Vision Google API. How to distribute the load?

Suppose you want to determine the photos that users upload through the client. The algorithm is this: the client sends to the API application request with loading images -> server consults the Google API Vision -> receives the response and writes it to the database. The response from the API Vision takes 2-3 seconds. Every second required to serve 5 000 000 such users. Is it enough to connect more instance servers to handle the load, or is it an impossible task? Maybe there are ideas that I just don't know? Thank you.

PS: the Application is written in PHP
April 7th 20 at 11:00
1 answer
April 7th 20 at 11:02
what is the question?

up - min (limits API, channel-server-PERC)
to you - max(channel-server-PERC)

the server put the growth of enterprises these indicators
when online servers, the answer is "enough"

Find more questions by tags Google Cloud Platform