Cost Breakdown

It pulls from the Agent Monitor's pricing engine to show per-model costs broken down by input, output, cache reads, and cache writes at the $/Mtok level. You get the top 10 most expensive sessions, daily spend trends, and cache hit rates that reveal whether you're reusing context or burning tokens. The best part is the optimization section, which flags sessions where you wrote cache tokens but never read them, or where you used Opus for something Haiku could handle. It's basically a finance report for your API spend, and it surfaces the stuff you'd never notice just watching the dashboard.