Make.com scenarios and the gpt-4o and gpt-4.1 shutdown

Short answer: Make moved scenarios onto gpt-4o-2024-08-06 in February 2026 and onto gpt-4.1 in March 2026 when older OpenAI models were retired. Both of those shut down on 14 January 2027. For the 28 September 2026 shutdown Make did not replace models automatically and said scenarios would stop running, so set a current model in every OpenAI module yourself.

Scan your Make scenario blueprints for retiring models (free, in your browser)

Where the model is set

The model is a setting on each OpenAI (ChatGPT, DALL-E, Whisper) module in a scenario. Make's February 2026 change moved scenarios to gpt-4o-2024-08-06, and its March 2026 change processes old GPT-4 names with gpt-4.1 even if the old name still shows in the dropdown. A scenario can therefore run on a retiring model while the module shows something else.

Fix

  1. In each scenario, use Export Blueprint (the scenario's … menu) to download its JSON.
  2. Paste the blueprint into the scanner; it lists every model ID by line.
  3. Open every OpenAI module and choose a current model explicitly, including modules that show an old GPT-4 name.
  4. Run the scenario once and compare the output.
Many workflows or services to move? The AI Model Shutdown Kit patches every n8n workflow through the API with a backup of each, scans code and config, and compares the old and new model on your own prompts (answers, tool calls, tokens, cost) before you switch. 18-page guide included.

Get the kit ($29, agencies $79)

Watch out

Sources

Other platforms

AI model shutdown calendar and scanner

Facts checked 28 October 2026. Not affiliated with OpenAI, Anthropic, Google or Make.com.

Did this fix it?

What's still not working?

Describe what happens and paste any error message. We read every report and fix the page.