spend
$13,513.25
tokens
30.5B tokens
models
13 models
summary
what they pay for
$100.00/mo
Self-reported. Nothing here is checked against a provider.
where the money went
| bucket | tokens | cost | share |
|---|---|---|---|
| cache read | 30.0B | $8,387 | 62.1% |
| cache write | 503.9M | $4,006 | 29.6% |
| output | 54.5M | $1,116 | 8.3% |
| input | 3.4M | $5.17 | 0.0% |
91.7% of this is cache, not completions. Context being re-read each turn, rather than anything typed or generated.
cache reuse
59.5:1
30.0B tokens read back for every 503.9M 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 40th percentile.
this month
$1,463 so far · $212/day · on pace for $6,769
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 · 13 models · 30.5B tokens | $13,513 | — | $0.442 | |||
| haiku-4-5 · used | $4,225 | −$9,289 69% | $0.138 | $1.00 | $5.00 | $0.100 |
| gpt-5.2 | $7,679 | −$5,834 43% | $0.251 | $1.75 | $14.00 | $0.175 |
| sonnet-5 · used | $8,449 | −$5,064 37% | $0.277 | $2.00 | $10.00 | $0.200 |
| gemini-3-pro | $8,558 | −$4,955 37% | $0.280 | $2.00 | $12.00 | $0.200 |
| fable-5-1 · used | $19,757 | +$6,243 46% | $0.647 | $10.00 | $50.00 | $0.250 |
| opus-5 · used | $21,124 | +$7,610 56% | $0.691 | $5.00 | $25.00 | $0.500 |
| opus-4-8 · used | $21,124 | +$7,610 56% | $0.691 | $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 62.1% of the bill. Published rates only: a weaker model often needs more turns, and those are not counted.