Never hit a limit
you didn't
see coming.
AI Cockpit puts the limits and the spend of eight AI services on one panel — Claude, ChatGPT & Codex, the Anthropic API, the OpenAI API, Kimi K3, OpenRouter, Grok and GitHub Copilot. It only reads. Nothing passes through a server of mine.
Both free · optional tip in the app
- What
- The limits and spend of eight AI services on one panel — Claude, ChatGPT and Codex, the Anthropic and OpenAI APIs, Kimi, OpenRouter, Grok, GitHub Copilot.
- Where
- Mac menu bar (macOS 14+), plus iPhone, iPad and Apple Watch from iOS 17 — and the Windows notification area. The phone fetches everything itself, no Mac has to be awake.
- Cost
- Free. No account with me, no subscription, no pro tier. An optional tip in the app that unlocks nothing.
- Trust
- It only reads. Keys stay in the device's keychain — on Windows, in the Windows Credential Manager. Nothing passes through a server of mine, no telemetry. No API key is required — the subscription cards run on OAuth.
The sentences this panel was built to prevent
Try again at 2:00 PM.
The limit isn’t the problem.
The surprise is.
It never arrives at a good moment. You are three files deep in a refactor, the context is warm, and the window was at 90% forty minutes ago — you just had no way of knowing that.
AI Cockpit keeps the numbers where you already look: the Mac’s menu bar, your Home Screen, your wrist. Eight services on one panel — you watch a window fill up, and it turns amber before the window runs out. The phone fetches its own figures; no Mac has to be awake for it.
Look before you sign in
Demo mode fills every card with sample figures — no account, no key, nothing to enter. It is in the app on all three platforms, and it is the fastest way to see whether the cockpit shows what you need.
The full cockpit
Two columns, ordered by provider: the subscription sits above the API bill of the same house. Below, your active Claude Code sessions with context usage.
dashboard — time marker, over or under plan, Codex credits · demo figures
What’s new, in pictures
Mac 6.9 and iPhone 2.10 are with Apple for review; Windows 1.4 follows. Everything below is the real app with sample figures from demo mode.
time marker — over or under plan at a glance, on phone and watch
widgets you set up — Home Screen and Lock Screen, with a live countdown
Mac — compact panel and desktop widgets
Usage window — where your Claude and Codex quota went
Quick start
Nothing to read up on: a four-step assistant opens on first launch, Skip works on every step, and everything can be done later in the settings. One thing to know beforehand — the cockpit reads your accounts. The subscriptions and API credit it shows are ones you already hold and pay for at the providers themselves.
What it does with those numbers
The services are listed above. This is what the cockpit makes of them.
NewOver or under planMAC + IOS + WIN
A time marker in every bar shows how much of the window has passed. One look tells you whether you are ahead of your quota or running into it — “28 % over plan” says it in words.
NewUsed — or what’s leftMAC + IOS + WIN
Read every quota the way you think: as used or as remaining, on cards, widgets, the menu bar and the watch. The warning colours stay honest either way.
NewA countdown that ticksMAC + IOS
On the Lock Screen and in the widget the time to the next reset counts down every second — and the iPhone widget now fetches every service itself, Codex credits included.
A forecast, not just a numberMAC + IOS + WIN
Every window says when it resets and, from your pace, when you will run into it — the figure you actually plan around.
Alerts before the wallMAC + IOS + WIN
A notification when a window crosses your own threshold. Two levels, both off until you switch them on.
Widgets everywhereMAC + IOS + WATCH
Desktop widgets on the Mac, Home Screen, Lock Screen and StandBy on the phone — set up your way: one service or all, used or remaining. A complication in four shapes on the wrist.
The menu bar, your wayMAC
Both values, only the most critical one, a ring or the time remaining — plus a key-figures bar you compose yourself.
Live Claude Code sessionsMAC + WIN
What is running right now, with model, subagents, token shares and context window — and a heads-up when a session waits for you.
Outages, namedMAC + IOS + WIN
When a provider reports an incident, its card says so — instead of leaving you to wonder whether the fault is yours.
Demo modeMAC + IOS + WIN
Every card filled with sample figures, without a single account. Look around first, sign in later.
Ask it out loudIOS
«How full is my Claude window?» — Siri and Shortcuts answer from the figures already on the device.
Where your quota wentMAC
By project, model and hour, up to a year back — raw tokens, their API-price equivalent and an estimated share of each window. Numbers only, kept on your Mac.
Eight services. Up to ten cards. One cockpit.
Every subscription and API you pay for, side by side — each with the one figure that decides whether you can keep working. Add only what you use; every card is optional. Claude counts twice if you want it to: a second account gets its own card.
