Prompt caching saved 91% on 7,407 coding-agent calls, and real logs found two bugs in my cost tool
I built a small open-source CLI, llm-cost-audit , that reads LLM call logs and ranks where money could be saved. Synthetic test data said it worked. So I pointed it at 22 days of my own Claude Code sessions to see what real data would say. Short version: at list API prices, the 7,407 calls come to…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-12 15:09 · DEV Community — AI
Prompt caching saved 91% on 7,407 coding-agent calls, and real logs found two bugs in my cost tool