* * * OCR API FOR PYTHON * * *

OCR API for Python.

pip install pennyocr, three lines, and any PDF or image becomes markdown or plain text. No model downloads, no CUDA, no Tesseract compilation — the GPU is our problem.

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=@receipt.jpg"

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

THE WHOLE INTEGRATION.

INSTALL
pip install pennyocr — one dependency (httpx). Python 3.9+.
THREE LINES
from pennyocr import PennyOCR · client = PennyOCR(api_key=...) · client.ocr('invoice.pdf').text
PER-PAGE RESULTS
result.page_results gives page-by-page text for citations, chunking and pagination-aware pipelines.
OPENAI SDK WORKS TOO
Prefer the openai package? Point base_url at https://api.pennyocr.com/v1 and send image_url parts to model pennyocr-markdown.
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
SYNC OR ASYNC?
The SDK is sync (httpx). For async today, call the REST endpoint with httpx.AsyncClient — it's one multipart POST. Async SDK is coming.
HOW DO ERRORS WORK?
PennyOCRError with a status_code: 401 bad key, 402 out of credits (buy more on the dashboard), 413 too large, 422 unreadable file.
WHERE'S THE SOURCE?
The SDK is tiny and readable — one file, MIT licensed. What you POST is what runs; zero retention by default.