Cost, Latency, Caching, and Rate Limits

By the end of this module you can measure and control cost and latency, and use caching and rate limits without silently serving a stale answer.

Units

1. Unit 08.00: Measuring cost per request honestly
2. Unit 08.01: Where the latency actually goes
3. Unit 08.02: Caching without serving a stale answer
4. Unit 08.03: Rate limits and graceful degradation
5. Unit 08.04: The optimisation that changed the output

Module work

• Activity
• Knowledge check
• Summary