* * * PENNYOCR × N8N * * *

OCR in n8n Workflows.

No community node needed: PennyOCR is one HTTP Request node. POST the binary from any trigger — email attachment, Drive upload, webhook — to https://api.pennyocr.com/v1/ocr and the next node receives clean text or markdown.

START FREE — 50 PAGES
$0.75 / 1,000 PAGES
1,333 PAGES PER DOLLAR · NO CREDIT CARD
A WORKING STARTING POINT

Import the workflow. Connect your key.

Choose one JSON template. Both start manually and read the same synthetic invoice. The file version downloads the PDF into binary field data, then submits it as multipart field file. The URL version sends a public URL with a one-page and $0.001 cost cap.

  1. Import one JSON file into a new n8n workflow.
  2. Open the PennyOCR HTTP Request node. Create or select a Header Auth credential: name Authorization, value Bearer YOUR_PENNYOCR_KEY. Keep the key in credentials, outside the workflow JSON.
  3. Run it manually. Read text, page_results and cost_usd in the response. Compare the text to the original before adding a downstream action.
  4. Replace the synthetic input with your own trigger or public document URL. Enable saving execution data only if it fits your document-retention requirements.

A 401 means check credentials; 402 means check your allowance or buy credits; 413 means reduce size or adjust the cap; 429 means wait before a deliberate retry. The templates stop on HTTP errors and have automatic retries disabled. They do not send extracted text to another app, run on a schedule or contain a live API key.

Both templates passed import and execution tests in n8n 2.44.4 with a local HTTP fixture, including 401, 402 and 429 error stops. Live PennyOCR account credentials were not used. Read the test details, then connect your credential and test your documents in your n8n instance.

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 NODE CONFIG.

HTTP REQUEST NODE
Method POST · URL https://api.pennyocr.com/v1/ocr?format=text · Auth: Header 'Authorization: Bearer pk_live_...' · Body: form-data, field 'file' from binary.
EMAIL → SHEET
IMAP trigger → PennyOCR → parse totals → append to Google Sheets. The classic receipt pipeline, four nodes.
DRIVE → SEARCHABLE
Watch a folder, OCR every new scan, write markdown next to it or into your vector store.
ERROR BRANCHES
402 (out of credits) and 413 (too big) are deterministic — route them to a Slack alert node instead of a silent fail.
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 A DEDICATED N8N NODE?
Use the importable HTTP Request templates on this page. They require your own Header Auth credential; no dedicated community node is needed.
URLS INSTEAD OF BINARIES?
Yes — POST JSON to /v1/ocr/url with {url, format} when the file lives at a link. Same price, plus optional page ranges.
HOW DO I MONITOR SPEND?
Use GET /v1/balance with your API key to check remaining allowance and prepaid credits. The URL endpoint supports max_pages and max_cost_usd to refuse work above your caps.