QPS
QPS, short for queries per second, is a throughput metric for how many queries or requests a system handles each second.
1 article
Last mentioned QPS stands for queries per second, the number of queries or requests that a system such as a server, database, search engine or API processes in one second. It is a basic measure of a system's capacity and load and is closely related to RPS, or requests per second.
For services that offer AI models through an API, QPS is also used as a unit for the inference capacity and call limits assigned to users or teams.
This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.