Document OCR & Structured Extraction
Pricing
from $8.00 / 1,000 document ocr processeds
Document OCR & Structured Extraction
Extracts text from receipt, invoice, or scanned document images (OCR via Tesseract, no GPU required) and, optionally, structures key fields (vendor, date, total, line items) via an LLM on OpenRouter.
Pricing
from $8.00 / 1,000 document ocr processeds
Rating
0.0
(0)
Developer
Oussema Toumi
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
3 days ago
Last modified
Categories
Share
Extracts text from receipt, invoice, or scanned document images via OCR (Tesseract, 100% CPU, no GPU required), with an optional structured extraction (vendor, date, total, line items) via an LLM on OpenRouter.
Input
| Field | Type | Description |
|---|---|---|
fileUrls | array | Direct image URLs (jpg/png/webp) |
ocrLanguage | string | Tesseract language code (default: fra) |
structuredExtraction | bool | Enable structured field extraction via LLM |
documentType | string | receipt, invoice, or generic |
llmModel | string | OpenRouter model (default: anthropic/claude-3.5-haiku) |
openrouterApiKey | string | Required when structuredExtraction=true |
Output (dataset)
Each record contains: url, documentType, ocrText,
ocrConfidence, and, when enabled, structuredData (JSON: vendor, date,
total, items, etc. depending on document type).
Billing (pay-per-event)
document-ocred— $0.008 — per document successfully OCR'dstructured-extracted— $0.006 — additionally, if structured extraction succeedsdocument-failed— $0 — never billed
Example: 100 invoices, OCR + structured extraction on all ≈ 100 × ($0.008 + $0.006) = $1.40 billed to the user.
Technical notes
- No GPU required: Tesseract.js runs entirely on CPU. On a small server (low RAM), processing images one at a time (already the case in this skeleton) avoids memory spikes.
- Current limitation: only accepts images (jpg/png/webp) by direct URL.
Scanned PDFs must be converted to images upstream (e.g. with a dedicated
Apify PDF→image Actor, or by adding
pdf-poppler/pdf2pic— requires additional system dependencies in the Dockerfile, deliberately omitted here to stay lightweight). - Structured extraction is optional and billed only when enabled: a user who just wants raw text only pays for the OCR.