All eight services run on all three platforms: OpenRouter and Grok arrived with version 6.0 for the Mac and are on iPhone, iPad and Apple Watch as of version 2.3; GitHub Copilot has been on iPhone, iPad and Apple Watch since version 2.5 and is on the Mac since 6.5. Only Claude Code sessions stays off the phone — it reads sessions running on the machine itself, so there would be nothing to show. Mac and Windows both have it.
One cockpit, five devices
The Mac app watches while you work. The iPhone app — which brings iPad and Apple Watch with it — answers the question you have everywhere else: is there anything left? And on Windows the same cockpit sits in the notification area of the taskbar.
the same number on the phone and on the wrist — sample figures from demo mode
AI Cockpit for Mac
The full instrument panel, one hotkey away.
- All ten cards — including a second Claude account and your live Claude Code sessions
- Drag the cards into the order you want them in
- History, sparklines and limit forecasts
- Four menu bar styles — and you choose which figures they show
- Alerts before a window runs out
Free
AI Cockpit for iPhone
The same numbers, wherever you are.
- All eight services, fetched by the phone itself — no Mac needed
- Home Screen widgets: one line per provider, in its colour
- Lock Screen and StandBy tiles with the age of every figure
- Demo mode — look around before signing in to anything
- Apple Watch included: a one-line verdict on your wrist and a complication in four shapes — no separate app, no extra download
Free · with an optional tip
AI Cockpit for Windows
The same core, rebuilt for the taskbar.
- All eight services and up to ten cards, as on the Mac
- A ring in the notification area, showing the figure you choose
- Sign in to Claude and ChatGPT from the app itself
- Outage notices per provider, straight from the status pages
- Demo mode — look around before signing in to anything
Claude Code sessions run on Mac and Windows, not on the phone — they read files on the machine. Widgets are on Mac and iPhone; the tip jar and the voice query exist only in the App Store editions. Everything else is on all three.
About the Windows build: it is a snapshot, not a twin — 1.3 matches macOS 6.5 and will not follow every Mac release. It is in no store, so there are no automatic updates, and the file is unsigned: Windows will call it an unrecognised app, and you get past that with More info → Run anyway. Version 1.3 is built and tested, but a full round on real hardware is still running — if you would rather wait, 1.2 is still there.
What runs where
Everything that keeps a limit from catching you out — on every screen you use. Honest ticks only: a dash means it is not there, “from 6.9” means it comes with the next version. Windows is a free test build outside the stores: no sandbox, no signature, no automatic updates.
| Feature | Macmenu bar | iPhone · iPad · WatchLock Screen · wrist | Windowsnotification area |
|---|---|---|---|
| Version today | 6.8 6.9 in review — what’s new → | 2.9 2.10 in review — what’s new → | 1.3 · test build Next: 1.4 — what’s new → |
| Price | free | free · optional tip | free |
| Runs on | macOS 14+ | iOS 17+ · watchOS 10+ | Windows 11 · x64 + ARM |
| Get it from | Mac App Store | App Store | GitHub release |
| Never caught out by a limit | |||
| Claude, ChatGPT & Codex, OpenAI, Anthropic, Kimi, OpenRouter, Grok, Copilot — all eight | yes | yes | yes |
| Warns before a limit hits — with a forecast of when | yes | yes | yes |
| Time marker: see at a glance if you are over or under plan | from 6.9 | from 2.10 | from 1.4 |
| Live countdown to the next reset | widget · from 6.9 | Lock Screen · from 2.10 | cards · from 1.4 |
| Show quotas as used or as what’s left | from 6.9 | from 2.10 | from 1.4 |
| Outage notices straight from the status pages | yes | yes | yes |
| Always in view | |||
| Gauge you never have to open | menu bar | Lock Screen | notification area |
| Widgets | yes | Home + Lock Screen | no |
| Widget you set up yourself — one service or all | from 6.9 | from 2.10 | no |
| On your wrist: Apple Watch app and complication | no | yes | no |
| Live Activity and StandBy | no | yes | no |
| Ask Siri | no | yes | no |
| Costs under control | |||
| API spend today and this month | yes | yes | yes |
| Monthly budget for all API costs, with warnings | yes | yes | no |
| Codex credit balance, in credits — never guessed dollars | yes | yes | from 1.4 |
| Where your Claude and Codex quota went — by project, model, hour | yes | no | no |
| A short daily summary | yes | no | no |
| For Claude Code users | |||
| Live Claude Code sessions, with a warning before the context window fills | yes | no | yes |
| Second Claude account | yes | yes | yes |
| Open with a keyboard shortcut | yes | no | yes |
| Trust | |||
| No account, no server in between, no telemetry | yes | yes | yes |
| Only reads — creates, changes and deletes nothing | yes | yes | yes |
| Credentials stay in | Keychain | Keychain | Credential Manager |
| From the App Store — one click, no security warning | yes | yes | no |
| Sandbox, enforced by macOS and iOS — not just promised | yes | yes | no |
| Signed and notarised | yes | yes | no |
| Automatic updates — fixes reach everyone | yes | yes | by hand |
| Public security log — four documented reviews | yes | same core | no |
| Demo mode — look around before signing in | yes | yes | yes |
| English and German | yes | yes | yes |
Free, and nothing sold on the side
Both apps are free on their App Stores — no trial that expires, no feature held back for a paid tier. No subscription, no account with me, no usage limit. The subscriptions and API credit the cockpit reads are ones you already hold and pay for at the providers themselves.
