Simple pricing. No subscriptions.

Yes. Purchase additional credit packs at any time. Credits never expire.

One credit = one document submission. Longer or multi-part documents may require more than one credit. Each submission includes full 7-agent debate, per-claim verdicts, and a signed certificate.

Typical documents complete in 5-10 minutes. Each analysis triggers 100-200 API calls to authoritative databases across 4 rounds of adversarial debate.

Not yet. Credit packs during launch. Enterprise customers contact sales for custom arrangements.

Buy another pack. No automatic charges, no overages.

Free tier: 1 concurrent analysis. Paid tiers: up to 3 concurrent. Enterprise: unlimited.

Credit packs are non-refundable, but unused credits never expire.

GauntletScore's verdicts are not based on what agents believe or estimate. During the tool verification phase, each agent issues direct, structured queries to authoritative databases (CourtListener, SEC EDGAR, eCFR, PubMed, and others). A claim is DEBUNKED when a database returns a record that contradicts it, or when the authoritative source returns no matching record. A claim is VERIFIED when the authoritative source confirms it. The full source citation for every tool query is preserved in the audit transcript.

The structured debate is designed to surface and resolve disagreements, but not to manufacture false consensus when the evidence is genuinely ambiguous. If agents hold opposing positions after four rounds and neither side can produce controlling external evidence, the claim is returned as INCONCLUSIVE. This is a distinct verdict, not a fallback; it tells you the claim could not be confirmed or refuted against available authoritative sources.

The Cloud Edition processes documents in memory during analysis. The original document text is not stored; only its SHA-256 hash is retained for certificate verification. Each analysis runs in an isolated subprocess whose memory is fully reclaimed on exit. For organizations that cannot send documents through any external API, the Sovereign Edition runs on your own hardware with no external network dependencies.

Our pre-registered validation study of 20 public companies caught 26 tool-verified factual errors in Phase 1: cases where an authoritative database directly contradicted a claim. The count was 27 until we ran the system on our own paper and it caught one of our own examples as a false positive. We corrected our number downward and documented the discovery. What the system does not catch: errors requiring deep domain expertise unavailable in any public database, and arguments that are logically structured but strategically misleading. We return INCONCLUSIVE rather than forcing a verdict when evidence is insufficient.

The opposite. Orchestration keeps getting absorbed into the models; verification cannot be, because independence requires staying outside the system being verified. Model cards already document frontier models silently degrading their own outputs and concealing actions. A tool cannot be the auditor of its own work. The better the models get, the more the verification layer must remain external.

Source-grounding tells you where a claim came from; it does not tell you whether the claim is true, or whether the source says what the output claims it says. Grounded tells you where it came from. Verified tells you whether it's true. GauntletScore checks each claim against the primary source and reports the verdict with the evidence.

Not yet, and we will not claim otherwise. Our current estimate of 65 to 75 genuine catches among 84 raw detections is engineering-derived. Independent human evaluation under academic oversight is in progress, and we will publish the result whichever way it comes out.