Hi, I am getting this every single day on OpenAI API - da vinci 003 model:
I am building business around it and willing to pay a lot, but this is simply not good.
That model is currently overloaded with other requests. You can retry your request, or contact us through our help center at help.openai.com if the error persists. (Please include the request ID XXXXXX in your message.)
Can you scale your servers or something guys? It would be nice in the century of cloud.
Thanks a lot.
especially around 7-9 PM GMT+1, its happening
I am getting it every day, on 3.5 AND on 4, any time of the day. Even with scripts that are voluntarily spacing queries to the API to less than one every 10 seconds.
I would like to be sure that this error is solely due to global overloading or if it can come from some miss handling of the queries on my part…
It’s global, everyone are seeing it.
It should really be user based rather than global.
I guess they do have user based limits but they haven’t configured things properly yet.
And I’m using ChstGPT plus is doing 90% of the usage.
They do say that you should not use GPT4 for production, but if it happens for other models then I guess that’s not look great.
I am considering other LLMs for some of my simpler use cases, though for GPT4 OpenAI is too good to replace 