It is paid for by a tip jar in the app, under Settings → About. It unlocks nothing and changes nothing — there is no paid tier to buy into. The long answer is in the FAQ.
- Credentials live only in the device's keychain — on Windows, in the Windows Credential Manager
- Direct connection to the official APIs — no server of mine in between, no telemetry, no ads
- The app only ever reads with a key: it creates, changes and deletes nothing
- Built by an indie developer in Switzerland — no VC, no data business (legal notice · Contact)
✓ Security-reviewed — four documented passes, the last against version 5.0 (10 August 2026). Checked against, not certified by:
A documented model-assisted review with Claude — not an external audit, and it says so plainly. The record names every host the app ever connects to, line by line: read the whole record, or check the privacy policy and the FAQ.
Convinced? Both apps are free: AI Cockpit for Mac · AI Cockpit for iPhone (iOS 17 and up).
What's new
Mac 6.8 is out, with a new Usage window: where your Claude and Codex quota went, by project, model and hour — raw tokens, the equivalent at API list prices (not an invoice) and an estimated share of the 5-hour and 7-day windows. The totals stay on your Mac, numbers only. Create analysis saves it all as an HTML report or CSV. History now keeps 180 days, and a monthly budget warns at 75 and 100 per cent of your API spend. Two figures were wrong: Anthropic API costs showed a hundred times too high, and session tokens were counted about 2.7 times. iPhone, iPad and Watch 2.9 is out too, with the same monthly budget, and GitHub Copilot now counts in the monthly total.
Coming next: Mac 6.9 and iPhone 2.10 are with Apple for review, Windows 1.4 is in preparation — quotas as used or remaining, a widget you can set up (on the Lock Screen too) with Codex credits, and calmer refresh intervals. What’s new, per platform: Mac · iPhone, iPad & Watch · Windows · every release in plain language →
How the numbers are read
Three pages go into the detail — each one also says what the app cannot know, because a number you cannot trust is worse than none.
Claude usage limits
The 5-hour and 7-day windows, model-scoped weekly limits, how the forecast is calculated and when it warns.
Codex quotas and reset times
Two Codex windows, never three: how quotas are matched by window length, where the live figures come from, what credits are.
API costs at a glance
Subscription quota is not API cost. Which services are read, why admin keys are needed, and what is only ever read.
Quick answers
The questions people search for most — answered from the providers' own documentation, with what they do not say.
When does the Claude limit reset?
The 5-hour window, the weekly limit, limits per model, where to see the reset time and what happens when you hit it.
Where did my Claude usage go?
Where Claude Code logs tokens per project, why a plain sum is too high, and the 30-day limit.
How do I check my Codex usage?
/status in the CLI, the usage page on the web, both windows,
resets and credits.
What is the OpenAI API costing me?
Where the month's spend shows up, how to set budgets and alerts, and why a ChatGPT plan is not API credit.
What is the Claude API costing me?
The Cost page in the Console, credits, spend limits, and the Cost API with an admin key.
Claude Pro or Max: how much more?
What the 5x and 20x really cover, what they do not, and how to tell whether you need Max.
ChatGPT Plus limits and resets
What OpenAI says about limits per model, what it leaves open, and what happens when you hit one.
How much Copilot is left?
AI credits and premium requests: where GitHub shows them, when they reset, and budgets.
OpenRouter credits and spend
Where to see your balance, how to read it by API, and limits per key.
Grok API usage and credits
Where xAI shows usage and credit, prepaid or invoiced, and spending limits.
Kimi API balance
Where Moonshot shows your balance, the balance endpoint, and what happens at zero.
Feedback & feature requests
Missing a provider? Want a metric the cockpit doesn't show yet? Tell me — short and direct is perfect.
Ready for the cockpit?
Mac, iPhone and Watch come from their App Stores, Windows as a test build — free, no subscription, no account with me: just the provider accounts you already have.
Both apps: free · no subscription · an optional tip inside the app
The subscriptions and API credit the cockpit reads are yours and stay with your providers — it adds no cost of its own. If you do leave a tip and change your mind, that goes through Apple, at reportaproblem.apple.com.