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% | $4.000 | $40.00 | $60.00 | $0.00 |
| 50% | $2.100 | $21.00 | $41.00 | $19.00 |
| 75% | $1.150 | $11.50 | $31.50 | $28.50 |
| 90% | $0.580 | $5.80 | $25.80 | $34.20 |
| 95% | $0.390 | $3.90 | $23.90 | $36.10 |
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.