# Mart402
> Web content extraction API built for AI agents. Pay per call with x402 (USDC on Base) - no account, no API key.

## Try it free
- Sandbox with identical API on Base Sepolia (free test USDC): https://mart402.dev

## Docs
- /agents.md: How to use this service as an agent
- /catalog: Machine-readable product & pricing catalog (JSON)
- /.well-known/ai-catalog.json: Discovery index
- /stats: measured latency & success rate (last 30 days), independently verifiable at market402.com

## Products (all pay-per-call via x402, prices in /catalog)
- POST /v1/extract: URL -> Markdown + metadata. JS rendering auto. ($0.002-0.006)
- POST /v1/parse/quote -> /v1/parse: PDF -> structured Markdown. Free quote, then flat $0.005/document for text-embedded PDFs, $0.012/page for scanned OCR. Japanese-strong OCR routing. Hallucination-guarded: dual-engine consensus (VLM + traditional OCR) + calibrated confidence in every OCR result - see /ocr.
- POST /v1/ocr: single image -> text with dual-engine consensus, calibrated confidence, and per-segment corroboration. Flat $0.005/image. Japanese-strong.
- POST /v1/enrich: company name/domain/URL -> verified company profile from primary sources (official site + GLEIF LEI registry). Per-field evidence + confidence, honest nulls. Resolution failures are never charged. Flat $0.015/company.
- POST /v1/verify: invoice field verification (tax math, JP registration check-digit, accounting JSON). ($0.001)
- POST /v1/structured: fill YOUR JSON schema from any URL. Hybrid LLM + deterministic canonicalization. ($0.02)
- POST /v1/jp-company: Japanese company site -> standard profile JSON. ($0.02)