An AI panel debates your goal; a referee rules on re-checkable evidence
Stage
Established
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Starter: Free (500 minutes per year, $0.15 per minute overage). Build: $149 per month (1,500 minutes per year, $0.14 per minute overage). Scale: $499 per month (7,000 minutes per year, $0.13 per minute overage). Enterprise: Custom pricing with volume-based rates and no overages.
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
Code-based agent logic (Python and TypeScript SDKs)
Integrated ASR, language and TTS in one runtime
Wideband voice codec (16 kHz)
Turn-taking and interruption handling
Real-time tuning and debugging tools
Quick deployment via CLI
Email support and SLA on Scale plan
Multi-language support for BPO
Escalation to human with full context
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
Single integrated runtime, not stitched third-party APIs
Built-in tenacity: agent retries, re-asks and escalates on failure
14-day deployment from kickoff to live call
99.9% uptime SLA across 100+ regulated deployments
Compliance certifications included on all plans at no extra cost
Referee decides on evidence, not argument quality
Panel from different vendors fails in different directions
Guava
Referee.chat