OCR · Translation · Document AI

Read any document,
in any language.

An OCR and translation API built Arabic-first, where most OCR falls short — plus manga-aware Japanese and 13+ languages with automatic detection. Send an image, get structured text back in under a second.

واجهة برمجية للتعرّف الضوئي على النصوص — العربية أولاً

⌁ Try it now — no signup Free API keyNo email needed

Arabic-first accuracy GPU OCR, ~300ms 500 free requests/day PDPL compliant — images never stored

0.99فاتورة ضريبية مبسطة
0.97التاريخ: ٠٦ يوليو ٢٠٢٦
0.98الإجمالي: ٥٧٫٥٠ ريال سعودي

Small surface, deep capability

One key, the whole document pipeline

Every endpoint speaks JSON, returns in one round trip, and is documented in an OpenAPI spec your tools can read.

POST /v1/ocr

Extract text

Image in, text out — boxes, confidence, reading order, and a copy-ready layout that preserves the page's line structure. lang=auto detects the script.

POST /v1/document

Documents (PDF)

A whole PDF in one call — per-page OCR and optional translation, billed by actual pages. No 50k-character minimums.

POST /v1/ocr-translate

OCR + translate

Every line translated with shared context in one round trip. format=overlay returns the page with the original text erased and the translation laid over it as selectable text.

POST /v1/translate

Translate

100+ languages with business controls: formality (فصحى or casual), context, and per-key glossary — your terminology, enforced.

POST /v1/correct

Fix messy text

OCR-artifact cleanup or spelling/grammar fixes with minimal edits — line breaks preserved, nothing rephrased.

POST /v1/ask

Process with an LLM

Summarize a scanned contract, extract fields from a receipt, classify a document — one call after OCR.

Live workbench

Try every tool, no key needed

Real API, real GPU. OCR an image, translate text, or clean up messy OCR — switch tools with one click.

Drop an image here or · up to 2MB

Layout-preserving text — copy-ready

Translation

Quickstart

First request in 30 seconds

Copy, paste, run. The same key works for every endpoint.

curl -X POST https://api.auto-reader.com/v1/ocr \
  -H "Authorization: Bearer YOUR_KEY" \
  -F "file=@receipt.png" -F "lang=auto"

# → { "lang_detected": "ar", "engine": "paddle", "latency_ms": 287,
#     "text": "فاتورة ضريبية...", "layout": "copy-ready lines",
#     "blocks": [...], "request_id": "..." }

Pricing

Free to try. Prepaid or monthly to scale.

1 credit = 1 OCR page = $0.001. Translation runs on our own GPU-hosted LLM and costs 10 credits a page — still a fraction of DeepL, with the OCR included.

Free

$0 forever

500 credits/day — 500 OCR pages or 50 translated pages, daily
All endpoints, all languages
Instant trial key — no email needed (25 credits/day)
Community support

Get a free key

Credits

$2 = 1,500 credits

$2 = 1,500 · $5 = 5,000 · $20 = 22,000 (+10%) · $100 = 120,000 (+20%)
OCR page = 1 · translate/fix/ask = 5 · OCR+translate page = 10 (+1 overlay)
Credits never expire · hard cap, spend only what you loaded
OCR $1/1,000 pages — vs $1.50 (Google, Textract), $4 (Mistral)

Start free, top up later

Monthly (coming soon)

$9 /mo = 12,000 credits

Starter $9/mo = 12,000 · Business $49/mo = 80,000 credits/month
Allowance resets monthly; overflow falls back to your prepaid credits
Predictable bills for production workloads

Start free today

Per translated page (OCR included)	Free tier	Base fee	Document minimums
Auto-Reader OCR — $0.01	500 OCR pages/day	none	billed by actual pages
DeepL API — ≈ $0.0375 + base fee	500k chars/month	$5.49/mo	min 50,000 chars charged per file
Google Vision OCR — $1.50/1,000 (no translation)	1,000/month	none	—

DeepL per-page estimate assumes ~1,500 characters/page at their $25/1M characters API rate. Self-hosted on our own hardware, PDPL-compliant, your images never train anything without consent.

Machine-readable by design

Built to be found — and used — by AI agents

An agent can go from discovering this API to its first OCR call in one step — no email, no human in the loop.

⚿

Self-provisioning keys

One POST /signup — no email, no captcha — returns a working trial key. Agents onboard themselves.

📄

/llms.txt

A plain-text manifest tells any LLM exactly what we do, how to authenticate, and where the spec lives.

⚙️

OpenAPI spec

Full machine-readable spec at /openapi.json — code generators and agents build clients without reading docs.

🔌

MCP server (coming soon)

Plug mcp.auto-reader.com into Claude, Cursor or any MCP client for instant OCR + translation tools.

API playground

Fire a real keyed request from the browser. Get a key below, paste it here — the equivalent curl is generated for you.

Bring your own tools: OpenAPI spec · import it into Postman or any client generator · llms.txt for your agent

Read any document,in any language.