Yeah it is strange performance is so bad but status is so good, haha
3 Likes
senols
13
The performance has been significantly slower since yesterday, and it appears that OpenAI may not be aware of the issue yet. Completing a request is currently taking around 5 minutes.
4 Likes
I am also experiencing this issue too. My requests timeout inconsistently
3 Likes
"Something went wrong. If this issue persists please contact us through our help center at help.openai.com. "
I’m getting this for the last 1 hr, won’t even respond to my friendly “Hi” lol
Not sure what’s going on…
4 Likes
Have been having the same issue over the last 12 hours.
3 Likes
Looks like the website is now down completely. I just get a white and empty page.
2 Likes
Same here. Really annoying. Does anybody know a workaround or faster / working model?
3 Likes
DaveC
19
Same issue. Calls to API that took a few seconds three days ago now taking 5 minutes or more
4 Likes
I noticed some issues with the chat API as well. Often times reponse time is decent, but other times it fails on timeout. Horrible for user experience of course 
3 Likes
dpiret
21
https://api.openai.com/v1/chat/completions is taking between 2s and a 5-minute timeout
4 Likes
Can confirm this is happening a lot today. Really hard to imagine building a decent UX on top of this.
4 Likes
Obligatory +1. I’ve implemented exponential backoff, but subsequent retries still hang. Often, my entire retry limit is exhausted with no response with the ChatCompletions API with gpt-3.5-turbo.
2 Likes
We have exactly the same problem in our project.
2 Likes
Now on the status page. For me, it’s been on and off since a few days.
2 Likes
Still getting very frequent errors… Timeouts, 502s…
4 Likes
Extremely slow for me still today even though their status says resolved. It’s unusable at the moment.
3 Likes
yeah ridiculously slow - had a few days of success back to usable speeds for turbo but this is not acceptable atm for a paid service.
2 Likes
amouss
29
in this page, it shows the error has been solved. But i am still getting it.
2 Likes
Still experiencing very long response times (few minutes), sometimes no response from api call at all…
2 Likes
Same here … impossible to use it today with the GPT3.5 and GPT-3.5-turbo only text-davinci-003 is ok
2 Likes
