* * * PDF TABLE EXTRACTION API * * *
PDF Table Extraction API.
Rule-based table extractors need ruling lines and a digital PDF. A vision-language model just looks at the page: scanned, photographed or born-digital, the tables come back as markdown with the cells in the right columns and multi-line cells kept together.
START FREE — 100 PAGES
$0.75 / 1,000 PAGES
1,333 PAGES PER DOLLAR · NO CREDIT CARD
AT A GLANCE
UPDATED
- PRICE
- $0.75 per 1,000 pages ($0.00075 per page), prepaid
- FREE TIER
- First 100 pages free per account, no credit card
- FORMATS
- PDF, PNG, JPEG, WebP, TIFF
- LIMITS
- 50 MB and 500 pages per request
- OUTPUT
- JSON with markdown (tables preserved) or plain text, per page and joined
- INTERFACES
- REST API, OpenAI-compatible chat completions, MCP server
- CREDITS
- Never expire; requests stop with a 402 when the balance runs out
01 / TRY IT
ONE ENDPOINT.
POST a file, get JSON back — the extracted text, per page and joined. PDF, PNG, JPEG, WebP or TIFF.
curl https://api.pennyocr.com/v1/ocr \
-H "Authorization: Bearer $PENNYOCR_API_KEY" \
-F "file=@report.pdf"
# $0.75 per 1,000 pages, first 100 free02 / USE CASES
WHERE THE TABLES ARE.
INVOICES & POS
Line-item tables with quantities, rates, tax and amounts, ready to split into rows.
FINANCIAL REPORTS
Balance sheets, P&Ls and annual-report tables from scanned filings.
SPEC SHEETS & CATALOGS
Product tables with part numbers and dimensions, straight into your database or RAG index.
LLM CONTEXT
Markdown tables are the format LLMs read most reliably, so extracted tables can go straight into a prompt.
03 / PRICE CHECK
HALF THE PRICE OF THE BIG CLOUDS.
Per 1,000 pages, public list prices, first tier.
PENNYOCR$0.75
AWS TEXTRACT$1.50
GOOGLE CLOUD VISION$1.50
AZURE DOC INTELLIGENCE$1.50
YOU KEEP50%
DOES IT WORK ON SCANNED PDFS?
Yes. Every page is read as an image, so scans and phone photos work the same as digital PDFs — no text layer required.
HOW DO I GET THE TABLE INTO A DATAFRAME?
Split the markdown table on pipes, or pass the markdown to pandas via a small parser. Multi-line cells are joined with <br>, which you can replace with a newline or a space.
IS IT CHEAPER THAN TEXTRACT TABLES?
Much. We charge $0.75 per 1,000 pages for everything on the page, tables included; see pennyocr.com/ocr-api-pricing/ for a side-by-side.
ALSO ON THE MENU