83trust / 100

Fact Check Deep

by x402.asterpay.io in Other

x402 APIPassing, checked 3 h ago

Deep fact-check with claim decomposition. Breaks compound claims into sub-claims (max 5), verifies each against source. Deterministic overall verdict.

POST https://x402.asterpay.io/v2/x402/ai/fact-check/deep

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
197 ms typical, 197 ms slowest 5%
Last check
3 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://x402.asterpay.io/v2/x402/ai/fact-check/deep" \
  -H "content-type: application/json" \
  -d '{"claim":"Tesla produced 1.8M vehicles in 2023 and grew 35% YoY.","source":"Tesla annual report excerpt..."}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.03:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fx402.asterpay.io%2Fv2%2Fx402%2Fai%2Ffact-check%2Fdeep
const res = await pay("https://x402.asterpay.io/v2/x402/ai/fact-check/deep", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"claim":"Tesla produced 1.8M vehicles in 2023 and grew 35% YoY.","source":"Tesla annual report excerpt..."}),
});
console.log(await res.json());

Example input

{
  "claim": "Tesla produced 1.8M vehicles in 2023 and grew 35% YoY.",
  "source": "Tesla annual report excerpt..."
}

Example output

{
  "claims": [
    {
      "claim": "Tesla produced 1.8M vehicles in 2023",
      "confidence": 0.95,
      "evidence": "Source confirms 1,845,985 vehicles.",
      "verdict": "supported"
    },
    {
      "claim": "Grew 35% YoY",
      "confidence": 0.9,
      "evidence": "Source indicates 38% growth.",
      "verdict": "contradicted"
    }
  ],
  "claims_checked": 2,
  "max_claims": 5,
  "overall_confidence": 0.85,
  "overall_verdict": "partially_supported"
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
3 h agoPassed402197 ms$0.05