Recommended Free Tools
For provider-confirmed API spend and rate-limit reporting, use Anthropic Console; for organization-wide automated reporting, use the Claude Code Analytics Admin API. Local CLI tools and VS Code extensions are better suited to personal history and at-a-glance quota awareness, but their cost figures may be estimates rather than billing records. A command-line interface or JSON export can be scripted, but that alone does not establish a supported CI integration.
First, know which usage meter you need
Claude Code usage can be charged to a plan pool or to an API account, depending on how you sign in. These are different meters: plan usage is subject to plan limits, while API-key usage is pay-as-you-go and billed to the relevant API account. Anthropic explains the distinction in its Claude Code plan and API billing guidance.
For API billing, Claude Code’s /cost command shows a current-session token and dollar view. It is not a substitute for historical provider reporting. A tracker that assigns API prices to token counts is showing an estimate; for subscription users, an API-equivalent amount is a comparison, not a plan invoice.
Compare the main tracking options
| Option | Best fit | Quota or rate limits | Cost data | Automation |
|---|---|---|---|---|
| ccusage | Local CLI reports across tools | Its core approach analyzes local usage files; the cited guide does not establish authoritative live Claude account quota. | Estimates from token usage and model pricing, with daily, weekly, monthly, and session views. | Structured output is documented and can be useful in scripts; a maintained CI integration is not established. |
| cctally | Local dashboard or CLI with quota-aware weekly analysis | Describes quota observations, forecasts, and alerts. | Transcript-derived totals are explicitly a lower bound, because some requests may lack usable model or token fields. | CLI reports can be scripted in principle; documented CI-provider support is not established. |
| ClaudeCodeUsage | VS Code users who want local charts and quota display | Displays Claude /usage utilization and retains observed quota and reset evidence. |
Estimates; the project says provider accounts remain the billing source of truth. | Local export and dashboard features are documented; dedicated CI support is not established. |
| Claude Code Usage Dashboard | VS Code users who want status-bar indicators and summaries | The extension listing says it requests limit data from Anthropic’s usage endpoint using a Claude Code OAuth token. | Scans local JSONL usage fields and applies API pricing; subscription amounts are API-equivalent estimates. | The listing does not document a CI integration. |
| Anthropic Console reporting | API users and teams seeking provider-side reporting | Reports blocked rate-limited requests and per-model input/output token rate-limit use. | Provider reporting includes model and period views and CSV export. | CSV export and workspace filtering support operational reporting; a CI integration is not asserted. |
| Claude Code Analytics Admin API | Organization administrators building internal analytics | Provides daily organization and user records, not a personal live quota display. | Estimated costs and token use by model. | Authenticated endpoint and pagination make automated retrieval feasible; using it in CI is an implementation choice, not a bundled integration. |
Which tracker shows rate limits or quota?
For a personal, in-editor view
ClaudeCodeUsage and Claude Code Usage Dashboard are the most directly oriented toward quota visibility inside VS Code. Their data paths differ: ClaudeCodeUsage describes local logs and observed quota information, while the Usage Dashboard listing describes a separate request to Anthropic’s usage endpoint for limit checks. Do not assume a quota indicator and a cost total come from the same source.
The Tool Desk
Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →For API rate-limit reporting
Anthropic Console is the clearest choice when you need provider-side API rate-limit information. Its reporting covers blocked requests and per-model input and output token limits, including uncached input-token use against the applicable input-token-per-minute limit. This is API reporting, not a live personal display of plan-pool usage.
How accurate are Claude Code cost trackers?
Accuracy depends on what is being counted. Local tools generally read saved session or transcript usage data and apply model pricing. That can help explain usage over time, but it is not necessarily the amount Anthropic will bill.
- cctally: Its documentation calls transcript totals a lower bound because some requests may not leave usable model or token details in transcripts.
- Claude Code Usage Dashboard: Its listing describes local processing of JSONL token fields for cost calculations. For subscription accounts, the resulting amount is API-equivalent, not a subscription charge.
- ClaudeCodeUsage: It labels cost as an estimate and identifies provider accounts as the billing source of truth.
- Anthropic Console: Use provider reporting when you need API cost data rather than a local estimate. Anthropic’s Console guide, dated March 16, 2026, says: “Note: Currently, it’s not possible to break down usage or cost by individual users.”
For organization-level user breakdowns, the separate Analytics Admin API provides daily records by user, estimated costs, and token totals by model. Anthropic says the data may be delayed by up to one hour; that is a stated freshness limit, not an average reporting delay.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Can you use a Claude Code usage tracker in CI?
There are three different levels of automation, and they should not be confused:
- Organization API: Anthropic’s Claude Code Analytics Admin API is the strongest documented programmatic route. It returns daily aggregates and supports pagination. An organization can build a scheduled job or CI workflow around it, subject to account eligibility, credentials, and its own secure secret handling. Anthropic states: “The Admin API is unavailable for individual accounts.”
- Scriptable local CLI: ccusage documents structured output, and cctally offers CLI reports. Those interfaces can be called from scripts, but the cited material does not verify a maintained CI integration, a supported CI-provider matrix, or tested artifact handling.
- Editor dashboards: ClaudeCodeUsage and Claude Code Usage Dashboard are documented as local/editor experiences; the cited material does not establish CI operation for either.
Before relying on any approach in a production pipeline, verify the current version’s authentication needs, secret handling, exit codes, data freshness, and behavior on the runner’s filesystem. A usable CLI or endpoint makes automation possible; it does not by itself mean the project officially supports CI.
Quick Recap
Which option should you choose?
- Choose ccusage or cctally for local history, session or project-level exploration, or reports you intend to script. Treat calculated costs as estimates and check each tool’s data-source caveats.
- Choose a VS Code dashboard when an in-editor status bar or quota display matters more than provider billing records. Check which fields come from local transcripts and which require an API request.
- Choose Anthropic Console for provider-side API spend and rate-limit reporting, especially when CSV exports are useful.
- Choose the Analytics Admin API when an eligible organization needs daily programmatic user and model reporting. It is not available to individual accounts.
Sources
- Anthropic: Using Claude Code with your Pro plan
- Anthropic: Claude Code usage monitoring
- Anthropic: Claude Code Analytics API
- Anthropic: Cost and Usage Reporting in the Claude Console
- ccusage project
- cctally project
- ClaudeCodeUsage project
- Claude Code Usage Dashboard listing
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.
