> For the complete documentation index, see [llms.txt](https://docs.burpgpt.app/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.burpgpt.app/model-setup/use-supported-local-model-providers/with-openai-compatible-api.md).

# Configure an OpenAI-compatible API

Connect to a model endpoint that supports OpenAI-compatible chat completions.

Use `OpenAI-compatible API` for a local, self-hosted, or third-party endpoint that supports the OpenAI chat completions schema.

Before you start, have the endpoint's API base URL, model identifier, and API key if required. Confirm that the model server is reachable from the computer running Burp.

## Configure the provider

1. Open the `BurpGPT Pro` tab and select `Provider settings`.
2. Select `OpenAI-compatible API` from `Model provider`.
3. Enter the API `Base URL`, typically ending in `/v1`. Do not enter the full `/chat/completions` URL.
4. Enter an `API key` if the endpoint requires authentication.
5. Enter the exact `Model` identifier exposed by the endpoint and press Enter to apply it. The dropdown contains examples; it does not query the endpoint's model list.
6. Set `Read timeout` in seconds.
7. Configure `Request parameters` using the extension's [supported fields](/getting-started/supported-model-providers.md#request-parameters). Only include parameters accepted by your endpoint and model.
8. Click `Test request`.

The editor checks parameter names and value types. The endpoint determines whether a model exists and whether it supports those parameters. If the test fails, inspect the response in Burp's `Logger`.

Selected data is sent to the configured endpoint. An OpenAI-compatible API may be hosted locally or remotely; compatibility describes its API format, not its data-handling policy.

Next, [analyse HTTP traffic](/analysis-and-prompts/analyse-http-traffic.md) or [use AI Chat](/analysis-and-prompts/use-ai-chat.md).