spend
$13,481.57
tokens
8.2B tokens
models
8 models
what they pay for
$220.00/mo
Self-reported. Nothing here is checked against a provider.
summary
where the money went
| bucket | tokens | cost | share |
|---|---|---|---|
| cache read | 7.4B | $1,498 | 11.1% |
| cache write | 237.7M | $1,296 | 9.6% |
| output | 524.4M | $10,466 | 77.6% |
| input | 81.1M | $222 | 1.6% |
cache reuse
31.1:1
7.4B tokens read back for every 237.7M written. Writing to cache costs 1.25–2× the input rate; reading costs a tenth. Higher is better.
Median is 59.5:1 across 5 people. You are in the 0th percentile. At the median you would have spent about $620 less.
Reuse drops when context is rebuilt: starting fresh sessions, clearing history, or editing an early turn, which invalidates everything cached after it.
this month
$462 so far
Projection uses the last fortnight, including days with no usage, over 25 remaining days.
the same tokens, priced elsewhere
| model | total | vs yours | effective | in | out | cache read |
|---|---|---|---|---|---|---|
| your mix · 8 models · 8.2B tokens | $13,482 | — | $1.64 | |||
| haiku-4-5 | $3,765 | −$9,716 72% | $0.458 | $1.00 | $5.00 | $0.100 |
| sonnet-5 | $7,530 | −$5,951 44% | $0.916 | $2.00 | $10.00 | $0.200 |
| gemini-3-pro | $8,579 | −$4,902 36% | $1.04 | $2.00 | $12.00 | $0.200 |
| gpt-5.2 | $9,342 | −$4,139 31% | $1.14 | $1.75 | $14.00 | $0.175 |
| opus-5 | $18,826 | +$5,344 40% | $2.29 | $5.00 | $25.00 | $0.500 |
| opus-4-8 | $18,826 | +$5,344 40% | $2.29 | $5.00 | $25.00 | $0.500 |
| fable-5-1 | $32,117 | +$18,635 138% | $3.91 | $10.00 | $50.00 | $0.250 |
USD per million tokens. Effective applies each rate card to your own mix. Published rates only: a weaker model often needs more turns, and those are not counted.