ClawMetry

AI spend for delivery teams

Know where AI spend goes before it surprises your project budget.

Trace consumption to the sessions and models behind it. Investigate expensive runs and compare alternatives using both cost and task outcomes.

ClawMetry records what each agent session consumed, by runtime, model and session, on the machine the agent runs on. Every amount on this page says how it was calculated and what it leaves out. An estimate is never shown as a bill.

One amount, calculated in the open

This is the Top Sessions by Cost table from the released open-source dashboard. Two sessions were seeded for the screenshot; neither is customer data.

ClawMetry Usage tab, Top Sessions by Cost: a claude-sonnet-4-5 session with 1.3M tokens costing $1.88, and an acme-internal-model session with 55K tokens showing $0.00.
Product test data: two seeded sessions in clawmetry 0.12.876, Usage tab, captured September 14, 2026. The first session's file records 1,340,000 tokens and the runtime's own cost for the call. The dashboard shows it as $1.88. The Derived badge labels the Cost column as a whole; for this session the amount is the runtime's recorded figure, which equals the calculation below.

Here is how $1.88 is reached. Each token category is priced separately, because a cached read costs a tenth of a fresh input token and a naive total overstates the amount.

Token categoryTokensPublished rate, USD per 1MAmount, USD
Input200,000$3.00$0.600
Output40,000$15.00$0.600
Cache read (0.1 × input rate)1,000,000$0.30$0.300
Cache write (1.25 × input rate)100,000$3.75$0.375
Total1,340,000$1.875, shown as $1.88

The full method is in How cost is computed.

Three kinds of money, kept apart

A cost figure is only useful if you know which of these it is. ClawMetry produces the first one today.

ViewWhat it isWhere it comes fromStatus
Usage value at published ratesRecorded tokens priced at the provider's published per-token rates, or the runtime's own cost figureSession files and the pricing table on the machineAvailable
Expected contract spendThe same usage valued at your negotiated rates, with the rate version it was priced fromYour rate card, supplied by youPilot objective, not available today
Allocated actual spendAmounts from an invoice or billing export, allocated to teams and projectsYour billing records. ClawMetry does not read invoices today.Pilot objective, not available today

Two readings to avoid. A cost that a runtime or an LLM gateway reports may itself be an estimate at published rates, not a charge. And if your team uses a subscription plan, the API-equivalent value of that usage shows how much was consumed. It is not an additional bill, and the plan fee is not included in it.

What is not priced, and what is not assigned

A total that silently leaves things out is worse than no total. Look for these two gaps before you quote a number.

Teams and projects first, people last

Cost conversations start with aggregates: which team, which runtime, which model. Today ClawMetry rolls usage up by runtime, model, session and agent, and by team through runtime-to-team mappings. A per-project view with budgets is not in a released version yet; a pilot can agree how projects are identified.

Opening an individual session is for investigating an expensive run or an incident, and access to it should be limited to the people allowed to see it. ClawMetry does not rank developers. Tokens, session length and generated lines do not measure the value of a person's work, and this page does not use them that way.

Limits that act on spend are covered in Budgets and limits: alerts work on their own, and a hard limit needs model traffic routed through the local proxy.

Compare alternatives by cost per accepted task

A cheaper model or agent is not cheaper if it fails more often. When you compare two alternatives, use one number for both:

Cost per accepted task = the cost of every attempt, including failed attempts and retries, divided by the number of tasks accepted, where both alternatives are held to the same acceptance criteria.

ClawMetry supplies the cost side and the signals that an attempt went nowhere: sessions with no file changes, sessions that looped, errored or were stopped. Deciding what counts as accepted stays with your team. A saving suggested by a recommendation is a hypothesis until a comparison like this one measures it. See Reducing spend and Estimating the productivity gains from observing AI agents.

Illustrative: what token spend does to a fixed-fee margin

Illustrative arithmetic, not customer data. Every number below is an assumption chosen to show the calculation. It does not prove a saving and it does not show that agents replace anyone.

Assumption or resultPlannedIf AI usage runs over
Fixed project fee (assumption)$100,000$100,000
Delivery team and other project costs (assumption)$76,000$76,000
AI agent usage (assumption)$4,000$10,000
Project margin20%14%

For scale, with the same caveat: a four-person project whose agents use $300 to $800 of tokens a working day would use $6,000 to $16,000 over 20 working days. Whether that is a problem depends on what the fee assumed, which is why the planned figure belongs in the budget from the start.

Sample monthly cost report

Sample layout with illustrative figures. This is the shape of report a pilot sets out to produce from your own data. The team names and amounts are invented and add up; ClawMetry does not generate this report as one document today.

TeamTokensUsage value, USDNote
Platform (illustrative)41.0M$1,240.00Mapped
Payments (illustrative)28.5M$860.50Mapped
Unassigned10.1M$312.25Residual: usage not mapped to a team
Unpriced2.4MNot pricedModels with no published rate; excluded from the total
Total82.0M$2,412.75Priced usage only

Start with a bounded cost pilot

Contract valuation, billing reconciliation and project reports need your data and your rules, so they start as a pilot rather than a feature switch.

Scope and pricing are by agreement. No saving is guaranteed.

More on security, deployment and procurement is on the Enterprise page and the trust hub.