API key used from one account gives avg 2 minutes response time, when used from other account its 12s to 16s response time with same request

[_j]

It is like you discover, not the application, but your account and the gpt-3.5-turbo models.

Slow responses and 503 Service Unavailable error on Chat API services

If your account has been targeted for the slowdown, there’s not much you can do. One theory might be that if you are in Europe, you are routed to a different datacenter with different performance when using a particular account. Nobody seems to have reported whether they get the same slow speed when moving to hosted US datacenter for their API calls. You can see if you instead get fast performance when you fine tune a very basic model (10 benign questions, 1 epoch) and then use that ft model.…

Maybe they bought new datacenter services for “special” users made of gamer GPUs now capable of running a vastly reduced gpt-3.5-turbo? Nobody knows.