Claim Verifier — AI-powered fact checking

Verify factual claims against live web sources and get structured, evidence-backed verdicts — not LLM vibes. The verdict is decided by deterministic evidence rules (source quality tiers + explicit verdict parsing); the LLM only writes the explanation. Out-of-scope claims (non-AI-infra) are rejected cleanly as UNVERIFIED.

Live URL probing included: claims like https://api.example.com/v1 is reachable are verified by a direct HTTP probe (deterministic, confidence 1.0).

Supported claims

Type	Example	Method
Claim verification	"OpenRouter offers Gemini 2.0 Flash free tier"	Web search + LLM synthesis
Endpoint check	"https://api.example.com/v1 is reachable"	Direct HTTP probe
Pricing / region / docs	"Anthropic API available in Indonesia"	Web search + LLM synthesis

Verdicts

TRUE · FALSE · PARTIALLY_TRUE · CHANGED · UNREACHABLE · BLOCKED · UNVERIFIED

• TRUE requires positive evidence from an official or primary (API) source; third-party-only positive evidence yields PARTIALLY_TRUE.
• Negative evidence with no counter-signal yields FALSE.
• No sources → UNVERIFIED (never a guessed verdict).

Input

{
  "claims": ["OpenRouter offers Gemini 2.0 Flash", "https://api.apify.com/v2 is reachable"],
  "mode": "standard",
  "provider": "groq",
  "llmModel": "openai/gpt-oss-20b",
  "apiKey": "YOUR_GROQ_API_KEY"
}

• mode: standard (3 searches, 5 sources) or deep (10 searches, 12 sources, more retries)
• provider: groq (recommended free tier) | openai | openrouter | custom (set customBaseUrl)
• apiKey: your own LLM API key (BYOK, stored as Apify secret). Model runs on Groq's free tier by default.
• max 20 claims per run

Output (dataset)

{
  "claim": "OpenRouter offers Gemini 2.0 Flash",
  "verdict": "PARTIALLY_TRUE",
  "confidence": 0.7,
  "explanation": "The OpenRouter website lists Gemini 2.0 Flash as an available model...",
  "sources": [{ "url": "https://openrouter.ai/google/gemini-2.0-flash-001", "type": "third_party", "supports": "API Pricing & Benchmarks" }],
  "verifiedAt": "2026-09-08T17:03:30.206Z",
  "verifyTimeMs": 1283
}

Pricing (pay-per-event)

• verify — $0.008 per claim (standard mode)
• verify-deep — $0.025 per claim (deep mode)
• apify-actor-start — $0.00005 per run

You pay for verification work; a claim rejected as out-of-scope is not charged.