Check your Claude Code usage with /usage
Type /usage in Claude Code. The command reference sums it up: “Show session cost, plan usage limits, and activity stats.” /cost and /stats are aliases, and it works while Claude is responding. (Claude Code docs: commands)
With a Pro or Max plan: “Subscribers see plan usage bars, activity stats, and a usage breakdown on the same screen.” The bars are the number to watch: how much of each limit is used. (Claude Code docs: costs)
Each limit has a reset time, and the error reference names where to find it: “Run /usage to see your plan limits and when they reset”. Before a window runs out, Claude Code can also warn you that you have used most of it. (errors)
What is using up your plan: the usage breakdown
On a Pro, Max, Team or Enterprise plan, /usage also breaks down what counts against your limits. Attribution is “recent usage attributed to skills, subagents, plugins, and individual MCP servers, each shown as a percentage of the total.” Behavior flags are “behaviors such as long context or cache misses, flagged when one accounts for 10% or more of recent usage.” A third part lists your heaviest /loop and other scheduled tasks. (Claude Code docs: costs)
Press d or w to switch between the last 24 hours and the last 7 days. Read the shares as a guide, not as a bill: “The figures are approximate and computed from local session history on this machine, so usage from other devices or claude.ai is not included.” (costs)
The same page lists why a long session uses more than your activity suggests: long context, cache misses after a break, scheduled tasks, subagents and compaction. (Why usage climbs in a long session)
The same bars on claude.ai, in the Desktop app and in VS Code
On claude.ai, with a Pro, Max, Team or seat-based Enterprise plan, “you can navigate to Settings > Usage to view progress bars showing how much of your five-hour session and weekly usage limits you’ve consumed.” It also shows the time left in the session and when the weekly limit resets. (Usage limit best practices)
In the Desktop app: “Click the usage ring next to the model picker to see your current context window usage and your plan usage for the period.” In the VS Code extension, /usage opens the Account & usage dialog with usage bars and a breakdown. (Desktop app, VS Code)
All of them show one allowance: “Context usage is per session; plan usage is shared across all your Claude Code surfaces.” (Desktop app)
A usage monitor while you work: /context and the status line
/context answers a different question: what fills the conversation right now. The command reference: “Visualize current context usage as a colored grid. Shows optimization suggestions for context-heavy tools, memory bloat, and capacity warnings.” (commands) A full context window is not a usage limit, but it feeds one: “Token costs scale with context size: the more context Claude processes, the more tokens you use.” (costs)
For a display that stays on screen, there is the status line, “a customizable bar at the bottom of Claude Code that runs any shell script you configure.” The script receives session data, including context_window.used_percentage and, on a subscription, rate_limits.five_hour.used_percentage and rate_limits.seven_day.used_percentage. (Claude Code docs: status line)
Type /statusline and describe what you want, and Claude Code writes the script. The plan fields are not there for everyone: “The rate_limits object is only present for claude.ai Pro and Max subscribers, or behind a Claude apps gateway with spend limits, and only after the first API response.” Watching costs nothing: “The status line runs locally and does not consume API tokens.” (status line)
Tokens, dollars or share of your plan: which number counts
On Pro and Max, the number that counts is the share of your limit: “The Session block in /usage shows API token usage and is intended for API users. Claude Max and Pro subscribers have usage included in their subscription, so the session cost figure isn’t relevant for billing purposes.” (costs)
Anthropic’s plan pages do not say how many tokens a limit holds. The Pro page: “The number of messages you can send will vary based on message length, including the length of files you attach, the length of your current conversation, and the model or feature you use.” (Pro plan, Max plan)
If you pay per token with a Claude Console account, the Session block is your number: tokens by model and a dollar total for the current session. “The figure is an estimate, so for authoritative billing see the Usage page in the Claude Console.” There, the Usage page breaks usage down by model, date and API key. (costs, Cost and usage reporting in the Claude Console)
Check which case is yours: if an ANTHROPIC_API_KEY environment variable is set, Claude Code uses that key instead of your subscription, and you are charged per token. (Using Claude Code with Pro or Max)
ccusage and other community usage trackers
ccusage is an open-source command-line tool under the MIT license. It is not made by Anthropic. According to its README, it “reads local usage data from coding agent CLIs and turns it into daily, weekly, monthly, and session reports.” (ccusage on GitHub)
Other community-built monitors and trackers for Claude Code exist; this page does not rate them. For plan limits and reset times, Anthropic’s own pages point to /usage and to Settings › Usage. (errors, usage limit best practices)
What to do with the numbers
Start with the flags: “On a Pro, Max, Team, or Enterprise plan, the /usage breakdown flags behaviors that account for 10% or more of your recent usage, such as long context or cache misses, each with a tip to reduce it.” (costs)
Then read the attribution. A skill or MCP server with a large share that you rarely need is a candidate to turn off. To compare two ways of working, note the bars, do the same kind of task both ways, and read them again.
