Reuse opportunity
The maximum share of input tokens that could be served from cache, independent of whether they actually were.
Opportunity is the ceiling. It is candidate reusable tokens divided by total input tokens, derived from how often equivalent prefix families recur.
It is deliberately separate from realized reuse. A repeated prefix is not proof of a cache hit, so Zumik reports the two side by side and calls the difference the missed-opportunity gap.
Keep reading.
Cache capture rate
Realized reused tokens divided by candidate reusable tokens - how much of the available reuse a provider actually delivered.
Workload Reuse Score (WRS)
A 0-100 score of how much a workload can benefit from reuse, built from opportunity, recurrence, locality, latency sensitivity, continuity, and payload redundancy.
Prompt caching
Reusing the computed state of a repeated prompt prefix so it is billed at a reduced cache-read rate instead of being recomputed.
See it in practice.
Definitions are useful; measurement is better. Run a diagnostic on your own workload.