Claude

Track Claude Code, Cowork, and Office agent usage from OpenTelemetry in one daily view.

StackSpend receives Claude OpenTelemetry from Claude Code, Cowork, and Office agents. See estimated daily cost, user-level attribution, model breakdowns, anomaly detection, and budget tracking alongside your other AI and cloud providers. Claude telemetry is usage-based and estimated, not an official Anthropic invoice.

Start free trial View setup guide

Read-only access·14-day free trial·No credit card required·Setup in under 5 minutes

The problem

Why Claude spend is hard to control

Claude usage can happen across developer tools, Cowork, and Office agents. Without one collector, teams cannot see where usage is coming from or which users and sessions are driving cost.

Claude OpenTelemetry includes many event types. Cost signals, token usage, tool events, and logs need normalization and deduplication before they are useful for finance or operations.

Claude sits alongside Anthropic API, OpenAI, Cursor, and cloud providers. Reviewing each source separately makes total AI spend hard to explain.

The solution

What StackSpend shows for Claude

StackSpend gives each Claude provider connection a scoped ingest key and copy-ready OpenTelemetry settings for Claude Code, Cowork, and Office agents.
Claude telemetry is normalized into daily cost rows with user, model, session, and source attribution so teams can separate Claude Code, Cowork, and Office agent usage.
Daily alerts, anomaly detection, budgets, and pace-to-forecast help teams spot unexpected Claude usage before the month closes.

Exactly what we track

Setup guide

Claude Code OpenTelemetryClaude Cowork OpenTelemetryClaude Office agents OpenTelemetryEstimated cost by modelUser and session attributionDaily spend and anomaly detection

Monitoring scope

What Claude cost monitoring covers

These are the details teams usually need when comparing native billing screens with a dedicated monitoring layer.

Tracks Claude Code, Cowork, and Office agent telemetry through OTLP ingest.

Separates estimated cost-bearing events from noisy logs and non-cost usage signals.

Uses a scoped provider ingest key rather than Anthropic API billing credentials.

Failure modes

What typically causes Claude costs to spike

A managed Claude Code rollout expands to more developers without a matching daily usage signal

Cowork or Office agent sessions start sending more Opus requests than expected

A long-running Claude session produces repeated high-cost model calls during a refactor

Telemetry includes both logs and metrics and needs deduplication before costs are trusted

Claude admin monitoring and Anthropic billing views vs StackSpend

Why teams move beyond native Claude billing

Claude admin monitoring and Anthropic billing views is built for investigation. StackSpend is built for prevention.

Claude admin monitoring and Anthropic billing views

Telemetry setup is separate from cost reporting and needs collector configuration
Raw OpenTelemetry events include noisy non-cost logs that are hard to read directly
No unified view with OpenAI, Cursor, cloud, and other AI providers
Estimated Claude tool usage is not automatically translated into daily budget signals

StackSpend

Copy-ready Claude Code managed settings and Cowork/Office OpenTelemetry fields
Normalized estimated cost rows with source tagging and deduplication
User, model, and session breakdowns in the same dashboard as other providers
Daily alerts, anomaly detection, and budget pacing for Claude usage

From day one

What you get when you connect Claude

Access model

OpenTelemetry ingest with a scoped usage:write provider key.

Visibility

Estimated cost by Claude source, user, model, and session.

Coverage

Claude Code, Cowork, and Office agents in one provider connection.

Signals

Daily alerts, anomaly detection, and budget tracking for Claude usage.

Best for

Who should use StackSpend for Claude

Product and engineering teams that need model-level visibility before AI bills surprise them.
Buyers consolidating OpenAI, Anthropic, Claude, Cursor, or open-model spend into one operating view.
Teams that need alerts and forecasting, not just retrospective usage dashboards.

Evaluation checklist

Start a trial

Open a StackSpend workspace and add Claude as a provider connection.

Copy the Claude setup

Generate the provider ingest key and paste the managed settings or OTLP fields into Claude admin.

Send a test event

Start a new Claude session, run a small task, and confirm Last Logs updates on the provider page.

Frequently asked

What Claude data does StackSpend track?

StackSpend receives Claude OpenTelemetry from Claude Code, Cowork, and Office agents. It tracks estimated cost, model, user, session, source, token signals, and recent telemetry health when those fields are present.

How do I connect Claude to StackSpend?

Create a Claude provider connection, generate the scoped provider ingest key, then paste the provided managed settings JSON into Claude Code or the OTLP endpoint and headers into Claude Cowork and Office agent monitoring.

Is Claude telemetry the same as my Anthropic invoice?

No. Claude OpenTelemetry is usage telemetry and StackSpend treats its cost fields as estimates. Final subscription coverage, credits, enterprise terms, or overage billing may differ from the telemetry estimate.

How is Claude different from the Anthropic provider?

The Anthropic provider is for Anthropic API billing. The Claude provider is for Claude Code, Cowork, and Office agents OpenTelemetry. You can use both if your team uses both Claude products and Anthropic APIs.

Connect Claude. See your spend today.

Read-only setup in under 5 minutes. 90 days of Claude cost history loaded automatically. Daily signals from day one.

Start free trial View setup guide

14-day free trial · No credit card required · Read-only access