One PR Billed 156M Tokens. Cap the Reads, Not the Rate.
A published trace of one 800-line pull request shows a coding agent billed roughly 156 million tokens to produce 289,000 — 98% of the volume was cache re-reads of context re-sent on every one of 512 turns. Coding-agent cost is set by turns per task and the width of each read, not by the model's rate card.
September 3, 2026 · 12 min read