How cost accounting works

The problem: an LLM platform’s unit economics live or die on one number — what does one published article actually cost? — and that number is surprisingly hard to get. Flat per-call estimates drift from reality (here, a flat constant once under-counted the platform’s dominant cost driver by ~6×); provider dashboards aggregate by account, not by article.

Layer 1 — the immutable usage event

Every LLM call emits an immutable usage event carrying the full attribution vector: tenant, contract, record, pipeline, step, model, token counts, timestamp. Not a log line — a queryable ledger row. Nothing about cost is derived at call time; events store facts (tokens, model), and money is computed later.

Layer 2 — the versioned pricebook

Prices change; history must not. Cost is computed by joining events against a versioned pricebook — the price valid at event time — so last month’s numbers stay true after a provider reprices. The same join reconciles the computed total against the provider’s actual invoice: if the ledger and the bill diverge, something is unmetered, and that is a defect, not a rounding note.

Layer 3 — cost of one article, honestly amortized

“Cost per article” includes more than its Generate run: Collect research that fed it is amortized across the articles it enabled. This is the number the platform actually steers by — it exposed, for example, that a period of post-gate rejects multiplied the effective cost per published article several-fold even though per-call prices never moved. Without per-article attribution that regression is invisible inside a monthly total.

Layer 4 — budgets that act

Metering feeds enforcement: per-run budgets with a kill-switch through the run control channel. A runaway loop stops because the ledger says so — not because someone noticed the invoice three weeks later.

The trade-offs, honestly

Metering every call costs a write per call and a discipline: any new LLM call path must emit the event, and the reconciliation check exists precisely to catch paths that forget. Amortization rules are a modeling choice — the platform records the raw vectors so the model can be changed retroactively without losing data.

See it in two minutes

The metering domain in list_domains exposes the read surface; per-run costs appear in run reports.

Specs: SPEC-107 (usage_event + pricebook), SPEC-022/023 (budgets + kill-switch), SPEC-124 (invoice reconciliation).