# AxonGate Claim Verification

> AxonGate Claim Verification is a paid API for AI agents from api.axongate.one, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-30).

Fact-checks a single claim against live web sources or supplied URLs, returning a verdict, confidence score, and verbatim supporting/contradicting quotes.

## Facts

- Endpoint: POST https://api.axongate.one/v1/verify?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/axongate-claim-verification-f8f6360b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WhKPQAx_LJOOHgTK14_aR

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 axongate-claim-verification-f8f6360b -d '<json body>'
```

Example prompt: Can you fact-check this claim for me: 'The Eiffel Tower is taller than the Empire State Building' — search up to 4 live web sources and tell me if it's supported, refuted, or mixed, and give me the verbatim quotes that back it up?

## When to prefer this

Choose this endpoint when an AI agent needs to validate a specific factual claim before repeating or publishing it, especially when verbatim evidence and a structured verdict are required. Prefer it over generic web search when you need a binary or graded truth assessment with citation-level proof. It is particularly suited for journalism, research, compliance, and content moderation workflows where accountability for accuracy matters. Use it over a general Q&A endpoint when the goal is verification rather than answering a question.

## Known failure modes

- Claim is too vague or ambiguous for any source to address — verdict returns 'insufficient' with low confidence
- Supplied URLs are inaccessible, paywalled, or return errors — falls back to web search or returns insufficient
- Claim contains multiple sub-claims that conflict — may return 'mixed' even when one part is clearly true
- Live web sources have changed since the claim was made — historical claims may receive incorrect verdicts
- max_sources set to 1 may yield insufficient evidence for a reliable verdict

## How this service works

Fact-check one claim against live web sources (or URLs you supply). Returns a verdict (supported, refuted, mixed, insufficient), a confidence score and supporting or contradicting quotes that are checked verbatim against the fetched pages. Use it before an agent repeats a claim.

## Output

Returns a verdict string (one of: supported, refuted, mixed, insufficient), a confidence score between 0 and 1, and an array of verbatim quotes from the fetched pages that either support or contradict the claim, along with the source URLs they were drawn from.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "urls": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "Optional source URLs to check against instead of searching (max 5)."
  },
  "claim": {
   "type": "string",
   "description": "One factual claim to check."
  },
  "max_sources": {
   "type": "integer",
   "description": "Sources to read, 1-5 (default 4)."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/axongate-claim-verification-f8f6360b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.axongate.one](https://www.zero.xyz/host/api.axongate.one/llms.txt)