spend
$2,077.34
tokens
6.7B tokens
models
15 models
summary
where the money went
| bucket | tokens | cost | share |
|---|---|---|---|
| cache read | 6.6B | $1,283 | 61.7% |
| cache write | 60.7M | $413 | 19.9% |
| output | 22.6M | $358 | 17.2% |
| input | 27.3M | $23.74 | 1.1% |
81.6% of this is cache, not completions. Context being re-read each turn, rather than anything typed or generated.
cache reuse
108.2:1
6.6B tokens read back for every 60.7M 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 60th percentile.
this month
$0.000 so far · $19.69/day · on pace for $492
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 · 15 models · 6.7B tokens | $2,077 | — | $0.311 | |||
| haiku-4-5 · used | $914 | −$1,163 56% | $0.137 | $1.00 | $5.00 | $0.100 |
| gpt-5.2 | $1,718 | −$359 17% | $0.257 | $1.75 | $14.00 | $0.175 |
| sonnet-5 · used | $1,828 | −$249 12% | $0.274 | $2.00 | $10.00 | $0.200 |
| gemini-3-pro | $1,873 | −$204 10% | $0.281 | $2.00 | $12.00 | $0.200 |
| fable-5-1 | $4,217 | +$2,139 103% | $0.632 | $10.00 | $50.00 | $0.250 |
| opus-5 · used | $4,570 | +$2,493 120% | $0.685 | $5.00 | $25.00 | $0.500 |
| opus-4-8 · used | $4,570 | +$2,493 120% | $0.685 | $5.00 | $25.00 | $0.500 |
USD per million tokens. Effective applies each rate card to your own mix, the only comparison that holds when cache reads are 61.7% of the bill. Published rates only: a weaker model often needs more turns, and those are not counted.