config.headers.setContentType is not a function

Questions
1

Describe the problem/error/question

Hello, I am using n8n:latest inside my vpn at Hostinger and my workflow stopped working, because my GPT-4.i-mini doesn’t answer anymore due to an error, I would like to know what should I do. Thanks

What is the error message (if any)?

Captura de Tela 2026-05-10 às 10.49.14
Captura de Tela 2026-05-10 às 10.49.142056×1340 174 KB

Please share your workflow

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

Captura de Tela 2026-05-10 às 13.24.57
Captura de Tela 2026-05-10 às 13.24.572498×498 145 KB

Share the output returned by the last node

Information on your n8n setup

  • n8n version:
  • Database (default: SQLite):
  • n8n EXECUTIONS_PROCESS setting (default: own, main):
  • Running n8n via (Docker, npm, n8n cloud, desktop app):
  • Operating system:
3

This is a known issue

Can you try this?

  1. Go ahead and save the credential anyway, just ignore the error message
  2. When you add an OpenAI node to your workflow, instead of using the default model dropdown, select your model By ID and type in the model name you need (e.g. gpt-4o, gpt-4o-mini, etc.)
4

Hi @Gustavo_Rincon , Welcome !

Since you’re self-hosted on Docker with :latest, i’d suggest to pin to a version before the regression. Change your Docker image from n8nio/n8n:latest to n8nio/n8n:2.18.5 (or whichever 2.18.x was your last working version) until the fix is released. That will get your workflows running again immediately.

Let me know :crossed_fingers: