AI inference cost simulator
Explore worked analyses of real AI products, or model your own: build it by hand or paste it in from your AI coding assistant. Set any input as fixed or simulated, then read the probability that your inference cost stays below a level you set.
SummaryYour product’s inference calls cost between $0.178 and $0.277 per report 80% of the time (median $0.225).
Set your offer pricing to read cost as a share of revenue against the 20% margin benchmark. Tap on 🔮 to add an input to a what-if scenario to explore ways to optimize your cost or margin.
Percentage of 2,000 draws falling below/above unit cost
Probability % margin of error is ±1.1 pts due to sampling error.
| task | $ per report | % of cost | Ktok |
|---|---|---|---|
| research report (basic flow) | $0.19 | 100% | 13.7 |
Impact of calibrating a variable to its typical value
each step: the same 2,000 draws re-run with that variable and every one before it held at its typical; to pin a variable down, measure it, test it, or cap it
| task | frequency | calls | simulated |
|---|---|---|---|
| research report (basic flow) | 1 run per report | 3 calls per run · frontier ×1 · workhorse ×2 |
Variables are sampled independently (no correlation between them) with a fixed seed; the base and what-if curves see the same samples, so their differences are the decision's effect alone.