Steven Gonsalvez

Software Engineer


CEREBRO


machine-read, human-curated

$62.09

Tokens
34,230,528
Model calls
557
Briefings
127
Signals kept
2,843
Per briefing
$0.4889
Per kept signal
$0.0218

Every CEREBRO run meters itself. The number above is the sum of the cost_usd field in the frontmatter of all 127 published briefings, in integer hundredths of a cent, summed once and divided once, so it is exact rather than approximately right.

What it is: the Claude API spend of the triage and digest passes, plus the Hacker News comment enrichment. Across the corpus that is 557 model calls and 34,230,528 tokens, of which 11,601,737 were cache reads (the cheap kind), and that is why the figure is what it is rather than several times larger.

What it is not: it excludes the machine it runs on, the bandwidth, the scrapers, the site’s own hosting, and every hour spent building the thing. It is the model bill, not the cost of the project. Anyone quoting it as “what an AI news digest costs” is quoting the smallest line of the invoice.

It works out at $0.4889 a briefing and $0.0218 per signal that actually made it through, on 269,532 tokens a day. The colophon explains which stages spend that and why the pre-rank exists.

Daily spend

Daily model spend across 127 briefings, from $0.0000 to $1.6210

By month

June 202610221412,267,016$5.48
July 2026316751298,291,976$19.63
August 2026316951276,674,044$17.00
September 202614342635,012,166$8.05
October 2026245441166,847,282$7.73
November 202617366815,138,044$4.20
total1272,84355734,230,528$62.09