> 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/getting-started/supported-model-providers.md).

# Supported model providers

Version 3.0 supports the following model providers.

Choose a cloud-based provider when you want hosted model performance and already have an API account. Choose a local or self-hosted provider when you need traffic to stay on infrastructure you control, or when you want to use internal models.

## Cloud-based providers

{% hint style="warning" %}
Using these services involves transmitting data to their servers. Please review each provider’s privacy policy to understand how your data is handled.
{% endhint %}

* Anthropic — <https://docs.anthropic.com/en/home>
* Google AI Gemini — <https://ai.google.dev/gemini-api/docs>
* Mistral AI — <https://docs.mistral.ai/>
* OpenAI — <https://platform.openai.com/docs/>

## Local and self-hosted providers

{% hint style="info" %}
For self-hosted or custom providers, the extension can use the standard OpenAI-compatible chat API schema.
{% endhint %}

* Ollama — <https://github.com/ollama/ollama/tree/main/docs>
* OpenAI-compatible API — use this for compatible local or self-hosted endpoints that expose a `/v1` chat API.

After choosing a provider, configure it in `Provider settings` and run `Test request` before scanning or using `AI Chat`.