Hardparsebeta
LoginUpload doc
Layout-aware OCR for people shipping stuff

Turn documents into Markdown + layout JSON.

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.

Good forRAG, invoices, scans, QA review
ReturnsMarkdown + layout bbox JSON
StatusPublic beta is live

Drop a file. See the boxes.

This is the actual parser, not a mockup. After parsing, inspect layout blocks, line overlays, category chips, confidence, and Markdown from the same result.

Parser

Upload one document.

Get Markdown, layout blocks, reading order, confidence, and boxes you can click. Most jobs take 30-60s; add email for a ready link.

PDF, image, or WebM · max 20 MB
SourceReady
Waiting for a document.
Result
No result yet.Upload a file to get Markdown and boxes.
01

Layout

Detects document regions, categories, confidence, and reading order before turning the page into text.

02

Bboxes

Switch between layout blocks and text-line overlays, then click any box to inspect its source.

03

Formats

PDFs, scans, screenshots, WebP, and WebM first frames run through the same live parser.

One upload endpoint.

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.

curlpythonnode
POST /v1/parse
# 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
Ship it

Need OCR inside your product?

Try the public beta first. If you need a private instance, higher limits, or integration work, email k.wikiel@gmail.com.

Email me