An AI panel debates your goal; a referee rules on re-checkable evidence
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Freemium
Pricing
Free: 5 successful runs per UTC day after email verification. Starter: $9.90/month for 30M tokens/month. Builder: $19.90/month for 80M tokens/month. Pro: $39.90/month for 200M tokens/month. Scale: $79.90/month for 500M tokens/month. Tokens refresh monthly and do not roll over. One-time token packs a
Free: $1.00 starting credit once. Credit plans from $10 top-up with no expiration. Your own key: 5% infrastructure fee after the first $5.00 of usage.
Key features
Choice decision type: select from supplied options
Score decision type: assign level on defined scale
Noul decision type: yes/no judgment against criterion
Decision flows: chain questions on canvas with branching
Batch processing for CSV, TXT, JSONL files up to 1,000 rows
Shared account balance across console, batch and API
Export results as CSV or JSONL
Failed requests are refunded
Probabilities included with all answers
Panel of up to six AI models from different vendors
Referee rules on re-checkable evidence only
Searches academic databases: arXiv, OpenAlex, Crossref, Europe PMC
Executes Python code to verify claims
Customizable acceptance standards
Matches pause and resume without losing work
Shared ledger prevents re-derivation
Spending limit per match
What makes it different
One API and console for playground, flows, batch and API access
Only questions on the executed path in flows are billed
Built on TypeSafe AI's Jev structured decision model
Test and measure decisions on your own data before production
Custom decision criteria defined by your own labels and rules
Referee decides on evidence, not argument quality
Panel from different vendors fails in different directions
JevModel
Referee.chat