* * * PENNYOCR × LANGCHAIN * * *

PennyOCR with LangChain.

LangChain's stock PDF loaders read text layers — scans and photos come back empty. Wrap PennyOCR in a loader and every document becomes markdown Documents with page metadata: pip install pennyocr langchain, then a ten-line custom loader (below) — an official langchain-pennyocr package is on the roadmap.

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=@scan.pdf"

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

THE TEN-LINE LOADER.

THE CODE
from pennyocr import PennyOCR · docs = [Document(page_content=p.text, metadata={"page": p.page, "source": path}) for p in PennyOCR().ocr(path).page_results]
WHY MARKDOWN IN
MarkdownHeaderTextSplitter chunks along real document structure — retrieval quality follows.
PAGE METADATA
Each Document carries its page number, so retrieved chunks cite real pages in the final answer.
MIXED CORPORA
One loader for born-digital PDFs, scans and photos — no branching on 'does this have a text layer'.
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
IS THERE AN OFFICIAL LANGCHAIN INTEGRATION?
Not yet — the loader above is 10 lines and works today. An official langchain-pennyocr package (and a LlamaIndex reader) is on the roadmap; email hello@pennyocr.com to nudge priority.
WHAT ABOUT LANGCHAIN AGENTS?
Point them at our MCP server (mcp.pennyocr.com) or wrap client.ocr as a @tool — the response includes cost_usd for budget-aware agents.
COST FOR A TYPICAL RAG INGEST?
A 10,000-page corpus is $7.50, once. The first 50 pages are free to prototype with.