# Verity Claim Verification

> Verity Claim Verification is a paid API for AI agents from verity-bzw7.onrender.com, paid per call via x402, $0.35/call, status unknown (last checked 2026-09-15).

Verifies a text claim as supported, unsupported, or uncertain, returning a confidence score, reasoning, and evidence

## Facts

- Endpoint: POST https://verity-bzw7.onrender.com/verify/pro
- Price: $0.35/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verity-claim-verification-f23580c9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_lrjHaVPe90Vp419f6f7JB

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-claim-verification-f23580c9 -d '<json body>'
```

Example prompt: Can you verify this claim for me — 'The Eiffel Tower is taller than the Empire State Building' — and tell me whether it's supported or not, how confident you are, and what evidence backs the verdict?

## When to prefer this

Use Verity when an AI agent needs to programmatically fact-check a specific claim or statement, especially in pipelines where trust, accuracy, or hallucination detection matters. Prefer this over general LLM reasoning when you need a structured, paid, auditable verdict with explicit evidence and confidence rather than an inline model guess.

## Known failure modes

- Missing required 'claim' field returns a validation error
- Claim is too vague or ambiguous resulting in an 'uncertain' verdict with low confidence
- Service unavailable on render.com cold start causing timeout
- Payment failure (x402) if USDC balance is insufficient — request is rejected before processing
- Overly long or complex claim may reduce reasoning quality

## How this service works

Grounded Pro reality-check (premium synthesis).

## Output

Returns a structured verdict object containing: a verdict enum ('supported', 'unsupported', or 'uncertain'), a numeric confidence score (0–1), a reasoning string explaining the judgment, and an array of evidence strings backing the verdict.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "claim"
 ],
 "properties": {
  "claim": {
   "type": "string"
  },
  "context": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "title": "Verdict",
 "required": [
  "verdict",
  "confidence",
  "reasoning",
  "evidence"
 ],
 "properties": {
  "verdict": {
   "enum": [
    "supported",
    "unsupported",
    "uncertain"
   ],
   "type": "string",
   "title": "Verdict"
  },
  "evidence": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Evidence"
  },
  "reasoning": {
   "type": "string",
   "title": "Reasoning"
  },
  "confidence": {
   "type": "number",
   "title": "Confidence"
  }
 },
 "description": "The structured judgment an agent pays for."
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-claim-verification-f23580c9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from verity-bzw7.onrender.com](https://www.zero.xyz/host/verity-bzw7.onrender.com/llms.txt)