Skip to content
Agentic Cinematic Universe

What this costs to run

Every time a worker runs, one line gets written down: which model it used and how much it consumed. Nothing else is stored — no prompts, no outputs, no business figures. The money is worked out when you look at it, from a single price list, so a price change re-prices the whole history at once.

Cost so far
Unknown
Nothing measured it. That is not the same as it being cheap.
Runs recorded
0
Nothing has been logged on this machine yet.
What the meter is bound by
Reused instead of paid for
Unknown
This is the biggest lever on the bill. Until it is measured, nobody knows if it is working.
Day by day

What has been recorded

example data
Nothing recorded yet

A hook writes one line every time a worker finishes. Until it is installed on this machine, the bill is unknown rather than zero — see what needs you on the front page.

vault-schema/AI-HQ/Runs/routing.md

The meter never blocks a run. If it fails it fails quietly, because a broken cost meter that stops the org from working is worse than no cost meter at all.

The price listwhat a million tokens costs, as of 2026-06-24
ModelFresh inputReused inputOutput
haiku-4.5$1.00$0.10$5.00
sonnet-5$2.00$0.20$10.00
opus-5$5.00$0.50$25.00
opus-5-fast$10.00$1.00$50.00
fable-5$10.00$1.00$50.00

Look at the neon column: reused input on the most expensive model costs less than fresh input on the cheapest one. That is why reuse is fixed before anyone argues about which model to use. Anthropic first-party API pricing, via the bundled claude-api skill's cached model table. Re-verify at https://anthropic.com/pricing before any figure reaches a human.