BTW, re. GPU costs we bill for uptime, not for volume of requests. So the price would be the same whatever the number of users (but latency might go up of course)
Let us know if this helps!
BTW, re. GPU costs we bill for uptime, not for volume of requests. So the price would be the same whatever the number of users (but latency might go up of course)
Let us know if this helps!