Enterprise-grade document AI.
For developers, system integrators, and product vendors who need to automate document workflows. Production-grade data extraction, document analysis, and masking, accessible to startups and small solution vendors.
Three core capabilities · use any combination
OCR Data Extraction · Document Analysis · Masking. Delivered as APIs today, extensible to SDKs and embedded delivery over time.
Extraction Basic
Structured extraction from invoices, bank statements, receipts, KYC forms, contracts, payslips. Returns JSON with named fields. Production-ready accuracy.
Read more →Extraction Pro
Everything in Basic + per-field confidence scores · validation rules · guardrails. Higher accuracy on complex documents. Built for fintech, banking, insurance, and regulated workflows.
Read more →OCR Full Text
Extract text from PDFs, scans, images. Generates a searchable PDF. Multi-language.
Read more →Aadhaar Masking
UIDAI-compliant automatic Aadhaar number redaction. Layout-preserving output. India-specific capability.
Read more →Document Analysis
Rule-based intelligent analysis. NDA gap analysis, contract compliance, regulatory filing review. Custom.
Read more →Extract an invoice in 6 lines
from abscode import DocumentAI client = DocumentAI(api_key="abs_sk_...") result = client.extraction.pro( file="invoice.pdf", document_type="invoice" ) print(result.fields)
{
"invoice_number": "INV-2026-001",
"date": "2026-06-05",
"vendor": "Acme Corp Pvt Ltd",
"vendor_gstin": "27AAAAA0000A1Z5",
"total_amount": 12450.00,
"tax_amount": 1900.00,
"currency": "INR",
"line_items": [...],
"confidence": 0.97
}The same production-grade foundation
Input formats
PDF · TIFF · JPG · PNG · scanned images. Multi-page documents supported natively.
Sync + Async modes
Sync for small docs (instant response). Async with webhook callback for batch / large documents.
Pre-processing built in
Deskew, denoise, orientation correction, contrast normalization. You upload raw, we handle quality.
Multi-language
Documents in any major language. Multilingual content within the same document handled natively.
Privacy by design
Transmitted data scrambled and anonymized. Zero document retention, auto-purged after processing.
Configurable schemas
Add new document types via simple configuration. No model retraining. Static AI models, predictable, consistent.
Pay only for what you process
Per-page pricing. Top up your wallet, credit doesn't expire while account is active. Bonus on bulk top-ups.