A: Hey,

Thanks a lot for reaching out! Inferences per minute are simply the number of API calls that a specific IP is allowed to make to Hazlo's servers. It's really only to protect the system from DDoS attacks & hasn't been a problem for any of our users. In the unlikely event that you do cross the inferences for a given minute, you can simply wait for the next minute; furthermore, if you do want to do bulk API calls, there is already a provision for large-scale prediction with .csv files.

Hope I was able to help with the query, and please don't hesitate to reach out if I can be of help anywhere else :)

Best,
Ojas from Hazlo