I am using the GPT-3.5-turbo model in my app. The API was working much better a few days ago but now it is taking me over 10 tries to get a return for a 380 token request (or around 40 words). I always get the connection timeout error. I am also paying for the API at the moment. Could someone please help with this?
Did you look at the status page in the last few hours?
yes, it is still pretty bad at the moment, it fails constantly and only works about half of the time.