A tool-library kiosk cannot miss the 9 a.m. Saturday rush. A hobbyist newsletter writer can wait if a reply is slow. Which pairing of capacity styles fits?
Select an answer to reveal the explanation.
Short Explanation
Think of reserving a Saturday-morning lane for the kiosk, and letting the hobbyist newsletter wait in the drop-in line. Provisioned throughput for the rush, on-demand tokens for the writer who can wait.
Full Explanation
Provisioned throughput reserves capacity for predictable, latency-sensitive volume such as a Saturday kiosk rush. On-demand token use fits a hobbyist who can tolerate a slowdown. Reversing those choices wastes money or misses the rush. Dedicated GPU servers are not required for every call.