Pro run
$19 per run
- Up to 150 of your examples
- Up to 8 models plus your current one as the baseline
- Verdict with cost per successful task, retry tax, failures and payback
We'll email you the day it opens. No payment now. Privacy
Pricing
Pay per verdict. It repays itself in days.
A run is a decision, not a subscription: a named model, its cost per successful task and the failures it will have, measured on your examples. On the public Banking customer-message intent classification (77 intents) run, a $19 verdict repays in 3.1 days on a $200 monthly bill.
Choose a run
Join the waitlist for the one you want. We'll email you the day it opens.
Deep run
$49 per run
- Up to 300 of your examples
- Up to 15 models plus your current one
- 3 re-checks within 30 days when prices or models move
We'll email you the day it opens. No payment now. Privacy
Model watch
$9 per month
- Your finalists re-checked when OpenRouter prices or models change
- A dated change list: who got cheaper, who now clears your bar
- Cached results reused, so only new or repriced cells run
We'll email you the day it opens. No payment now. Privacy
What every verdict contains
- The cheapest model that matches your current one on your tasks, in a paired comparison with a stated margin.
- Cost per successful task with the retry tax shown separately.
- Pass rate with a 95% interval, p50 and p95 latency per model.
- The failure examples, ready to read.
- A payback table and a script that re-runs it with your own key.
Model spend runs on your own OpenRouter key. The key is used for the run and never stored.