Skip to content

Jan: using the VIDAI Control Plane as the backend

Jan runs LLMs locally by default. To add a remote provider, Jan's engine config accepts an OpenAI-compatible base URL and API key. Add one for the control plane and its models appear in Jan's model list alongside your local ones.

TL;DR

  1. Settings → Remote Engines → Add Provider. Choose OpenAI.
  2. Fill in:
  3. Base URL: https://your-vidai-server.example.com/v1
  4. API Key: your VIDAI API key
  5. In Model List, add a model registered on the control plane (e.g. gpt-4o-mini).
  6. Save. The model appears in Jan's model picker under the remote provider you named.

Prerequisites

  • Jan installed (macOS, Windows, or Linux desktop).
  • Control plane base URL and an API key from API Keys.
  • A model registered on the Models page.

Local vs remote

Jan lists local models (running on your machine via llama.cpp) and remote models (via engines like the one you just added) in the same picker. Selecting a VIDAI-remote model routes that conversation through the control plane; selecting a local model does not.

Attribution

One VIDAI API key per Jan install — same pattern as Chatbox.

Verify it works

Pick your VIDAI model in Jan's model picker and send:

reply with exactly: ok

A row appears on Request Logs.

If something's off

Raise an issue at github.com/vidaiUK/vidai-quickstart/issues with the engine config (masking the key). We'll get it sorted.

Where to go next