Image to Text OCR API: Bulk, 27 Languages, No Google

Extract text from thousands of images in one run. Paste image URLs and get clean text, Markdown, a confidence score and word counts for each one. It uses the open-source Tesseract 5 OCR engine running inside the Actor. It does not scrape Google Lens, so it isn't hit by rate limits, captchas or sudden breakage.

• 🖼️ Formats: PNG, JPEG, multi-page TIFF, WebP, BMP and GIF. Google Drive and Dropbox share links work too
• 🌍 27 OCR languages: English, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Swedish, Danish, Norwegian, Finnish, Czech, Turkish, Russian, Ukrainian, Greek, Arabic, Hebrew, Hindi, Vietnamese, Indonesian, Thai, Chinese (Simplified and Traditional), Japanese and Korean. Mix several in one run
• 📊 Confidence score per image (0–100), so you can route low-quality scans to a human
• 💸 Pay only for images where text is found. Blank images, broken links and unsupported files are free. No start fee
• 🔒 Private: images are processed in your run's container and deleted straight away

What can I use it for?

• Digitising receipts, invoices, forms, labels and signs
• Pulling text from screenshots, memes, slides and product photos for search or moderation
• Feeding AI agents and RAG pipelines with text from images
• Bulk-indexing scanned archives (multi-page TIFF)

Input example

{
  "urls": ["https://raw.githubusercontent.com/tesseract-ocr/tessdoc/main/images/eurotext.png"],
  "ocrLanguages": ["eng", "deu"],
  "outputFormat": "both"
}

Output example

{
  "url": "https://raw.githubusercontent.com/tesseract-ocr/tessdoc/main/images/eurotext.png",
  "success": true,
  "hasText": true,
  "ocrConfidence": 89.9,
  "words": 66,
  "text": "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 <lazy> #90 dog ...",
  "markdown": "The (quick) [brown] {fox} jumps! ...",
  "durationMs": 1630
}

Pricing

$0.0015 per image with text ($1.50 per 1,000 images). Pay-per-event, no subscription and no start fee. You're charged once per image where OCR found text, however many frames a TIFF has. Set Maximum cost per run and the Actor stops cleanly at your limit.

How does the price compare?

Price for 1,000 images, including start fees for one run, from each Actor's public Apify Store pricing (checked 19 October 2026):

Actor	Per image	Start fee	1,000 images
This Actor	$0.0015	none	$1.50
keyman98/image-pdf-ocr	$0.002	$0.00005	$2.00
gochujang/image-ocr-extractor	$0.002	$0.001	$2.00
steadydata/image-ocr-text	$0.003	none	$3.00
zenomastro/image-ocr-text-extractor	$0.005	$0.001	$5.00
s-r/google-lens-ocr	$0.006	$0.005	$6.01

Use it from the API

curl -X POST "https://api.apify.com/v2/acts/poised_beardlichen~image-to-text-ocr/run-sync-get-dataset-items?token=<YOUR_APIFY_TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{"urls": ["https://raw.githubusercontent.com/tesseract-ocr/tessdoc/main/images/eurotext.png"]}'

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("poised_beardlichen/image-to-text-ocr").call(run_input={"urls": ["https://example.com/receipt.jpg"]})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item["ocrConfidence"], item["text"])

Use with AI agents (MCP)

Give Claude, Cursor or any MCP client the ability to read images through the Apify MCP server:

{ "mcpServers": { "apify": {
  "url": "https://mcp.apify.com/?tools=poised_beardlichen/image-to-text-ocr",
  "headers": { "Authorization": "Bearer <YOUR_APIFY_TOKEN>" } } } }

Tips for best results

• Pick only the languages in your images. 1–3 languages are faster and more accurate.
• Images with text at least about 20 px tall give the best results. Very small or blurry text lowers the confidence score.
• Handwriting is not well supported, because Tesseract is built for printed text.

FAQ

Is it a Google Lens scraper? No. OCR runs locally with Tesseract 5 (LSTM), so results are consistent and it doesn't break when Google changes its pages.

Can it read PDFs? Use our PDF to Text & Markdown with OCR Actor for PDFs and DOCX. It also handles scanned PDFs.

What if no text is found? You get hasText: false and are not charged.

Is there a size limit? 50 MB per image by default, adjustable up to 500 MB.

Calling it from an AI agent or a script (async pattern)

A single image usually finishes in under 20 seconds. The Apify MCP server waits only about 30–45 seconds for a run before it returns. So for batches, slow pages, or whenever a call returns before the run is done, start the run and fetch the results afterwards rather than waiting on it:

1. Start the run: POST https://api.apify.com/v2/acts/poised_beardlichen~image-to-text-ocr/runs with input such as {"url": "https://raw.githubusercontent.com/tesseract-ocr/tessdoc/main/images/eurotext.png"}. The response contains data.id (the run ID) and data.defaultDatasetId.
2. Wait for it to finish: poll GET https://api.apify.com/v2/actor-runs/<runId>?waitForFinish=60 until status is SUCCEEDED.
3. Fetch the results: GET https://api.apify.com/v2/datasets/<defaultDatasetId>/items?clean=true.

Send your token as Authorization: Bearer <APIFY_TOKEN>. Through MCP, if the call returns a run ID instead of results, use the server's run-status and dataset tools (e.g. get-actor-run, then get-dataset-items) with that ID. For small, quick jobs you can use the synchronous endpoint POST /v2/acts/poised_beardlichen~image-to-text-ocr/run-sync-get-dataset-items instead, which waits for up to 300 seconds.

Other tools by us

• PDF to Text & Markdown with OCR: PDFs, DOCX and scans to clean, LLM-ready text.
• Website Screenshot & PDF API: bulk screenshots and PDFs with cookie banners removed.
• Bulk Email Verifier & Validator: MX, disposable, role and typo checks at $0.30 per 1,000.
• Bulk PageSpeed & Lighthouse Checker: Lighthouse scores, Core Web Vitals and top fixes for many URLs on mobile and desktop, from $0.005 per audit.
• Website Screenshot & PDF for AI Agents: a lightweight copy of the screenshot tool for agents and one-off calls (no Standby). Same prices, starting at $0.0015 per screenshot.

Support

Found an image that reads poorly? Open an issue on the Issues tab with the URL.