Chatbox: using the VIDAI Control Plane as the backend

Chatbox's OpenAI Compatible provider option accepts a custom API host and key. Configure it and every conversation from the Chatbox desktop app runs through the control plane.

TL;DR

1. Settings → Model Provider → OpenAI Compatible (or Custom).
2. Fill in:
3. API Host: 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. Start a chat.

Prerequisites

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

Multiple models

Add multiple model entries in the provider settings — the model picker at the top of a conversation lists all of them.

Attribution

Chatbox is single-user. One VIDAI API key per Chatbox install is the natural pattern — each install becomes its own row on Chargeback's "Chargeback by API key" section.

Verify it works

Start a new chat 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 provider config (masking the key) and your Chatbox version. We'll get it sorted.

Where to go next

• Client integrations overview
• API Keys
• Chargeback