Is anyone else experiencing it? For the last 2 days, both of the APIs have been randomly stuck in very few (1%) cases but this number jumped from our baseline normal (earlier it used to be around <0.1%ish).
I tried shifing to other providers and everything is working correctly there, although I didn’t find any report somewhere so just wanted to validate if its happening with others as well?
Hey pradumangoyal, that's frustrating.
If you're still experiencing the issue, you could temporarily try an older model that supports your use case. Please also contact OpenAI Support with the timestamps and time zone, request IDs if available, model name, input length, and details of your retry and timeout settings.
I'll be closing this thread for now, but Support can take a closer look if the issue persists.
Avinash