What's really fun is how inconsistent they are with "request" limits, at least with the embedding API. The documentation says "X requests per minute" but what they really mean is "X documents per minute". But their reporting shows requests per minute. So if you are embedding multiple documents per request, you will start getting 429s but the usage dashboard will look like you are nowhere near the limit. Super fun.

It's soo bad haha I think they just put the request limit to give comfort but it's not accurate at all