# Verity Suite Citation Endpoint

> Verity Suite Citation Endpoint is a paid API for AI agents from suite.veritylayer.dev, paid per call via x402, $0.25/call, status unknown (last checked 2026-09-14).

Finds and returns calibrated supporting citations for a factual statement, with a signed verdict on how strongly the sources establish the claim.

## Facts

- Endpoint: POST https://suite.veritylayer.dev/cite
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verity-suite-citation-endpoint-e3e2a7f6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_5ozb2W3FCwbWlXze-XReN

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability verity-suite-citation-endpoint-e3e2a7f6 -d '<json body>'
```

Example prompt: Can you find supporting citations for the claim 'regular aerobic exercise reduces the risk of type 2 diabetes by up to 50%' — focus on clinical sources — and tell me how strongly the evidence actually backs it up?

## When to prefer this

Use this endpoint when an AI agent needs to ground a specific factual claim in real, verifiable sources before presenting it to a user or publishing it — especially when auditability matters (the signed receipt provides cryptographic proof of the result). Prefer this over generic search when you need a calibrated support score, structured citation objects, and explicit reasons why sources were accepted or rejected. The domain_hint parameter makes it particularly strong for domain-specific fact-checking (clinical, legal, financial). The fail-closed design means you get an honest 'not supported' rather than hallucinated references.

## Known failure modes

- Statement too vague or broad to retrieve relevant sources — low support score with explanatory reasons
- Domain hint narrows search too aggressively, excluding valid sources — partial support returned
- No credible sources found — verdict returns not_supported with support score near 0
- Statement is contradicted by retrieved sources — verdict returns contradicted with reasons
- Signing not configured — receipt field returns null
- Statement exceeds 2000-character limit — request rejected with validation error
- Network or upstream search failure — fail-closed behavior, error returned rather than hallucinated citations

## How this service works

The trust fabric for AI agents — calibrated, fail-closed services agents pay per call.

## Output

Returns a verdict (supported, partially_supported, not_supported, or contradicted), a calibrated support score from 0 to 1, a list of citation objects, concrete reasons for the verdict (including why any candidate sources were rejected), optional caveats about coverage or recency, and an optional Ed25519-signed VerityLayer receipt for auditability.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "statement": {
   "type": "string",
   "title": "Statement",
   "maxLength": 2000,
   "minLength": 1,
   "description": "the factual claim to find supporting sources for"
  },
  "domain_hint": {
   "anyOf": [
    {
     "type": "string",
     "maxLength": 2000
    },
    {
     "type": "null"
    }
   ],
   "title": "Domain Hint",
   "default": null,
   "description": "optional topic/field to focus the search (e.g. 'clinical', 'tax law')"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-suite-citation-endpoint-e3e2a7f6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from suite.veritylayer.dev](https://www.zero.xyz/host/suite.veritylayer.dev/llms.txt)