Turn any document into clean structured data with one API call
PDFs, scans, and images in — JSON out. Five hosted REST APIs for OCR, PII masking, structured extraction, and rule-based document analysis. Priced per page, no monthly commitment.
Five production APIs
Pick the endpoint that fits the job. Every API takes the same inputs and returns the same structured JSON shape.
OCR Full-Text
Full text extraction plus a searchable PDF. Auto-deskew and orientation correction; multi-language including Hindi, Tamil, Telugu, and Arabic. Rs 0.25 /page
Details →PII Masking
Redact Aadhaar, PAN, account numbers, names, addresses, phone, and signatures with configurable rules. Output preserves the original layout. Rs 0.25 /page
Details →Extract Basic
Structured extraction from invoices, bank statements, receipts, KYC forms, and contracts. Returns JSON with named fields and bounding boxes. Rs 0.90 /page
Details →Extract Pro
Everything in Basic plus confidence scores, guardrails, and validation rules. Higher accuracy on complex docs; built for fintech and regulated workflows. Rs 1.40 /page
Details →Document Analysis
Rule-based intelligent analysis: NDA gap analysis, contract compliance review, policy adherence, and regulatory filing validation. Configured to your documents. Custom
Details →Compare every API
See inputs, outputs, accuracy modes, and per-page rates side by side, then choose the right endpoint for your pipeline.
All APIs →How it works
From sign-up to production in four steps. No infrastructure to provision.
Included in every API
One consistent contract across all five endpoints, so you build the integration once.
Structured JSON output
Every response is structured JSON with extracted data, confidence scores, and bounding boxes for each field.
Sync + async webhook
Process small documents synchronously, or run larger jobs asynchronously with a webhook callback on completion.
Pre-processing built in
Deskew, denoise, orientation correction, and contrast normalization run automatically before extraction.
Secure by default
TLS 1.3 in transit, AES-256 at rest, and documents auto-purged after processing. We do not train models on your data.
SDKs for every stack
First-party SDKs for Python, Node, Java, .NET, and PHP, plus copy-paste cURL examples in the docs.
99.5% uptime SLA
A 99.5% uptime SLA with a p95 latency target under 8 seconds for a 10-page document.
Enterprise quality. Startup pricing. Global reach.
Built for teams that need accurate document processing without enterprise contracts or lock-in.
Flat per-page pricing
A single per-page rate per API. No monthly commitment, no surge pricing, no tiered overages.
Multi-language
OCR across Indian scripts including Hindi, Tamil, and Telugu, plus Arabic and Latin text.
Private by design
Documents are auto-purged after processing and never used to train models. Your data stays yours.
Regional hosting
India processing on GCP Mumbai, and Africa processing on Johannesburg for AF and ME customers.
Built for document-heavy workflows
From KYC onboarding to invoice processing and contract review.
Fintech & KYC
Read Aadhaar, PAN, and KYC forms, then mask PII before storage. Pair Extract Pro with PII Masking for regulated onboarding.
Explore →Lending & NBFC
Parse bank statements, income proofs, and application forms into structured JSON to speed up loan decisioning.
Explore →Accounts Payable
Extract line items, totals, and tax fields from invoices and receipts with confidence scores for straight-through processing.
Explore →Legal & Contracts
Run NDA gap analysis, contract compliance review, and policy adherence checks with rule-based Document Analysis.
Explore →Common questions
Everything you need before your first API call.