Skip to content

Windsurf: using the VIDAI Control Plane as the backend

Windsurf's Advanced Settings expose a Custom Model configuration that speaks the OpenAI wire shape. Point it at the control plane and Cascade's chat and edits flow through us.

TL;DR

  1. Windsurf → Settings → Advanced Settings → Custom Model.
  2. Enable Custom Model and set:
  3. Base URL: https://your-vidai-server.example.com/v1
  4. API Key: your VIDAI API key
  5. Model Name: a model registered on the control plane (e.g. gpt-4o-mini)
  6. Save. In the chat model picker, select your custom model.

Prerequisites

  • Windsurf installed.
  • Control plane base URL and an API key from API Keys.
  • A model registered on the Models page.

What runs through the control plane

Once the custom model is selected in a chat / Cascade session, every message and every tool step routes through the control plane. Windsurf's first-party Cascade Base and premium models stay on Codeium's infrastructure.

Attribution

One VIDAI API key per Windsurf user (or per team) — the Chargeback tab's "Chargeback by API key" section then breaks spend down per seat.

Verify it works

Open a chat with your custom model selected 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 your custom-model config (masking the key) and the Windsurf version. We'll get it sorted.

Where to go next