If you want to track Claude Code usage, choose a tool based on what you need to measure: Anthropic’s organization dashboard or Analytics API for team reporting, OpenTelemetry for custom centralized monitoring, and local tools such as ccusage or a VS Code extension for personal history and multi-agent views. These options report different things—such as activity, tokens, estimated cost, provider spend, or subscription limits—so they are not interchangeable.
Choose a tracker by the question you need answered
| Need | Best-supported option | Key limitation |
|---|---|---|
| Organization adoption and accepted-code metrics | Anthropic Claude Code analytics dashboard | Plan and role eligibility apply; data refreshes daily, and some value measures are estimates. |
| Custom organization reports | Anthropic Analytics API | Requires organization credentials and provides daily reporting; platform availability has exceptions. |
| Centralized, customizable telemetry | OpenTelemetry export to a chosen backend | Requires setup and deliberate privacy and retention controls. |
| Personal or cross-agent history | ccusage local CLI | Analyzes local tool data; cost outputs are estimates. |
| Usage visibility inside VS Code | Claude Code Usage extension | Local observations and estimated prices are not a billing ledger or definitive quota record. |
When comparing tools, check the audience, source of data, supported agents, refresh rate and granularity, cost or quota accuracy, customization, privacy controls, and setup effort.
As an Amazon Associate I earn from qualifying purchases.
Anthropic dashboard: organization-level adoption and value
Anthropic’s Claude Code analytics dashboard is the simplest option for eligible organizations that want usage and adoption reporting without building their own pipeline. The Help Center lists Team plan Owners and Primary Owners; Enterprise Owners, Primary Owners, and Admins subject to seat requirements; and API Console Admin, Billing, and Developer roles as eligible. Individual Pro and Max accounts are not eligible for this organization analytics feature. Anthropic’s dashboard eligibility and feature details
The Usage tab includes lines accepted, suggestion acceptance rate, activity trends, and top commands. The Value tab shows estimated productivity lift, cost per commit, and estimated annual value, with formulas and adjustable assumptions. Treat those Value figures as organization-specific estimates, not universal measurements or independently established productivity benchmarks. The dashboard refreshes daily. Contribution metrics are described as public beta, require GitHub Cloud, and are unavailable to Console users.
#1 Best Overall
Anthropic Analytics API: custom organization reports
Teams that need their own reporting can use Anthropic’s GET /v1/organizations/usage_report/claude_code endpoint. It returns daily aggregated, user-level activity such as sessions, lines added and removed, commits, pull requests, tool usage, model-level tokens, and estimated cost; results support cursor pagination. Anthropic says data can lag by up to one hour. Claude Code Analytics API documentation
The endpoint requires appropriate Admin API credentials; workspace API keys do not work. It is not an individual self-service usage tracker. Anthropic’s documentation says, “The Claude Code Analytics API is not currently available” on Claude Platform on AWS, and directs AWS users to the Usage page in Claude Console. Enterprise activity for claude.ai users is handled through a separate Enterprise Analytics API and key type. See Anthropic’s API availability and access details and the Enterprise Analytics API documentation.
OpenTelemetry: flexible monitoring for teams
Claude Code can export metrics as time series, events through logs, and optionally distributed traces through OpenTelemetry. A team can send that data to its chosen observability backend and build dashboards around its own needs. Anthropic documents the export and configuration options in its Claude Code monitoring and usage guide.
Recommended Free Tools
Plan privacy settings before enabling detailed telemetry. Tool content is not included in trace spans by default, but enabling detailed tool content can expose file contents, command output, and MCP, WebFetch, or WebSearch results. Raw API-body logging can include conversation history. Review redaction, access, and retention policies before turning on these options.
Services such as telemetry.dev and Langfuse document Claude Code or coding-agent telemetry use cases. Their own feature descriptions establish what they say they support, not an independent ranking of quality or performance.
Local reports: ccusage and a VS Code extension
ccusage for local, cross-agent history
ccusage is a local CLI that reads coding-agent CLI data and generates daily, weekly, monthly, and session reports. Its listed coverage includes Claude Code, Codex, OpenCode, Amp, Gemini CLI, GitHub Copilot CLI, and other tools. It suits questions such as “How much am I actually using each coding CLI?” or “Which conversations are the most expensive?” Its reports analyze local data, and its cost figures are estimates rather than authoritative subscription allowances or provider bills.
Rank #4
Claude Code Usage for an editor view
The Claude Code Usage VS Code extension documents local usage views for Claude Code and OpenAI Codex. It distinguishes official usage or quota observations from estimated API-equivalent prices. Use it as a convenient editor view, not as a definitive billing record; the provider account remains the source of truth for billing.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Know whether you are tracking spend, tokens, or quota
“How much did Claude Code cost me?” can mean actual API charges, an estimate of what local token use would cost at API prices, subscription-plan usage, or remaining quota. A useful tracker should make clear which of those it displays.
Best Value
Metering depends on how Claude Code is signed in. With a subscription seat, usage draws on included plan usage and may reach a plan limit. With an API key, usage is pay-as-you-go and charged to the relevant Console or cloud account. For API-key sessions, Claude Code’s /cost command shows running session spend; Anthropic also points users to the Console or cloud-provider dashboard for spend information. Anthropic’s guidance on Claude Code metering
Accordingly, treat local API-equivalent prices as estimates, provider-reported charges as billing data, and subscription usage or quota as a separate measure. A token total alone does not establish either an API bill or remaining subscription allowance.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
The Tool Desk
Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →
