Layout
Detects document regions, categories, confidence, and reading order before turning the page into text.
Upload a PDF, screenshot, scan, or WebM. Hardparse detects regions, read order, confidence, and source boxes, then returns clean Markdown.
$1 OCR credit after email verification. Then $0.005/page. 20MB files.
This is the actual parser, not a mockup. After parsing, inspect layout blocks, line overlays, category chips, confidence, and Markdown from the same result.
Get Markdown, layout blocks, reading order, confidence, and boxes you can click. Most jobs take 30-60s; add email for a ready link.
Detects document regions, categories, confidence, and reading order before turning the page into text.
Switch between layout blocks and text-line overlays, then click any box to inspect its source.
PDFs, scans, screenshots, WebP, and WebM first frames run through the same live parser.
The public beta verifies uploads by email and starts accounts with $1 OCR credit. For higher volume or private deployments, email k.wikiel@gmail.com.
# Public beta: no key required for low-volume testing curl https://hardparse.com/v1/parse \ -F file=@document.pdf \ -o result.json jq '.markdown' result.json jq '.pages[0].regions[0].box' result.json
Try the public beta first. If you need a private instance, higher limits, or integration work, email k.wikiel@gmail.com.