Too many requests

[Mladen_Bozic]

Hi n8n Support Team,

I’m on n8n Cloud and I’m running into persistent errors with the Message model node (OpenAI). Even with throttling in place, executions often fail with:

“The service is receiving too many requests from you” (HTTP 429)
sometimes also “You exceeded your current quota.”

I’m a paid customer.

What happens

• The flow reaches Message a model and fails with 429. This occurs both when processing multiple items and sometimes even on a single item.

What I expect

• Stable execution with OpenAI using my credential, or clear guidance on required throttling/settings on n8n Cloud.

[jabbson]

Hey @Mladen_Bozic hope all is well. Welcome to the community.

If OpenAI says that you are exceeding the quota, you are probably exceeding the quota. Even paid customers have quota

https://platform.openai.com/docs/guides/rate-limits

[Michiel_Slik]

It could be you are requesting multiple requests in a short time. What you can do is go to the Node → settings tab. Then opt in retry on fail, enter a number of retries and set the wait between tries to something like 5000. Maybe this will help you.

[Muhammad_Haris1]

may be the issues is you are getting multiple request