Bug: OpenAI "Message a model" Node Fails - "Cannot read properties of undefined (reading 'error')"

Hello,

I am experiencing a persistent bug with the OpenAI “Message a model” node on n8n Cloud version 1.102.3. Regardless of the configuration, the node fails immediately with the error: TypeError: Cannot read properties of undefined (reading 'error').

Troubleshooting Steps Already Performed:

  1. Confirmed Operation: Message a Model is set correctly.
  2. Deleted the node and created a fresh one.
  3. The error occurs even with a simple, static prompt (e.g., the word “Test”).
  4. Configured the prompt using the recommended separate System and User message roles.
  5. The error is identical in all scenarios.

This appears to be a platform bug, as the node fails before any API call is made. Please advise.

Thank you.

1 Like

I’m experiance the same thing…

Add me to the list. Experiencing the same issue, even with a basic chat input of “test”

EDIT: Rolling back to 1.101.2 with no other changes fixes it for me.

Same Problem

how i can go back to 1.101.2?

Experiencing the same exact issue

Thank you all for reporting. This has been fixed with this PR and will be released soon.

1 Like

New version [email protected] got released which includes the GitHub PR 17412.

1 Like

Had the same issue, updated to 1.104.0 but now it keeps giving “The service is receiving too many requests from you” it is infact not receving too many requests and I am using open ai Plus account so what is the problem?

Hey Rida,

It’s a bit confusing, but ChatGPT Plus and the OpenAI API are completely separate.

  • ChatGPT Plus ($20/month) only applies when you use ChatGPT in the browser or mobile app.
  • The OpenAI API (which n8n’s Message a Model uses) is billed separately on a pay‑as‑you‑go basis. ChatGPT Plus does not give you API credits.

If your OpenAI API account shows $0 remaining and you haven’t added a payment method, you’re still on the free trial (or it has expired). When that happens, you’ll get the insufficient_quota / “too many requests” error even if you’re barely using it.

How to fix:

  1. Go to https://platform.openai.com/account/billing/overview
  2. Add a payment method.
  3. Switch to pay‑as‑you‑go billing and set a monthly budget.

Once that’s done, n8n will be able to send requests again.

1 Like