DWA Open Data · data APIs on Apify
DATA · Leads & companies

Image OCR: Extract Text from Images, Screenshots & PDFs

Image OCR in bulk: extract text from image and PDF URLs, with per-line boxes and confidence. Screenshots, receipts, scans, scanned PDFs. No API key, no proxy.

Who it is for

Sales, growth and RevOps teams building prospect lists, and agencies feeding a CRM with fresh, structured company data.

Pricing

EventPricePer 1,000
Image or page OCRedCharged once per image or scanned PDF page that was read with OCR. Files that fail to download or decode are not charged.--
PDF text-layer pageCharged once per PDF page whose text could be copied directly without OCR.--
Actor StartCharged when the Actor starts running. Number of events charged depends on Actor memory (one event per GB, minimum one event).$0.00005-

Prices are read live from the Apify listing at build time. Apify platform usage is included in event prices.

Input

  • fileUrls · Image or PDF URLs: Public links to images (PNG, JPEG, WEBP, GIF, BMP, TIFF) or PDFs, one per line. Links to files in an Apify key-value store work too. The prefilled list is 26 small receipts, invoices and notes as a ready-to-run test.
  • outputFormat · Output: Plain text is the whole page as one string. Lines gives every text line with its box corners and confidence.
  • maxPagesPerPdf · Max pages per PDF: Only the first pages of long PDFs are read. Each page is one row and one charge.
  • maxFiles · Max files: Stops after this many files.

Use it from an AI agent (MCP)

Add this server URL to Claude, Cursor, VS Code or any MCP client. Authenticate with your Apify account.

https://mcp.apify.com/?tools=transparent_meteorite/image-ocr-text-extractor

FAQ

How do I run Image OCR: Extract Text from Images, Screenshots & PDFs?

Open it on Apify, fill in the input form, and press Start. You can also call it from the Apify API, a schedule, or an AI agent via MCP. Results land in a dataset you can download as JSON, CSV or Excel.

How is it billed?

Pay-per-event on Apify: you are charged only for the events listed in the price table above, plus nothing else from this listing. There is no subscription.

Where does the data come from?

Only publicly available sources. The Actor does not log in to any account or bypass access controls.

Can I use it from an AI assistant?

Yes. Add the MCP URL shown above to any MCP-capable client (Claude, Cursor, VS Code and others) and the Actor becomes a callable tool.