Make (Integromat): using the VIDAI Control Plane as the backend¶

Make's built-in OpenAI module points at api.openai.com. Reach the control plane from a scenario via the HTTP → Make a request module — call /v1/chat/completions directly.

TL;DR — HTTP module¶

Add an HTTP → Make a request module:

URL: https://your-vidai-server.example.com/v1/chat/completions
Method: POST
Headers:
Authorization: Bearer your-vidai-key
Content-Type: application/json
Body type: Raw → JSON (application/json)

Request content:

{
  "model": "gpt-4o-mini",
  "messages": [{"role": "user", "content": "{{1.prompt}}"}]
}

Parse response: Yes (auto-parses JSON into mappable fields)

Map data.choices[].message.content into downstream modules.

Prerequisites¶

A Make account.
Control plane base URL and an API key from API Keys.
A model registered on the Models page.

Storing the API key¶

Use Make's Data Store to hold the key so it's not pasted into every scenario. Read it into a variable at scenario start.

Attribution¶

One VIDAI API key per Make scenario (or per team). Each key becomes a row on Chargeback.

Verify it works¶

A two-module scenario: Manual trigger → HTTP as above with the prompt reply with exactly: ok. Run once. Confirm the parsed response contains "content": "ok". A row appears on Request Logs.

If something's off¶

Raise an issue at github.com/vidaiUK/vidai-quickstart/issues with the HTTP module config and the failing execution log (mask the key). We'll get it sorted.