Out of RPD, Clock Start - GPT Vision?

[_j]

API rate limit hit but it was not actually hit

You cannot compare the billing information, which has a cutoff of 00:00 UTC to separate usage into different days, to that of the rate limiter, which has a rolling adaptive formula for usage that is not separated into distinct days. The accounting can also have delays in adding calls to billings. Also, all models in a model class count against the rate limit, while the usage page is only displaying one model in the screenshot. The daily limit for the preview model is quite low, even though the…

You will find that if you make a request and receive back its header, it will say something like 4999 request left. Make another request in a few minutes, same number. The requests are always “refilling” if you will, working back to a memoryless state.