ccusage vs OpenAI Status in 2026

Q: Is ccusage free to use?

ccusage is licensed under MIT . The sources here state no price for it, so a price is not published here. It can run directly without a global installation using npx . Check its own pages if you need more detail on cost.

Q: Is Codex Forecast free and does it have an API?

It is free, with no account and no paid tier . A public API that needs no key gives stats, paginated reset history, forecasts and operational health . The API has a published OpenAPI specification . It is not affiliated with OpenAI .

ccusage, OpenAI Status and Codex Forecast compared on what each reports, what each costs, how each is used and what to check before you choose.

By SupaKeeper · 2026-10-10

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

ccusage tracks and displays cache creation and cache read tokens separately ^[1]. OpenAI Status's page says OpenAI is not aware of any issues affecting its systems ^[2]. Codex Forecast estimates when OpenAI will next reset Codex usage limits ^[3].

Option	Own fee	Card fee	What it reports
ccusage	Not published	Not published	Token usage and costs from local data ^[1]
OpenAI Status	Not published	Not published	System status and uptime, Codex 99.95% ^[2]
Codex Forecast	Free, no paid tier ^[3]	Not published	Estimate of the next Codex limit reset ^[3]

The short answer

ccusage can be run directly without a global installation using npx ^[1]. OpenAI Status's page says OpenAI is not aware of any issues affecting its systems ^[2]. Codex Forecast gives a statistical estimate of when OpenAI will next reset Codex usage limits ^[3].

If you want to change the token prices ccusage uses for a given model, its page covers overriding token pricing per raw model name in ccusage.json ^[1]. OpenAI Status's page lists Codex at 99.95% uptime across 4 components ^[2]. Codex Forecast's sources cover a reset estimate built from several sources ^[3].

What ccusage, OpenAI Status is built for

ccusage can be run directly without a global installation via npm or other package runners ^[1]. It tracks cache creation and cache read tokens separately ^[1]. It allows overriding token pricing per raw model name in ccusage.json without rebuilding ^[1].

OpenAI Status's page says OpenAI is not aware of any issues affecting its systems ^[2]. It lists Codex at 99.95% uptime across 4 components ^[2], and APIs at 99.96% uptime across 13 components ^[2]. Uptime is reported at an aggregate level across all tiers, models and error types ^[2].

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]. It combines an account it checks every 60 seconds, OpenAI staff announcements and the OpenAI status page ^[3]. When a measured refill and an announcement disagree, it trusts the measured refill ^[3]. Each reset used in the forecast is listed with a link to where it was announced ^[3].

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]. A public API that needs no key gives stats, paginated reset history, forecasts and operational health ^[3]. It is an independent tracker and is not affiliated with OpenAI ^[3].

Pricing and fees

ccusage is licensed under MIT ^[1]. Its sources here state no price, so a price is not published here.

OpenAI Status's sources here state no price for viewing the page, so a price is not published here ^[2].

Codex Forecast is free, with no account and no paid tier ^[3]. The table gives each option's own fee and a card fee, which none of these sources state.

Setting it up and daily use

ccusage can be run directly without a global installation using npx ^[1], or via npm or other package runners ^[1]. Pricing can be overridden per raw model name in ccusage.json ^[1].

OpenAI Status needs no setup described in its sources here. Its page says OpenAI is not aware of any issues affecting its systems ^[2]. The sources say nothing more about routine use.

Codex Forecast is a website with a public API ^[3]. The site and API share a snapshot that is cached for up to five minutes ^[3]. The API has a published OpenAPI specification ^[3].

Things to check before you choose

Ask what you need to know: your own token spending, whether OpenAI systems are up, or when Codex limits may reset. ccusage's page speaks of cache creation and cache read tokens ^[1], OpenAI Status's of system issues ^[2], and Codex Forecast's claims of reset estimates ^[3].

Check ccusage's pages for the coding agents it supports.

Check how fresh the data must be. Codex Forecast shares a snapshot cached for up to five minutes ^[3]. Check the other pages for how often they update, since the facts here do not say.

Check whether you want data from your own machine or from a website, and whether an API matters to you.

How to choose

If you want to run a usage tool without a global install, ccusage's page describes npx ^[1].

If you want to override token prices per model name, ccusage describes ccusage.json ^[1].

If you want to know whether OpenAI reports any issues, OpenAI Status's page says so ^[2]. Its Codex uptime is shown as 99.95% ^[2].

If you want an estimate of the next Codex limit reset, Codex Forecast's claims describe it ^[3].

If you want free reset emails or a keyless public API, Codex Forecast's claims describe both ^[3] ^[3].

Frequently asked questions

Is ccusage free to use?

ccusage is licensed under MIT ^[1]. The sources here state no price for it, so a price is not published here. It can run directly without a global installation using npx ^[1]. Check its own pages if you need more detail on cost.

What does OpenAI Status show?

Its page says OpenAI is not aware of any issues affecting its systems ^[2]. It lists Codex at 99.95% uptime across 4 components ^[2]. Uptime is reported at an aggregate level across all tiers, models and error types ^[2].

Does ccusage track cache tokens?

ccusage tracks and displays cache creation and cache read tokens separately ^[1]. It also allows overriding token pricing per raw model name in ccusage.json without rebuilding ^[1]. Check its own pages for which coding agents it supports.

How does Codex Forecast estimate Codex limit resets?

It combines an account it checks every 60 seconds, OpenAI staff announcements and the OpenAI status page ^[3]. When a measured refill and an announcement disagree, it trusts the measured refill ^[3]. Each reset used is listed with a link to its announcement ^[3].

Is Codex Forecast free and does it have an API?

It is free, with no account and no paid tier ^[3]. A public API that needs no key gives stats, paginated reset history, forecasts and operational health ^[3]. The API has a published OpenAPI specification ^[3]. It is not affiliated with OpenAI ^[3].

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

Try Codex Forecast