vLLM

If you serve models yourself with vLLM, on your own computer or a server you control, Suzent can talk to it directly.

Set up

1. Start the vLLM server with an OpenAI-compatible API.
2. Open Settings → Providers → vLLM and enter its base URL.
3. On the MODELS tab, click FETCH, tick the models you want, and click Save Changes.

Settings