93% of my agent's tokens were context it had already seen
This story is from 2026-10-21. It is preserved in the archive; the latest stories are on the live feed.
The median turn in my agent sends 135,267 tokens through the model and generates 424. The median visible answer is 247 tokens. The median reasoning trace is 52. Everything else was context the model had already read. That is the number I had wrong for a year. I thought an agent step costs roughly w…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-21 04:37 · DEV Community — AI
93% of my agent's tokens were context it had already seen