ccusage vs Claude Code Usage Monitor in 2026

Q: Is Codex Forecast free to use?

Codex Forecast is free, with no account and no paid tier . It is a website with a public API that needs no key . Its free email alerts are sent when a reset actually happens if you opt in . The facts here give no other price for Codex Forecast.

ccusage and Claude Code Usage Monitor compared on what each does, what each costs and what to check before you pick one.

By SupaKeeper · 2026-10-27

SupaKeeper is published by LunarWerx, which makes some of the tools compared here.

ccusage and Claude Code Usage Monitor compared on what each does, what each costs and what to check before you pick one for tracking coding agent usage.

Option	What its sources say it does	Cost	Account or install
ccusage	Its page says it analyzes coding agent CLI token usage and costs from local data ^[1], reads local usage data from coding agent CLIs into daily, weekly, monthly and session reports ^[1], tracks and displays cache creation and cache read tokens separately ^[1], and is MIT licensed ^[1]	not published	run directly without a global installation ^[1]
Claude Code Usage Monitor	Its page calls it a privacy-first companion for Claude Code ^[2], its default Custom plan monitors token consumption, message counts and cost ^[2], and it offers reset-aware forecasting and pace calculations ^[2]	not published	can be installed from PyPI using uv or pip, with Python 3.9 or later required ^[2] ^[2] ^[2]
Codex Forecast	Its own description says it gives a statistical estimate of when OpenAI resets Codex usage limits ^[3], combines several sources ^[3], and can email you when a reset happens if you opt in ^[3]	free, no paid tier ^[3]	no account ^[3]; a website with a public API ^[3]

The short answer

Both tools report on coding agent usage, but they start from different places. ccusage runs directly without a global installation, so it can be used on demand with a package runner ^[1], it is licensed under MIT ^[1], and it lets you override token pricing per raw model name without rebuilding ^[1]. Claude Code Usage Monitor is a privacy-first companion for Claude Code ^[2] whose default Custom plan monitors token consumption, message counts and cost ^[2]. It falls back to labeled local estimates when official statusline captures are stale or expired ^[2]. If you work on the command line and want usage reports from local CLI data, ccusage's own pages point that way. If you want a privacy-first watch over a Claude Code account with the Custom plan, Claude Code Usage Monitor's pages point that way.

What ccusage, Claude Code Usage Monitor is built for

ccusage is licensed under MIT, so the source code can be used under that license ^[1]. It runs directly without a global installation, which means it can be started on demand rather than set up as a permanent tool ^[1]. It lets you override token pricing per raw model name in its configuration file without rebuilding ^[1], so you can set your own cost figures. Claude Code Usage Monitor describes itself as a privacy-first companion for Claude Code ^[2]. Its default Custom plan monitors three metrics: token consumption, message counts and cost ^[2]. Its page says stale or expired official statusline captures fall back to labeled local estimates ^[2], so it has a fallback when that official capture is not current. For anything else either tool does, check its own page, since the facts here name only these details outside the table.

What Codex Forecast is built for

Codex Forecast is made by the team that publishes this site. It gives a statistical estimate of when OpenAI will next reset Codex usage limits ^[3]. By its own description, the estimate combines an account it checks every 60 seconds, OpenAI staff announcements and the OpenAI status page ^[3], and when a measured refill and an announcement disagree, it trusts the measured refill ^[3]. It lists each reset used in the forecast with a link to where it was announced ^[3], and its named-day predictions are scored in public, misses included ^[3]. You can opt in to free emails that are sent when a reset actually happens ^[3]. It is a website with a public API ^[3] that needs no key and gives stats, paginated reset history, forecasts and operational health ^[3], with a published OpenAPI specification ^[3]. The site and API share a snapshot cached for up to five minutes ^[3], and it is an independent tracker not affiliated with OpenAI ^[3].

