spend
$865.05
tokens
5.1B tokens
models
15 models
summary
where the money went
| bucket | tokens | cost | share |
|---|---|---|---|
| cache read | 4.9B | $413 | 47.8% |
| cache write | 31.5M | $184 | 21.3% |
| output | 25.5M | $204 | 23.5% |
| input | 101.6M | $64.03 | 7.4% |
69.1% of this is cache, not completions. Context being re-read each turn, rather than anything typed or generated.
cache reuse
156.1:1
4.9B tokens read back for every 31.5M 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 80th percentile.
this month
$307 so far · $39.24/day · on pace for $1,288
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 · 5.1B tokens | $865 | — | $0.171 | |||
| haiku-4-5 · used | $778 | −$86.84 10% | $0.154 | $1.00 | $5.00 | $0.100 |
| gpt-5.2 | $1,496 | +$631 73% | $0.295 | $1.75 | $14.00 | $0.175 |
| sonnet-5 | $1,556 | +$691 80% | $0.307 | $2.00 | $10.00 | $0.200 |
| gemini-3-pro | $1,607 | +$742 86% | $0.317 | $2.00 | $12.00 | $0.200 |
| opus-5 | $3,891 | +$3,026 350% | $0.768 | $5.00 | $25.00 | $0.500 |
| opus-4-8 | $3,891 | +$3,026 350% | $0.768 | $5.00 | $25.00 | $0.500 |
| fable-5-1 | $4,099 | +$3,234 374% | $0.809 | $10.00 | $50.00 | $0.250 |
USD per million tokens. Effective applies each rate card to your own mix, the only comparison that holds when cache reads are 47.8% of the bill. Published rates only: a weaker model often needs more turns, and those are not counted.