DOCUMENT AI · FOR EVERY TEAM

Document technology, absolute for all.

One hosted API for data extraction and document analysis, returning structured JSON you can wire straight into production. Pay-after-you-process pricing and lean processing that moves and stores less data, so startups, integrators and enterprises all run on the same foundation.

Structured JSON Pay-as-you-go Sync + async Zero data retention
CAPABILITIES, DELIVERED THROUGH APIs

Three core capabilities · use any combination

Extraction · Extraction Pro · Document Analysis. All delivered as hosted cloud REST APIs, call over HTTPS, get structured JSON back.

Need full-text OCR or Aadhaar masking? Both are available as part of our on-premise deployment, not as a cloud API — talk to sales.

Need full-text OCR at volume? It is available as part of our on-premise deployment, not as a cloud API — talk to sales.

CODE EXAMPLE

Extract an invoice in 6 lines

python
node.js
curl
from abscode import DocumentAI

client = DocumentAI(api_key="abs_sk_...")

result = client.extraction.pro(
    file="invoice.pdf",
    document_type="invoice"
)

print(result.fields)
response.json
{
  "invoice_number": { "value": "INV-2026-0017",
    "confidence": 0.99, "validation": "passed" },
  "vendor_gstin": { "value": "27AAAAA0000A1Z5",
    "confidence": 0.94, "validation": "passed",
    "check_digit": "verified" },
  "total_amount": { "value": 12450.00,
    "confidence": 0.97, "validation": "passed",
    "reconciles_with_line_items": true },
  "guardrails": { "all_passed": true, "warnings": [] }
}
EVERY API GETS

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.

PRICING

Priced per extracted page

Pay after you process: your monthly cost is the greater of your monthly minimum and what you actually processed. Pay-as-you-go has no minimum at all.

Free Trial
credits
One-time · 30 days · no card
  • 1,000 extracted pages
  • Extraction and Extraction Pro
  • No card required
Pay As You Go
per extracted page · no commitment
  • Pay only for what you process
  • A month with no usage costs nothing
  • No minimum, no lock-in
  • Credit limit of
Commit
per extracted page · monthly minimum
  • 11% below pay-as-you-go
  • 17% below pay-as-you-go
  • 13% below pay-as-you-go
  • Credit limit rises to
  • No minimum term
Commit
per extracted page · monthly minimum
  • 22% below pay-as-you-go
  • 25% below pay-as-you-go
  • 20% below pay-as-you-go
  • Credit limit rises to
  • Unlocks Document Analysis

Enterprise: Higher volume, on-premise, a purchase order, or a custom SLA — talk to us.

All prices exclude tax. In India, GST is added at the prevailing rate.

All prices exclude VAT, sales tax and any withholding tax.

Affordable to all. Our optimizations cut processing time and the amount of data moved and stored first, fewer server cycles, so the same production accuracy costs less and carries a lighter footprint. That value passes straight through to the per-page rate, whether you send a hundred pages a month or a hundred thousand.

See full pricing →
FAQ

Common questions

What can the Document AI API do?
It is a single hosted REST API that reads documents and returns structured JSON, delivering three capabilities you can use in any combination: Extraction, Extraction Pro and rule-based Document Analysis. You call it over HTTPS and wire the JSON response straight into production.
Which file formats and document types does the API accept?
It accepts PDF, TIFF, JPG, PNG and scanned images, and processes multi-page documents natively. Structured extraction is tuned for common business documents including invoices, bank statements, receipts, KYC forms, contracts and payslips, and new document types can be added through configuration rather than model retraining.
Do you do plain OCR or Aadhaar masking?
Not as a cloud API. Both are available in our on-premise deployment — get in touch and we'll talk through it.
Do you do plain OCR?
Not as a cloud API. Full-text OCR is available in our on-premise deployment — get in touch and we'll talk through it.
Does the API return structured JSON, and does it support asynchronous processing?
Yes. Every capability returns structured JSON with named fields ready for production. A synchronous mode gives an instant response for small documents, while an asynchronous mode with a webhook callback handles batch jobs and large documents.
What is the difference between Extraction and Extraction Pro?
Extraction returns structured JSON with named fields at production-ready accuracy from documents such as invoices, receipts and KYC forms. Extraction Pro adds per-field confidence scores, validation rules and guardrails for higher accuracy on complex documents, and is built for fintech, banking, insurance and other regulated workflows.
Does the API store or retain my documents after processing?
No. Documents are auto-purged after processing with zero retention, and data in transit is scrambled and anonymized. The service is designed to move and store less data while still returning the full structured JSON result.
How is the Document AI API priced?
You pay the greater of your monthly minimum and what you actually processed. One credit is one extracted page: Extraction uses 1 credit a page, Extraction Pro 2, and Document Analysis 2.5. Pay-as-you-go has no minimum at all, so a month with no usage costs nothing. Committing to a monthly minimum lowers your rate on everything you process and raises your credit limit. Nothing is bought in advance, nothing expires, and there is no overage rate. The free trial gives you 1,000 credits — 1,000 extracted pages — for 30 days with no card. See the full breakdown on /pricing/document-ai/.
THE FULL TOOLKIT

Explore the rest of the Document AI API

Take this and you also get all of these. Document Analysis is available on committed plans.

Start with 1,000 free credits

1,000 extracted pages across Extraction and Extraction Pro. No credit card. API key in your inbox in minutes.