Gpt-3.5-turbo extremely frequent timeouts

API
22

Can confirm this is happening a lot today. Really hard to imagine building a decent UX on top of this.

4 Likes
23

Obligatory +1. Iā€™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
24

We have exactly the same problem in our project.

2 Likes
25

Screenshot 2023-03-22 at 20.20.44
Screenshot 2023-03-22 at 20.20.44948Ɨ405 28.1 KB

Now on the status page. For me, itā€™s been on and off since a few days.

2 Likes
26

Still getting very frequent errorsā€¦ Timeouts, 502sā€¦

4 Likes
27

Extremely slow for me still today even though their status says resolved. Itā€™s unusable at the moment.

3 Likes
28

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
29

in this page, it shows the error has been solved. But i am still getting it.

2 Likes
30

Still experiencing very long response times (few minutes), sometimes no response from api call at allā€¦

2 Likes
31

Same here ā€¦ impossible to use it today with the GPT3.5 and GPT-3.5-turbo only text-davinci-003 is ok

2 Likes
32

Same issue. Both 3.5 and turbo are timing out on almost every api call.

2 Likes
33

+1 stuck API calls ~10% of the time on gpt-3.5-turbo and text-davinci-003 today

2 Likes
34

I am blocked from ChatGPT because I purchased ChatGPT Plus, which blocks you from ChatGPT

1 Like
35

+1. Unusable. 95% timeout rate

1 Like