Know exactly what your AI coding costs.
whereai reads your local Claude Code session files and gives you instant visibility into token usage, costs per session, cache efficiency, and AI-powered workflow recommendations — all without sending your data anywhere.
How it works
Everything you need to understand
your Claude Code spend
Cost & Token Analytics
See every token, every cent
Track costs and token usage per session, per model, and per prompt. Understand exactly where your Claude Code spend is going, broken down across all your projects.
Cache Efficiency
Measure your cache savings
See your cache hit rates in real time and understand how much you're saving by reusing context across sessions. Built-in insights surface when caching is working well and when it isn't.
AI-Powered Insights
Get personalised workflow recommendations
whereai analyses your usage patterns and surfaces concrete suggestions for reducing costs — from optimal session length to prompt structure improvements.
