4d • General discussion
Where my Claude Code tokens actually went (new long-form)
New long-form is up: Where Do Claude Code Tokens Actually Go? I Measured 6.5 Billion
I read a full week of my own Claude Code logs (my Shorts pipeline, the nightly episode job and my own sessions, so a heavier setup than most) and sorted every token by where it went.
What I found: 95% of the 6.5 billion tokens were cache re-reads, because every step re-sends the whole conversation. Priced at API list rates (I'm on a flat plan), cache writes were the heaviest slice at 49%. The longest 10% of threads used 74% of everything. Tool output was only 0.2% as new text, but it gets re-read on every later step, roughly 68 times its size by my estimate.
The fix I'd do first: one task per session, then /clear. Full numbers, method and the ranked list: https://www.500xengineer.com/blog/where-claude-code-tokens-go
Question for you: how long does your longest Claude Code session run before you clear it, and what does /usage say your top row is?
0
0 comments
Where my Claude Code tokens actually went (new long-form)
skool.com/500xengineer
Learn the newest AI tools for building software, then turn them into income. Career tracks, 18 Claude skills and service playbooks.
Powered by