I’m seeing long queue times in using Assistant API with gpt-4-1106-preview. Is anyone seeing the same? I know this has previously been an issue.
Yes, it is very slow for a couple of days now.
It got even worse. It’s taking like a solid 20 (TWENTY SECONDS) in the queue. Can’t manage that with my application as there’s an expectation by the user to have a short reply. I’m thinking to drop assistant until they manage to drop this waiting time.
I concur. Performance of the Assistant API is absolutely horrible and it has been ongoing for several weeks now.
Feeling like OpenAI has completely dropped the ball on this API as these latency issues are never acknowledged and clearly not addressed.
FYI, I am Tier-4 and have already spent several hundreds dollars for this subpar service.
I’m facing the assistants api run states issue with gpt-4-1106-preview model. The run locks in “queued” forever and the same happens with every other thread I create. I even tried to create another assistant but it doesn’t seem to have any effect. Do you know whats going on?