Just want to know about it
The first 500 calls are fast requests, where your responses will appear faster than people who are using slow requests
After your quota of 500 calls is exhausted, you’ll have unlimited number of slow requests which usually have a certain waiting time for each response depending upon the traffic on the model you’re using (Claude sonnet gets most traffic so it’s sometimes very slow with slow reqs)
Also if you wanna keep using fast reqs after your quota has exhausted, you can get more by enabling usage based pricing where you’ll be charged according to the number of requests you make
Hope this helped clear your doubts
2 Likes