Private cost estimates, limit visibility, savings analysis, and reporting for Claude Code and Codex across their CLI and desktop coding sessions, plus Cursor, Grok Build, Hermes, opencode, Cline, and Copilot CLI, read from the records already on your machine. No account. No telemetry. Your prompts never leave it.
live from ~/.claude and ~/.codex. Not a mockup of your data, it is your data
npx tokimeter limits groups locally observed usage into 5-hour
and 7-day views for budgets you set. When a tool records vendor counters, Tokimeter shows
those separately; it never invents a provider quota or reset time.
claude
Last 5h: ~$49.91 · 149 calls · 40.2M tokens · 83% of ~$60 budget ⚠
Last 7d: ~$49.91 · 149 calls · 40.2M tokens
codex
Last 5h: ~$11.96 · 109 calls · 22.6M tokens
Vendor-reported (plus plan), as of 11:18:
5h window: 48% used · resets in 1h 9m (13:08)
Weekly: 73% used · resets in 4d 17h (Mon, Jul 13 05:46)
Codex records OpenAI's own rate-limit counters locally; Tokimeter surfaces them with exact reset times. Claude Code doesn't log rate limits, so you get the honest rolling window instead of an invented countdown.
Daily, weekly, per-tool 5h, and per-session budgets, with warnings in the CLI and in Claude Code's own status line once you cross 80%. Never blocking.
Daily use stays claude and codex. No wrapper commands to remember.
The same local data answers the questions a running total can't. Every one of these is computed on your machine, with no extra model calls.
Finds routine work running on a premium model and shows what the same tokens would cost on a cheaper tier. It's an upper bound, stated plainly, never a nudge.
Splits a session into the main thread and the subagents it spawned, with cost broken out by agent type and the skills they used.
How much of each budget window remains, in dollars and tokens, and how long until you reach it at your current pace.
A single session end to end: cost, the models it used, how work was delegated, and whether its cache actually paid off.
The projects where you run two tools in the same window, and how the spend splits between them. Correlation, shown as correlation.
A clean Markdown or HTML report with per-project lines, ready for a client chargeback or your own records.
Exact where the data is exact, and clearly marked ~ where it's an estimate.
Read straight from the same local files your tools already write, including Claude Code and Codex desktop coding sessions. Nothing is sampled or modeled.
On a subscription you pay a flat fee. The ~$X is what that same usage would cost at API rates, so you can see the value you're pulling out. Provider/tool-reported costs keep their provenance; paid proxy accounting remains experimental until invoice reconciliation.
Input, cache write, cache read, and output are priced separately. Every price is labeled verified built-in, community feed, custom local, or provider/tool reported. Unknown models stay out of priced totals and appear only as a separate rough estimate.
Every insight and tip is computed locally from your own metadata. Tokimeter never makes a model call of its own.
A VS Code / Cursor extension shows today's spend in the status bar and a cost dashboard inside the editor, using the same local metadata with no account. It's a viewer for the local tool; the CLI stays the source of truth.
tokimeter-vscode-0.1.0.vsix.⋯ menu → Install from VSIX…
(or run code --install-extension tokimeter-vscode-0.1.0.vsix)Tokimeter: Show Cost Dashboard from the command palette.Works in VS Code, Cursor, and other VS Code forks. Release notes and the verified checksum are available on GitHub.
Tokimeter stores usage metadata only: tokens, models, costs, project paths. Never prompt or response content, because there is no field for it anywhere, by construction. Nothing is sent anywhere by default, so no telemetry and no phone-home. The optional proxy binds to localhost and never logs your API keys.
The local tool is free and complete. Pro and Team add what a local tool can't: history that outlives your logs, alerts that reach you away from the terminal, and a shared view for a whole org.
The local CLI and reports, always free.
Billed annually at $48, or $5 monthly. 7-day trial; payment method required.
Billed annually at $120/user, or $12 monthly. Early access while we onboard the first teams.
Prompts and code are never collected on any plan, by construction. Pro checkout saves a payment method and shows the first charge date before confirmation. Cancel before that date to avoid a charge; local data remains on your device.
Close and reopen Terminal after setup. tokimeter doctor is optional troubleshooting. MIT licensed; the local tool is free and complete.