Claude Code vs OpenRouter: tracking usage on Mac and Windows
This is not an argument about which tool writes better code - that depends on your work, and anyone claiming otherwise is guessing. It is about something narrower and more answerable: how each one is metered, and what you can actually see while you use them.
How each is tracked
Claude Code uses an existing local login, and usage is read locally, so it keeps working when the network does not.
OpenRouter uses an OpenRouter API key, and it fronts many upstream models, so per-model spend is the easiest thing to lose track of.
How Claude Code and OpenRouter meter your usage
Claude Code is included with Claude Pro, which Anthropic prices at $17 a month on an annual plan ($200 billed up front) or $20 billed monthly, with Max at $100 a month for five times Pro's usage, and with Ultra, which replaced Max 20x, at $200 for ten times Pro's week. Those limits are shared between Claude and Claude Code, so chat and coding draw from one allowance. Paid plans have a five-hour session limit (a verified Ultra account has none) and weekly limits, and Settings > Usage shows progress bars for both, the time left in the current session and when the weekly limit resets.
OpenRouter works the other way round: no allowance, only a balance. You prepay US-dollar credits and each request's cost is deducted at the provider's price, with no markup on inference. OpenRouter's cut is a fee on each credit purchase, which its pricing page sets at 5.5% on pay-as-you-go Standard and 8% on Business; a Free plan offers 25+ free models at 50 requests a day.
That means there is no session or weekly window to wait out. Under OpenRouter's credit and rate limit rules, a request your balance or a per-key cap cannot cover fails with a 402. Paid models carry no plan-based rate limit, so a limit you hit there normally comes from the upstream provider. The free model variants are capped at 20 requests per minute, with a daily ceiling of 50 that rises to 1,000 once your account has bought at least $10 of credits.
Inside Claude Code, /usage shows subscribers their plan usage bars, activity stats and a usage breakdown. On OpenRouter, the Activity dashboard slices spend, requests and tokens by model, provider, API key, app or user, and exports them as CSV or PDF.
When Claude Code hits a session or weekly limit, the message shows when the window resets. Pro and Max users can wait, upgrade, or turn on usage credits to keep working past the limit. One trap from Anthropic's help center: if an ANTHROPIC_API_KEY environment variable is set, Claude Code uses it and you pay API usage charges instead of drawing on your subscription. On OpenRouter the fix is money rather than time: add credits, manually or through auto top-up, or lift the cap on that key. Plans and limits checked 3 October 2026 on each vendor's official pages.
Why this matters if you run both
Running two tools means two places to check, two sets of limits, and two chances to be surprised mid-task. The cost is rarely the money - it is losing your thread because something stopped answering and you did not see it coming.
Watching both in one place
SessionWatcher shows Claude Code and OpenRouter together in the Mac menu bar or the Windows taskbar. It reads and displays usage on your Mac or PC; it does not read your code or your conversations. That boundary matters more when you are pointing one tool at two providers.
Per-tool detail is in the Claude Code tracker guide and the OpenRouter tracker guide.
Frequently asked questions
Can I track both at once?
Yes - both appear in the same reading, in the Mac menu bar or the Windows taskbar.
What does each need?
Claude Code uses an existing local login. OpenRouter uses an OpenRouter API key.
Does it read my code?
No. Usage only, never code or conversation content.
Does OpenRouter have a five-hour limit like Claude Code?
No. Claude Pro and Max have a five-hour session limit plus weekly limits, shared between Claude and Claude Code. OpenRouter has no usage windows: a request fails when your credit balance or a per-key cap cannot cover it, paid models follow the upstream provider's rate limits, and free variants top out at 20 requests per minute and 50 per day, rising to 1,000 per day once you have bought at least $10 of credits (OpenRouter limits).
Which account pays when I run Claude Code?
It depends on how Claude Code authenticates. Signed in with a Claude Pro or Max account, it draws on your plan usage limits. If an ANTHROPIC_API_KEY environment variable is set, it uses that key and you pay API usage charges instead. Launched through OpenRouter's Ori Harness with ori claude, it runs with OpenRouter credentials, and that traffic is paid through normal OpenRouter billing.
SessionWatcherRunning both?
Watch them in one menu bar.
Native app for the Mac menu bar and the Windows taskbar. Track Claude, Codex and 20 more tools' usage, costs, and rate limits in real time.


“Fast, simple, and does exactly what it should. Definitely worth it.”
@nicojerome on GitHub
macOS 14+. Free for 7 days, no credit card.





