Prompt caching bills repeated input tokens at the cache-read rate instead of the standard input rate. The table below shows the effective input price and monthly cost at different cache hit rates for a 10M-input / 1M-output token month.
10,000,000 input tokens and 1,000,000 output tokens per month. Output pricing is unchanged.
| Cache hit rate | Effective input / 1M | Monthly input cost | Monthly total | Saving vs no cache |
|---|---|---|---|---|
| 0% | $0.150 | $1.50 | $2.10 | $0.00 |
| 50% | $0.076 | $0.77 | $1.36 | $0.74 |
| 75% | $0.040 | $0.40 | $1.00 | $1.10 |
| 90% | $0.018 | $0.18 | $0.78 | $1.32 |
| 95% | $0.010 | $0.10 | $0.70 | $1.40 |
Providers only bill the cache-read rate when repeated content qualifies for caching and the cache is still warm. This page is an arithmetic estimate from stored catalog rates, not a guarantee of provider billing behaviour. Confirm cache rules and minimum token thresholds in the provider documentation.