Pricing and fees

Codex Forecast is free, with no account and no paid tier ^[3]. The facts given here do not state a dollar price for ccusage ^[1] or for Claude Code Usage Monitor ^[2], so a price is not published for either. Neither source describes a fee, a trial or a discount, so none is stated here. Claude Code Usage Monitor's default configuration is its Custom plan ^[2], but the facts give no price for that plan. The only price in the facts for any tool on this page is free for Codex Forecast ^[3]. If you need the cost of ccusage or Claude Code Usage Monitor for your own use, check their own pages, since the facts here do not state one.

Setting it up and daily use

ccusage runs directly without a global installation, using npm or another package runner, so it can be started on demand rather than installed as a system tool ^[1]. It is MIT licensed ^[1]. Claude Code Usage Monitor can be installed from PyPI using a package tool, with Python 3.9 or later required ^[2] ^[2], and its page names pip and uv as two ways to install it ^[2] ^[2]. Its default Custom plan monitors token consumption, message counts and cost ^[2]. Codex Forecast is a website with a public API, so you open it in a browser or call its API for data ^[3], and there is no account and no paid tier to set up ^[3]. Its free reset emails are available if you opt in ^[3]. The facts here say nothing more about routine use for any tool, so check their own pages for anything further.

Things to check before you choose

Ask which coding agents you use. ccusage's pages name many sources at once ^[1], while Claude Code Usage Monitor's given facts describe a companion to Claude Code ^[2], so match that to the tools you run. Ask where your usage data lives: ccusage reads from local CLI data ^[1], and Claude Code Usage Monitor mentions official statusline captures and local estimates ^[2]. Ask what the cost figures must reflect: ccusage lets you override token pricing per raw model name ^[1]. Ask whether a price exists for either tool, since the facts here give none, and check their own pages for it.

How to choose

The two rivals answer different questions about coding agent usage. ccusage turns local CLI usage data into daily, weekly, monthly and session reports ^[1], so it fits when you want reports from local data and can run it on demand without a global install ^[1]. Claude Code Usage Monitor is a privacy-first companion for Claude Code ^[2] tracking token consumption, message counts and cost ^[2], so it fits when that watch over Claude Code is what you need. Codex Forecast answers a different question: when OpenAI will next reset Codex usage limits ^[3], with free reset emails if you opt in ^[3] and no account needed ^[3]. Choose the tool whose sources name the question you actually have.

Frequently asked questions

Is Codex Forecast free to use?

Codex Forecast is free, with no account and no paid tier ^[3]. It is a website with a public API that needs no key ^[3]. Its free email alerts are sent when a reset actually happens if you opt in ^[3]. The facts here give no other price for Codex Forecast.

Does ccusage cost anything?

The facts given here do not state a dollar price for ccusage ^[1]. Its page says it analyzes coding agent CLI token usage and costs from local data ^[1] and is MIT licensed ^[1], but it does not name a fee. Check its own page if you need the cost.

Does Claude Code Usage Monitor cost anything?

The facts given here do not state a dollar price for Claude Code Usage Monitor ^[2]. Its default configuration is its Custom plan ^[2], which monitors token consumption, message counts and cost ^[2], but the facts give no price for that plan. Check its own page if you need the cost.

Can Codex Forecast tell when Codex usage limits reset?

Yes. Codex Forecast gives a statistical estimate of when OpenAI will next reset Codex usage limits ^[3]. By its own description, the estimate combines an account it checks every 60 seconds, OpenAI staff announcements and the OpenAI status page ^[3], and it trusts a measured refill when it disagrees with an announcement ^[3]. It can also email you when a reset actually happens if you opt in ^[3].

What coding agents can ccusage read usage data from?

Its sources include Codex, with the command ccusage codex daily. ^[1] It says it reads local usage data from coding agent CLIs and turns it into daily, weekly, monthly and session reports ^[1]. Check its page for the full list before you rely on it.

It is free, with no account and no paid tier. ^[3]

Try Codex Forecast