* * * DOCUMENT OCR API * * *

Document OCR API.

Contracts, forms, letters, reports, archives — if it has words on it, one POST turns it into text. Half the price of the big-cloud document APIs, with none of the console safari.

START FREE — 50 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 50 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=@contract.pdf"

# $0.75 per 1,000 pages, first 50 free
02 / USE CASES

WHAT PEOPLE DIGITIZE.

DOCUMENT PIPELINES
Drop OCR into ingestion pipelines: file in, text out, JSON all the way down.
SEARCH & RAG
Make scanned archives searchable, or feed clean text to your embeddings and LLM pipelines.
LEGAL & COMPLIANCE
Contracts and filings become reviewable text — processed and discarded, never stored.
BACK-OFFICE AUTOMATION
Forms, faxes and mailroom scans read at $0.75 per thousand pages instead of $1.50.
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%
04 / FAIR QUESTIONS
GET YOUR API KEY →
QUESTIONS? HELLO@PENNYOCR.COM
WHAT DOCUMENT TYPES ARE SUPPORTED?
PDF, PNG, JPEG, WebP and TIFF, up to 50 MB and 500 pages per request. Multipage PDFs are billed per page.
HOW IS THIS DIFFERENT FROM TEXTRACT OR GOOGLE VISION?
Same job — document in, text out — at half the public list price, through one endpoint you can integrate before lunch.
HOW ACCURATE IS IT?
Modern vision-language models beat classic OCR on real-world documents: skew, tables, stamps, handwriting. Try your worst document free.