How to See Claude Code Usage Limits on Mac

Short answer: type /usage inside Claude Code. On a Pro or Max plan it shows how much of your 5-hour session limit and your weekly limit you’ve used, and when each resets. The same numbers are on claude.ai under Settings → Usage. To keep Claude Code usage limits in view on a Mac without asking, add them to Claude Code’s status line or run a menu bar app such as FavTray (free), CodexBar or Claude Usage Tracker.

Checked 26 September 2026 against the Claude Code docs, Anthropic’s help centre and each app’s own site.

What are Claude Code’s usage limits?

On a Claude Pro or Max subscription, Claude Code doesn’t bill per token. Instead you get a share of usage that refills on two clocks:

Limit	How it works
Session (5-hour)	Resets every five hours. When it runs out, Claude Code says “You’ve hit your session limit” and shows the reset time
Weekly	Applies across all models and resets at a fixed time each week. The message reads “You’ve hit your weekly limit”
Model-specific	Some plans also cap a model family; the message then reads “You’ve hit your Opus limit” (or Sonnet), and switching model with /model keeps you working

Two details catch people out:

• The limits are shared. Anthropic says Pro and Max limits are shared across Claude and Claude Code, so a long chat on your phone uses the same allowance as your coding session.
• API-key users have no plan limits. If you sign in to Claude Code with a Console API key, or have ANTHROPIC_API_KEY set, you pay per token and see spend in the Claude Console instead. Everything below is about subscriptions.

If you’re deciding whether a bigger plan is worth it, our Claude Max worth it breakdown does the maths. This page is only about seeing where you are.

How do you check usage limits inside Claude Code?

Run /usage at the Claude Code prompt. According to the Claude Code commands reference, it shows session cost, plan usage limits and activity stats, and on Pro, Max, Team and Enterprise plans it adds a breakdown of what counted against your limits.

• /cost and /stats are aliases for the same screen (/stats opens on the Stats tab).
• It runs immediately even while Claude is responding, so you don’t have to wait for a turn to finish.
• The dollar “Session” figure at the top is an estimate at API list prices. On a subscription it isn’t what you pay; the usage bars are what matter.

Older help articles mention /status for this. In current versions /status shows your version, model, account and connectivity, and /usage is the one with the limit bars.

When you hit a limit, /rate-limit-options lists what you can do: wait and continue automatically when the limit resets, add usage credits, or upgrade. It doesn’t appear in the command menu, so type it in full.

How do you check Claude usage limits on claude.ai?

Open claude.ai/settings/usage (Settings → Usage). It shows the same session and weekly bars with their reset times, and the usage-credits section if you’ve turned credits on. Team and Enterprise admins see their organisation’s view under Admin settings → Usage.

This is the quickest check when you’re not in a terminal, but it’s still something you have to remember to open.

How do you show Claude Code usage limits in the status line?

Claude Code passes a JSON blob to your status line script, and on Pro and Max it includes rate_limits.five_hour and rate_limits.seven_day, each with used_percentage and resets_at. A minimal script:

#!/bin/bash
input=$(cat)
FIVE_H=$(echo "$input" | jq -r '.rate_limits.five_hour.used_percentage // empty')
WEEK=$(echo "$input" | jq -r '.rate_limits.seven_day.used_percentage // empty')
echo "5h ${FIVE_H:-–}% · week ${WEEK:-–}%"

Save it as ~/.claude/statusline.sh, make it executable, and point the statusLine setting in ~/.claude/settings.json at it (or run /statusline and describe what you want). Two limits of this approach:

• rate_limits only appears after the first response in a session, and only for Pro and Max subscribers.
• You only see it while a Claude Code session is open, in that terminal.

How do you see Claude Code usage limits in the Mac menu bar?

A menu bar app keeps the numbers visible all day, including when no session is running. The good ones reuse the Claude Code login already on your Mac, so there’s no second sign-in.

FavTray (free). FavTray’s AI usage tracker is free on every install, with full history. For Claude it shows:

• the 5-hour session, the weekly limit and any model-specific weekly limit your plan reports, plus usage credits if you have them;
• a tick on each bar where an even pace would put you, and a plain-English pace line (“Using faster than average”, “On pace”, “Plenty of room”);
• a projection once you’re 10 minutes into a window: “At this pace you’ll hit the limit in 1h 20m, around 16:40”, or the percentage you’ll end the window on;
• notifications at 80%, 95% and when a limit is hit;
• optionally, the session or weekly percentage left, or the time to reset, as text in the menu bar itself.

It reads Claude Code’s saved login to check your limits (macOS may ask you once to allow access to the “Claude Code-credentials” keychain item) and never refreshes it, so it can’t sign you out of Claude Code. It refreshes every 15, 30 or 60 minutes (15 by default), half as often in Low Power Mode, and again when you open it if the last reading is more than 5 minutes old. The same screen covers 30 providers, including Codex, Cursor, Gemini and Copilot, if you use more than one coding tool.

Other menu bar apps that show Claude limits:

App	Price (checked 26 Sep 2026)	Good to know
CodexBar	Free, open source (MIT)	Tracks 87 providers, has a CLI, macOS 14+
Claude Usage Tracker	Free, open source (MIT)	Multiple Claude accounts, terminal status line, macOS 14+
Usagebar	Free tier; $9 one-time	Claude-focused; reads Claude Code’s keychain login
SessionWatcher	$6.99 one-time (Claude); Pro $59 one-time or $24/yr	Widgets and 90-day history on Pro

For a wider comparison, including tools for OpenAI, Cursor and API spend, see our roundup of AI usage tracking tools.

Why do ccusage and /usage show different numbers?

ccusage reads the log files Claude Code writes on your Mac and adds up tokens and cost. ccusage blocks even groups them into 5-hour blocks. But the logs don’t contain Anthropic’s plan limits, so ccusage can’t tell you what percentage of your limit you’ve used, and its blocks won’t line up exactly with the official window.

• For “how close am I to being cut off?”, use /usage, claude.ai, or a menu bar app that reads your plan’s usage from Anthropic.
• For “what did this project cost?”, ccusage (or FavTray’s cost view, which also works from local Claude Code and Codex logs) is the right tool.

What should you do when you’re close to the limit?

• Check the reset time first. If the session resets in 20 minutes, waiting may be cheaper than anything else.
• Switch model if you hit a model-specific limit; /model to a different family keeps you going. It won’t help with the session or weekly limit, which covers every model.
• Cut token use. Shorter contexts, /compact and fewer re-reads go a long way; our guide to reducing Claude Code token usage has the details.
• Add usage credits or upgrade from /rate-limit-options, or manage credits with /usage-credits. Credits are billed separately from your plan, so set a monthly cap.

If you’re weighing plans against API pricing, see Claude Code pricing: Pro vs Max vs API.

Sources (checked 26 September 2026): Claude Code commands, status line docs, costs and usage docs, Using Claude Code with your Pro or Max plan, and each app’s own page linked above.