Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 23 additions & 0 deletions openhands/usage/llms/openai-llms.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,29 @@ If the model is not in the list, enable `Advanced` options, and enter it in `Cus

Just as for OpenAI Chat completions, we use LiteLLM for OpenAI-compatible endpoints. You can find their full documentation on this topic [here](https://docs.litellm.ai/docs/providers/openai_compatible).

### Using PZERO

[PZERO](https://pzero.studio/agents) provides an OpenAI-compatible endpoint. Create a PZERO API key, then go to `Settings` > `LLM` in the OpenHands UI, enable `Advanced` options, and set:

- `Custom Model` to `openai/deepseek-v4-flash`
- `Base URL` to `https://api.pzero.studio/v1`
- `API Key` to your PZERO API key beginning with `pzero_`

You can also configure PZERO in `config.toml`:

```toml
[llm]
model = "openai/deepseek-v4-flash"
api_key = "pzero_YOUR_KEY"
base_url = "https://api.pzero.studio/v1"
```

Replace `pzero_YOUR_KEY` with your PZERO API key. To use a different model, query the public `GET https://api.pzero.studio/v1/models` endpoint and prefix the returned model ID with `openai/`.

<Note>
Use `https://api.pzero.studio/v1` as the `Base URL`. Do not use the full `https://api.pzero.studio/v1/chat/completions` endpoint as the base URL.
</Note>

## Using an OpenAI Proxy

If you're using an OpenAI proxy, in the OpenHands UI through the Settings under the `LLM` tab:
Expand Down