Book a demoStart free

What the report looks like.

Same shape every time. Your numbers, not ours.

Page one, at full size.

The entry band’s skeleton, run on a month that regenerates from a published seed. Your copy carries your own rows, hash-chained and re-derivable on /proof.

AI Spend Assessment: findings

Sample

Workspace
A mid-size workspace (synthetic sample)
Window
2026-08-01 to 2026-08-31
Requests
76,747
Metered
$3,642.58

$3,642.58 was metered across 76,747 requests in this window.

Every row names the published price list it was metered on. 4 lists priced this window; for the models in it their rates are identical, so the version stamp moved and the arithmetic did not.

The month at a glanceDaily metered spend across 31 days, split into cache read, uncached input, output. The heaviest day is 2026-08-20 at $314.43; an armed cap ended that evening and the rest of the night is refusals, which cost nothing and so are not on this chart.Cache readUncached inputOutput$0$100$200$300$400161116$314212631cap held 22:50 · 1,850 refused
Fig 1. Every figure on this plate is computed from the month, not typed.

Contents

  1. What this report coversAssembled
  2. What was measuredAssembled
  3. The month at a glanceAssembled
  4. Where the dollars went: by modelAssembled
  5. Where the dollars went: by API keyAssembled
  6. Where the dollars went: by routeAssembled
  7. How concentrated the spend isAssembled
  8. The heaviest dayAssembled
  9. What your caps didAssembled
  10. Cost per successful outputAssembled
  11. Re-derivable without trusting usAssembled
  12. What this report does not sayAssembled
  13. The two evenings, read by handBy hand
  14. Waste foundBy hand
  15. The ranked movesBy hand
Open the full document

Fifteen sections, nine figures. Print or save as PDF from there.

Sample figures throughout. A customer’s document carries their own.

The ranked moves.

Written by hand, from that evidence. Not a console surface.

Impact is modeled and net of quality, in your own dollars.

Sample

  1. 1

    Arm a daily envelope on every key that can loop

    One key had one and stopped inside its own evening. One did not and ran to the end of the wave.

    Confirm it
    §9 and §13, and the 1,850 refusals behind the 22:50 line in Fig 1.

  2. 2

    Cap the retries before the retries cap you

    A client that retries a large prompt five times bills the whole prompt five times. The cost of a failure is set by how much context is resent, not by how long the answer was.

    Confirm it
    §10, where the same key is the only one carrying failures.

  3. 3

    Watch the cache-read share like a metric, not a feeling

    A deploy reordered a prompt prefix and nothing broke, nothing alerted, and the receipts got more expensive for three weeks.

    Confirm it
    §14 and the cache series beside it.

What arrives.

  • The document

    Readable in the console while it assembles, and written straight out to a file in Markdown or HTML from the same response.

  • The ranked moves

    Written by hand from that evidence: what to change first, and what it is worth.

  • The receipts

    Every row exportable and re-derivable without us, under the published chain recipe.

  • The console it came from

    Yours to keep when the work ends, with your caps and kill-switch already armed.

Written so it can be forwarded.

See the assessment