Per the official Claude API release notes, on Oct 29 Anthropic launched the Usage and Cost Analytics API in beta, with two endpoints, /v1/organizations/analytics/usage and /analytics/cost, that filter and group token usage and cost by model, workspace, API key, and the user or service account behind each request, with 1-minute, 1-hour, or 1-day buckets. The older Usage and Cost API is now legacy but still supported. On Oct 28 the maximum request size for the Messages and Token Counting APIs on the first-party Claude API rose from 32 MB to 128 MB.

Key Takeaways

  • ✓The new API needs the analytics-usage-cost-2026-08-24 beta header; one endpoint returns token and request counts, the other cost in USD (per the official docs)
  • ✓group_by takes up to 5 dimensions, time buckets can be 1m, 1h, or 1d, and each filter accepts up to 100 values
  • ✓Claude Console and Claude Enterprise organizations share the same endpoints and fields; it also works on Claude Platform on AWS and Claude Models on Google Cloud (Anthropic managed)
  • ✓The old Usage and Cost API and four Enterprise Analytics usage and cost report endpoints are now legacy but still supported, with migration guides
  • ✓Since Oct 28 the Messages and Token Counting APIs accept requests up to 128 MB instead of 32 MB (4x), on the first-party Claude API only
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

🔬

In-Depth Technical Analysis

Background and pain point

Once teams wire Claude into products, internal tools, and agents, the usual question is where the money goes: which API key, workspace, or service account uses the most, and how that changes by day or hour. The older Usage and Cost API and the Enterprise usage reports had limited dimensions, and Console and Enterprise organizations had to integrate separately. Request size was another pain point: requests carrying many images, PDFs, or long context could exceed the 32 MB cap.

What changed and how it works

Per the official release notes, the Usage and Cost Analytics API launched in beta on Oct 29 with the analytics-usage-cost-2026-08-24 beta header. It has two endpoints: /v1/organizations/analytics/usage returns token and request counts, and /v1/organizations/analytics/cost returns cost in USD. According to the docs you can filter and group by model, workspace, API key, service tier, and the actor behind each request, with up to five group_by dimensions; time buckets can be 1 minute, 1 hour, or 1 day, and results are ranked by the chosen metric so top consumers come first. The cost endpoint can also split by cost type and token type. Console organizations use an Admin API key or an OAuth token with the org:admin scope, and Enterprise organizations use a key with the read:analytics scope. The old endpoints are now legacy but still supported. On Oct 28 the maximum request size for the Messages and Token Counting APIs on the first-party Claude API rose from 32 MB to 128 MB.

Benchmarks

This is a platform and billing tooling update, not a model release, so there are no benchmarks. Anthropic has not published data latency or how far back history goes.

How to use it

For an internal cost dashboard, the official SDK's client.beta.organization.analytics.usage.list can pull daily, per-model data, and the SDK adds the beta header and paginates for you. Give the collector its own Admin key and rotate it, or follow the docs and use Workload Identity Federation for short-lived tokens. Integrations built on usage_report or cost_report can follow the official migration guides. Apps that send many images or documents in one call can now go up to 128 MB on the first-party API; check the docs separately for cloud provider limits.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

Up NextClaude API ships version 2026-10-21, its first since 2023: sampling parameters removed, new major SDKs across languages
Read Now→