, see [llms.txt](https://docs.ox.security/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ox.security/fix-with-ox/gpt.md).

# OX GPT

The GPT connector lets OX run AI-powered capabilities with your own GPT account and policies.

When connected, OX routes all LLM requests with your GPT token. Ownership, logging, and billing stay on your side, and your network rules apply.

For on-prem, the connector is required to enable AI capabilities. For SaaS, it lets you use AI without relying on an OX-managed account, whether for compliance, data-handling, or internal policy.

During operation, OX sends only the context required to fulfill a request, for example, prompts or short code snippets, to your configured provider, so confirm that this aligns with your organization’s data-handling policy.

### GPT SaaS vs on-prem

| Deployment Mode | Without GPT Connector                                   | With GPT Connector                                        | Data Path                                                                             |
| --------------- | ------------------------------------------------------- | --------------------------------------------------------- | ------------------------------------------------------------------------------------- |
| OX SaaS         | AI capabilities are available by default with OX token. | Requests are routed to your GPT account using your token. | OX calls the provider API on your behalf.                                             |
| OX On-Prem      | AI capabilities are unavailable until configured.       | Required. Requests run with your GPT token.               | Requests leave your environment only to the approved provider or proxy you configure. |

## Prerequisites

| Item           | Details                             |
| -------------- | ----------------------------------- |
| GPT API token  | Active API token for your provider. |
| OX permissions | OX Admin account.                   |

## Connecting to GPT

1. In the OX platform, go to the **Connectors** page.
2. Select **Add Connector** and search for **GPT**.
3. In the **Configure your ChatGPT credentials** dialog, select **CONNECT**.

<figure><img src="https://884876233-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FdK3XMLdV8zRg847RmGmZ%2Fuploads%2Fgit-blob-b938f3a23e05af025b41305c488540fe4bfa8d6e%2FGPT_Connect.png?alt=media" alt=""><figcaption></figcaption></figure>

| Field     | Description                                          |
| --------- | ---------------------------------------------------- |
| **Token** | The provider token OX uses to authenticate requests. |

4. Select **CONNECT**. AI capabilities become available. OX does not use an OX-managed account.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.ox.security/fix-with-ox/gpt.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
