Can confirm this is happening a lot today. Really hard to imagine building a decent UX on top of this.
Obligatory +1. Iāve 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.
We have exactly the same problem in our project.
Still getting very frequent errorsā¦ Timeouts, 502sā¦
Extremely slow for me still today even though their status says resolved. Itās unusable at the moment.
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.
in this page, it shows the error has been solved. But i am still getting it.
Still experiencing very long response times (few minutes), sometimes no response from api call at allā¦
Same here ā¦ impossible to use it today with the GPT3.5 and GPT-3.5-turbo only text-davinci-003 is ok
Same issue. Both 3.5 and turbo are timing out on almost every api call.
+1 stuck API calls ~10% of the time on gpt-3.5-turbo and text-davinci-003 today
I am blocked from ChatGPT because I purchased ChatGPT Plus, which blocks you from ChatGPT
+1. Unusable. 95% timeout rate