Last verified

How to check usage in Claude Code?

3 Steps · in-session · console
  1. Run /usage inside a session. The Session block at the top shows token statistics for the current session; below it, subscribers get plan-limit bars.
  2. Switch the window with d for the last 24 hours or w for the last 7 days, and read the breakdown by skills, subagents, plugins and individual MCP servers.
  3. Reconcile against the Usage page in the Claude Console if money matters — the in-session dollar figure is computed locally and isn't authoritative.
Command /usagein session
Windows 24hor 7 days
Scope this machineonly
Authoritative Consoleusage page
§ 01 / SOURCE

Where this answer comes from.

Methodology →
PER VENDOR DOCS · AUG 01, 2026

The number in your terminal is an estimate, and the docs say so.

Two caveats sit in Anthropic's own cost documentation, and both change how you should read the panel. First, Claude Code "computes the dollar figure locally from token counts priced at standard list rates, so it doesn't reflect promotional pricing or contracted discounts and may differ from your actual bill". For authoritative billing, the Console's Usage page is the reference.

Second, the plan-limit breakdown is "approximate and computed from local session history on this machine, so usage from other devices or claude.ai is not included". If you work across a laptop and a desktop, neither number is the whole picture.

What the breakdown does well is attribution: it splits recent usage across skills, subagents, plugins and individual MCP servers as percentages, and flags behaviours like long context or cache misses when one accounts for 10% or more. That's the part that actually tells you where the tokens went.

Scope of our check: this page is read off the documentation. /usage is a session command that draws an interactive panel, so it isn't scriptable and we have no transcript to publish — unlike the CLI-level commands we tested elsewhere.

In-session command: /usageDollar figure: local estimate, list ratesExcludes: other devices · claude.aiAttribution: skills · subagents · MCPFlags at: ≥10% of recent usage
!
Per vendor docs — we did not run this test. The answer above rests on the source below, read on . Where we run a capability ourselves, this section carries the terminal transcript instead.
Source Anthropic docs — Manage costs effectively, "Track your costs" https://code.claude.com/docs/en/costs
§ 02 / WHY

Reading it correctly.

2.1
Subscribers and API users read different halves

The Session block's cost figure is aimed at API users, who are billed per token. On Pro or Max your usage is included in the subscription, so that dollar number isn't a bill — it's a proxy for how hard you're driving the tool. What subscribers should read instead are the plan usage bars and the activity breakdown on the same screen.

If you're weighing which billing model suits you, the number is still useful as an input to the subscription-vs-API comparison.

2.2
The breakdown is where the savings are

Attribution by skills, subagents, plugins and MCP servers turns a vague "I hit my limit" into something actionable — a chatty MCP server or a subagent fan-out can quietly dominate. The flags for long context and cache misses point at the two biggest levers directly.

Context is the usual culprit: token cost scales with how much the model has to read, which is why prompt caching and compaction exist at all.

2.3
When the panel won't load

If the plan-limit request fails — usually because the usage endpoint is rate limited — /usage falls back to the last bars it loaded on that machine within the past hour, labelled Showing last-known usage with an age. Press r to retry. Without a recent snapshot it reports the rate limit and offers the same retry.

That's a display problem, not a billing one. The Console remains correct regardless.

Frequently asked.

Quick follow-ups people search after this question.

Q · 01 What's the command to see Claude Code usage? +
/usage, typed inside a running session. It shows a Session block with token statistics and, for subscribers, plan usage bars with a breakdown. Press d or w to switch between 24 hours and 7 days.
Q · 02 Is the dollar figure my actual bill? +
No. Anthropic's docs state it's computed locally from token counts at standard list rates, so it ignores promotional or contracted pricing and may differ from what you're charged. The Console's Usage page is authoritative.
Q · 03 Does it include usage from my other machine? +
No. The figures come from local session history on that machine, so work from another device or from claude.ai isn't counted. Treat each machine's panel as a partial view.
Q · 04 How do I find what's eating my limits? +
The breakdown attributes recent usage to skills, subagents, plugins and individual MCP servers, and flags long context or cache misses when either accounts for 10% or more. That's usually enough to identify the culprit in one look.