* * * OCR FOR AGENTS * * *

OCR Built for AI Agents.

Agents don't read dashboards — they need tools that state their price, enforce their caps, and fail with errors they can recover from. PennyOCR ships a remote MCP server (mcp.pennyocr.com), a free cost estimator, hard max_pages/max_cost_usd guards, prepaid credits that bound worst-case spend, and a signup flow documented for non-humans at /llms.txt.

START FREE — 100 PAGES
$0.75 / 1,000 PAGES
1,333 PAGES PER DOLLAR · NO CREDIT CARD
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=@report.pdf"

# $0.75 per 1,000 pages, first 100 free
02 / USE CASES

AGENT-NATIVE BY DESIGN.

MCP SERVER
Add {"url": "https://mcp.pennyocr.com"} to mcpServers and your agent sees read_document and estimate_cost. Works with Claude, OpenAI Agents SDK, Cloudflare Agents.
COST BEFORE COMMIT
estimate_cost is free and exact: '200 pages, $0.15'. The agent can reason about spend before spending.
HARD CAPS
max_pages and max_cost_usd refuse deterministically — with the numbers — before any GPU work. A looping agent stops at your prepaid balance, never your card limit.
RECOVERABLE ERRORS
401/402/413/422 with machine-readable detail strings that say exactly what to change. No mystery 500s to retry into.
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
HELLO@PENNYOCR.COM
HOW DOES AN AGENT GET A KEY?
The whole flow is REST and documented at pennyocr.com/llms.txt: request an email code, verify it, mint a key, optionally buy credits via a Stripe checkout URL a human completes.
IS THERE AN OPENAI-COMPATIBLE ENDPOINT?
Yes — POST /v1/chat/completions with image_url parts, model pennyocr-markdown or pennyocr-text. Any OpenAI SDK works by changing base_url.
WHAT ABOUT GIANT PDFS?
Page ranges today (pages: '1-20'), up to 500 pages per request. Async jobs with webhooks are on the roadmap.