← All work  /  LLM cost engineering

ClaudeCut

A drop-in local proxy that cuts Claude API and Claude Code bills by 40–70% without touching your code.

• Places prompt-cache breakpoints correctly, so repeated context is billed at the cached rate instead of full price.
• Switches models automatically by task and shows spend on a live cost dashboard.
• 500+ npm downloads in two weeks.

PythonFastAPIAnthropic APIPrompt caching

Code on GitHub ↗ npm package ↗ Write-up ↗