GPT-4o mini extremely slow today via API

API
1

Hi everyone,

I’ve been using GPT-4o mini via API calls in production for about a year without any major issues.

However, today I’m experiencing extremely slow response times. Requests that normally complete in a few seconds are now taking significantly longer, sometimes timing out.

Nothing has changed on my side:

  • Same infrastructure

  • Same request structure

  • Same model (gpt-4o-mini)

  • Similar token usage

Is anyone else experiencing similar latency issues today?

Are there any known incidents, rate limit changes, or performance degradations affecting GPT-4o mini?

I would appreciate any feedback or confirmation.

Thanks in advance.

2

Yes, today it is slow. I am also facing the same issue."

3

Hi and welcome back!

I just ran a few tests and saw response times of roughly 300 to 600 ms for gpt-4o-mini with both the Responses API and chat.completions.

Please let us know if you are still experiencing the issue. If so, sharing a few request IDs would help the team investigate more efficiently.

1 Like
4

I have tested it, and it’s working fine.

1 Like