If you are blocked right now, or want Anthropic’s own list of ways to use less, read Claude usage limit reached — what to do.
One more option: Grace
Our own product — this section is advertising.
Grace is our product for Claude Code on Mac and Windows. The numbers on this page show how much of your plan your work uses; Grace is for getting the same work done with less of the plan’s limit. We measured it against Claude Code with caveman and context-mode installed:
Test result
≈ −49 % of the 5-hour limit for the same 60 tasks.
Measured against Claude Code with two token-saving plugins already installed: caveman and context-mode.
Read from the limit in whole percentage points, two measurements added up: 32 % with Grace 0.3.8, 63 % with Claude Code + caveman + context-mode · 60 tasks, Claude Max 20x on both sides · October 2 – 3, 2026: 30 tasks at the same time on two accounts, 30 with the comparison run measured separately on the same day · on the comparison account 54 s of readings are missing at a 5-hour reset, which can only make the saving look smaller
≈ 96–100 %more work in the same limit
Calculated from the limit value above: ≈ 96 % more. On 43 of the 58 tasks both runs finished, at least twice as much: 2.0× to 4.4×, calculated from Claude’s cost per task (quality on those: 94 % with Grace, 93 % Claude alone). 2 more such tasks are not counted because of their quality (45 % with Grace, 93 % Claude alone).
49 %less time
Measured at the same time with Grace 0.3.8 (October 3, 2026): 3 h 41 min with Grace, 7 h 10 min Claude alone — the time of all 30 tasks, added up. Grace was faster on 28 of them; quality: 93 % with Grace, 90 % Claude alone. Only the 30 tasks measured at the same time are compared on time; the other 30 were measured separately.
All measurements, task by task Token savers, measured
Try it yourself: your first month is free, and /usage shows the difference on your own work.
Just create an account · no payment details · ends on its own
Questions
How do I check my Claude Code usage?
Type /usage in Claude Code. On Pro and Max it shows plan usage bars and a usage breakdown; on claude.ai the bars are under Settings › Usage. (Claude Code docs: costs, usage limit best practices)
How do I see my Claude Code token usage?
The Session block at the top of /usage shows the token usage of your current session by model. /context shows what is filling the context window right now. (costs, commands)
Is there a Claude Code usage monitor?
Yes, built in: a custom status line can show the used percentage of your five-hour and weekly limits and of the context window. The Desktop app has a usage ring next to the model picker. (status line, Desktop app)
Is there a Claude Code usage dashboard?
For your own plan it is Settings › Usage on claude.ai. API organizations have the Usage and Cost pages in the Claude Console; Team and Enterprise admins have an analytics dashboard. (usage limit best practices, Console reporting, analytics)
What is ccusage?
An open-source command-line tool, not made by Anthropic. Its README says it reads local usage data from coding agent CLIs, Claude Code among them, and turns it into reports. (ccusage on GitHub)
Do /cost and /stats still work in Claude Code?
Yes. Both are aliases for /usage; /stats opens it on the Stats tab. (commands)
Sources
Anthropic’s pages and the ccusage README, checked on 5 October 2026. Anthropic changes limits, commands and wording from time to time — their pages are what counts.
- Claude Code docs: Manage costs effectively code.claude.com
- Claude Code docs: Commands code.claude.com
- Claude Code docs: Customize your status line code.claude.com
- Claude Code docs: Error reference code.claude.com
- Claude Code docs: Desktop application code.claude.com
- Claude Code docs: Use Claude Code in VS Code code.claude.com
- Claude Code docs: Track team usage with analytics code.claude.com
- Usage limit best practices support.claude.com
- What is the Pro plan? support.claude.com
- What is the Max plan? support.claude.com
- Use Claude Code with your Pro or Max plan support.claude.com
- Cost and Usage Reporting in the Claude Console support.claude.com
- ccusage README on GitHub (third party, not Anthropic) github.com