Skip to main content

Spend estimates

Before you run a workflow, Nomic shows a spend estimate — a dollar range with a short explanation — on the workflow builder, the run kickoff screen, and Nomic workflow rows. It forecasts what a run will deduct from your AI Usage pool. It is guidance, not a quote: your actual bill is always the sum of the spend events a run records.

What shapes an estimate​

Two things drive every estimate:

  • The size of your input. Cost grows with input size, but not always in step with it — some workflows stay nearly flat as inputs grow, while others climb steadily with each added page.
  • What past runs actually cost. As a workflow accumulates runs, its estimate leans more on its own real run costs and less on reference figures, so it grows more accurate the more you use it.

Checked against our internal run data, the estimated range contains the actual cost for the large majority of runs, so you can treat the band as a realistic spread rather than a guess.

How to read an estimate​

  • It's a range, not a point. The band is the typical spread of outcomes for a run of that size — most runs land inside it; a few won't.
  • The number tracks your input size. Select your files and the estimate re-computes for that exact page count. With nothing selected, it shows a typical run for the workflow.
  • Hover for the details. The tooltip tells you the size the range applies to (a page count, or "per run" when cost doesn't scale with size) and what the figure is based on — a rough estimate from default rates when the workflow has no runs yet, or one learned from this workflow's own past runs once it does. It grows more accurate the more the workflow runs.

How to operationalize it​

  • Sanity-check before large runs. Multiply the per-run estimate by how many runs you plan; if a 300-sheet review or a big batch looks expensive, scope it down or pilot on a subset first.
  • Pilot to calibrate. Run a workflow on a few representative inputs. After those runs, the estimate stops leaning on default rates and starts reflecting what your team actually spends.
  • Reconcile against actuals. The estimate forecasts; Admin → Usage and Settings → Usage record what each run truly cost. Use those to confirm the estimate and to set budgets.
  • Lower the estimate by scoping the input. Fewer or smaller files move the range down; see Overview for more ways to stretch your AI Usage.

Where to next​

  • Overview — How AI usage is billed and how far a typical allocation goes.
  • Models — Token pricing that underlies every run's cost.
  • Indexing — Per-page parse pricing, which seeds the reference figures.