what-would-it-cost is a Claude Code cost tracker: what your Pro or Max subscription would cost at API prices, live above your prompt. One line, always on, updated after every model request, showing this session at API prices, the session's model mix, the total for every session on the machine today, your current weekly limit window from Claude Code's own reset time, your billing cycle so far, how many times over the cycle has paid for your plan, and a 14-day sparkline. Click invoice on the bar for the full bill broken down by model and token type, with a 60-day chart. It reads your history on install so the numbers start with your past month instead of zero.
Be the first to rate What Would It Cost. Your feedback helps other users decide.
Read the live line above your prompt: session cost, model mix, today, 7 days, cycle and multiple.
Click invoice for the full bill by session, 7-day window, billing cycle or all time, with a 60-day chart.
Add the plugin at user scope so it runs in every session and prices your existing transcripts on first run.
Similar tools in the same category β compare side-by-side
Thyme is a native reverse-engineering IDE for Android and native binaries on macOS, Linux and Window...
Submilli is a code-execution runtime with a semantic permission model for business agents that gener...
Orbit is a local-first runtime for coding agents: you keep using your authenticated agent CLI and Or...
Guides and comparisons about code tools
Ten launches that put a number on agent work: per-repo bills, live cost bars, expiring quota, cheap worker models and local decision engines.
Nine new tools for evidence rather than dashboards: signed records, decision logs, MCP analytics, protocol tests, sandboxes and long-running agent supervision.
Nine new tools aimed at the same wall from different angles: indexed wikis, stale memory, knowledge graphs, reversible compression and multi-agent rooms.
Nine launches that keep work on your own hardware: a model storage server, offline file search, native dictation, ARM64 VMs and a single-binary coding agent.
Nine Show HN launches beneath the model: filesystems, snapshots, gateways and deploy tools that decide what an agent sees and what survives.