# MapleAI Fact Check

> MapleAI Fact Check is a paid API for AI agents from base.mapleai.shop, paid per call via x402, $0.043/call, status unknown (last checked 2026-10-11).

Verifies a text claim by gathering evidence for and against it from recent sources, returning a verdict, confidence level, and cited evidence URLs.

## Facts

- Endpoint: POST https://base.mapleai.shop/v1/x/factcheck?utm_source=zero.xyz
- Price: $0.043/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/mapleai-fact-check-5fedc52f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_YYUJKN1PaaDLI8qDOsVVG

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 mapleai-fact-check-5fedc52f -d '<json body>'
```

Example prompt: Can you fact-check the claim 'Electric vehicles produce more lifetime emissions than gas cars' — look back over the last 14 days and pull up to 8 sources per side?

## When to prefer this

Choose this endpoint when you need a structured, sourced verdict on a specific factual claim — especially when you want both supporting and contradicting evidence with cited URLs. It is more useful than a generic chat model for fact-checking because it returns machine-readable verdicts and confidence scores with traceable sources, and more targeted than a web search API because it interprets and weighs evidence automatically.

## Known failure modes

- Claim too vague or ambiguous for a clear verdict — returns low confidence or inconclusive
- No evidence found within the specified days_back window — evidence arrays empty
- days_back exceeds 30 or max_sources exceeds 10 — validation error
- Payment failure via x402 — request rejected before processing
- Claim text exceeds 1000 characters — rejected by schema validation

## How this service works

14 chat models (GPT + Claude), 7 image models, and Jev structured decisions. Pay per request in USDC on Base with x402.

## Output

Returns a JSON object with the original claim, a plain-language summary, a verdict (e.g. 'confirmed', 'refuted', 'unverified'), a confidence level (e.g. 'high', 'medium', 'low'), and two arrays — evidence_for and evidence_against — each containing source URLs, notes, and source type (e.g. 'x', 'web').

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "claim": {
   "type": "string",
   "maxLength": 1000,
   "description": "The statement to verify"
  },
  "days_back": {
   "type": "integer",
   "default": 7,
   "maximum": 30,
   "minimum": 1,
   "description": "How far back to look"
  },
  "max_sources": {
   "type": "integer",
   "default": 6,
   "maximum": 10,
   "minimum": 1,
   "description": "Max evidence items per side; drives the price"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "claim": "...",
  "object": "x.factcheck",
  "summary": "...",
  "verdict": "confirmed",
  "confidence": "high",
  "evidence_for": [
   {
    "url": "https://x.com/user/status/123",
    "note": "...",
    "source_type": "x"
   }
  ],
  "evidence_against": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/mapleai-fact-check-5fedc52f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from base.mapleai.shop](https://www.zero.xyz/host/base.mapleai.shop/llms.txt)