Spend report · @zen-compactor-47
$196/mo burn
ranked against 38 devs · median $473/mo
59%
Runs 59% under the median — $196/mo vs $473. Quietly efficient.
82%
82% of tokens re-read context already loaded; only 2.3% was newly written code. Paying to reload, not to create.
95%
Opus drives 95% of the bill — the single biggest cost lever on this profile.
Where this landspercentile vs cohort · ◆ median
Monthly spend$19632nd pctl
Tokens that were actual code2.3%61st pctl
Spent re-reading context82%1st pctl
Opus reliance95%89th pctl
Burn per active day$729th pctl
Model mixby cost
Opus 94.8%Everything else 5.2%
Cut the burncomputed from these numbers
Route routine work to Sonnet — saves ~$45/mo
Keep Opus for architecture and hard debugging; /model sonnet for edits, tests, boilerplate.
Cohort distributionprojected / month
<$100
5
$100–300
you
$300–600
7
$600–1k
5
$1k–2k
5
$2k–5k
3
$5k+
2
$ npx tokenrot
Leaner than 68% of developers. See where you land.