97% of what my coding agent billed for was re-reading its own context
This story is from 2026-09-16. It is preserved in the archive; the latest stories are on the live feed.
Token counters tell you how much you spent. I wanted a different number: how much of what I paid for was new text the model actually produced. So I measured it against a complete local log corpus of my own agentic coding work: 722 sessions, 150,902 model calls, 34.56 billion tokens. By tokens bille…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-09-16 07:11 · DEV Community — AI
97% of what my coding agent billed for was re-reading its own context