Whisper API 429 Rate Limit Error on One Server Despite Active Quota

API Bugs
1

Hi everyone,
I am encountering an issue with the Whisper API where I consistently receive an HTTP 429 error on one server, despite having an active quota and the same API key works fine on another server. The error message states that I have exceeded the rate limit, even though my company’s OpenAI account is charged, and we haven’t reached the quota limit as per the dashboard.

Here are the steps I’ve tried:

  • Implemented exponential backoff with retries.
  • Confirmed the same API key works without issues on a different server.
  • Checked my usage on the OpenAI dashboard, and the quota is not exceeded.

Has anyone else experienced a similar issue, where one server repeatedly hits the rate limit but the same key works on another? Any advice or suggestions would be greatly appreciated.

Thanks in advance!

2

I’m experimenting the same issue, with Postman I don’t get the error, with my NodeJs backend I get that. I see none has answered since Sept. Any news?