Skip to content
PennyOCR logo

PennyOCR

Extracts text from PDFs, scans and images through an OCR API that returns the text as JSON.

Free plan · From $0.75 per use

DocumentsFor developersUsage-based pricing
pennyocr.com ↗
Open pennyocr.comAlternativesSet it up for my teamIs PennyOCR yours? Claim the card →
At a glanceswept Oct 13, 2026

≈ 4visits/mo

Little sign of use · estimate, read Oct 13, 2026

  • PennyOCR4
  • #1 Coda3.6M
For
Developers integrating document OCR into applications via a single API endpoint
Price
Free plan · From $0.75 per usepricing page, read Oct 20, 2026
Company
PENNYOCR IS OPERATED BY TATSMANY LLC · Domain since 2026privacy policy · domain registered
Runs as
API
Used for
  • Extract text from invoices and receipts
  • Convert scanned PDFs and images into text
  • Read tables from skewed or handwritten scans
read off pennyocr.com on Oct 20, 2026
Worth knowingcomputed from what we read · each with its source
Pricingpricing page, read Oct 20, 2026

Free plan · From $0.75 per use

pricing page

Your datawhat they publish, each line with its page · read Oct 20, 2026

“By default we do not store your documents or their extracted text, and we never use them to train models.”

privacy policy ↗

These are PennyOCR's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.

How a program reaches itfound, not claimed · read Oct 20, 2026
  • MCP servercom.pennyocr/ocrverified in the MCP registry
  • Stateanswers, 2 toolschecked 2026-10-20
  • Address to connectmcp.pennyocr.com
  • MCP docspennyocr.com/mcpthe vendor's page ↗
  • Status pagelinked from the homepagepennyocr.com/status ↗

MCP server details →

This card as JSON, for your agent →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Documentsby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

Compare PennyOCR with

Pick up to two.

All 10 alternatives to PennyOCR →

All Documents tools →

Not it? Say what you need

beta

Three tools from the Atlas for the job you describe, each with what fits and what does not.

From people who use itnot part of the reading

No notes yet. What do you use PennyOCR for?

Sign in to leave a note
Questions this page answers
  • What is PennyOCR?

    Extracts text from PDFs, scans and images through an OCR API that returns the text as JSON. It is listed in the Atlas under Documents and made by PENNYOCR IS OPERATED BY TATSMANY LLC.

  • Who is PennyOCR for?

    Developers integrating document OCR into applications via a single API endpoint

  • How much does PennyOCR cost?

    PennyOCR has a free plan; paid plans start at $0.75 per use, per its pricing page on 2026-10-20.

  • Is PennyOCR free?

    Yes, PennyOCR has a free plan, per its pricing page on 2026-10-20.

  • Do people use PennyOCR?

    Little sign of use: ≈ 4 visits/mo · estimate, 2026-10.

  • Who owns PennyOCR?

    PennyOCR is run by PENNYOCR IS OPERATED BY TATSMANY LLC, per its privacy policy (2026-10-20).

  • Does PennyOCR train AI on your data?

    No, per its privacy policy (2026-10-20): “By default we do not store your documents or their extracted text, and we never use them to train models.”

  • Is PennyOCR safe?

    We do not audit vendors. What PennyOCR publishes, read 2026-10-20: on training with your data, “By default we do not store your documents or their extracted text, and we never use them to train models.”.

  • What are alternatives to PennyOCR?

    In Documents, by use: US Global Mail, Foxit PDF Services (MCP), Corenexis, LlamaIndex, Conversion Tools, Redactable.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.

How we read every tool → · By INITE Atlas Desk