> ## Documentation Index
> Fetch the complete documentation index at: https://arka-agent-mintlify-f21cea86.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# vLLM fallback

> Use a local vLLM OpenAI-compatible server as an Arka fallback provider.

Start vLLM, then enable it in Arka’s fallback chain:

```bash theme={null}
export VLLM_HOST=127.0.0.1:8000
export VLLM_MODEL=your-loaded-model
export VLLM_FALLBACK=1
arka doctor
```

Arka tries vLLM when it is reachable or explicitly configured, then continues
through the normal provider chain if the local server fails. Set
`VLLM_FALLBACK=0` to disable the opt-in fallback behavior.


## Related topics

- [Testing Arka with the pytest suite](/guides/testing.md)
- [Arka — AI terminal agent documentation](/index.md)
- [Operation modes](/guides/operation-modes.md)
- [Find free models](/guides/free-models.md)
- [OCR + vLLM evidence](/guides/vision-evidence.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.