3.5 Billion Tokens in Claude Code in January
Pushing the boundaries of what's possible with AI coding agents - almost 3.5 billion tokens in one month and no desire to go back
Almost 3.5 billion tokens in Claude Code in January. I pushed it this month to explore what's possible now - and to be honest it's a bit addictive.
My $200 max plan got me $2664 in tokens at list price. Never got to more than 80% of my rate limit. This part is probably not sustainable, but I believe the tokens will get cheaper and / or the open weight models will get good enough for it not to be a concern when the subsidy goes away.
I still need to finish a more value oriented analysis of everything I landed this month (and some stuff I didn't) using a tool I rebuilt with some of these tokens, but I definitely don't want to go back.
Related insights
Almost $10K in Tokens in April
15 billion tokens, 302 Linear issues shipped to production, just me in Claude Code. Real 'headcount equivalent' territory—and a reminder to measure impact, not just output.
4+ Billion Tokens in February
252 PRs merged, $2700 at list price for my $200 max plan - continuing to find the edge of what's possible within sane guardrails
You Don't Need Opus for Everything
Right model, right task. In Claude Code you can pin a model per skill—I drop to Sonnet or Haiku when the full power of Opus isn't needed to stay inside my limits.
Get More Like This
Follow along as I build and share what I learn
Found this helpful? Share it with your network!