Introduction to DocuRift
Learn about DocuRift's AI-powered OCR for shipping and logistics documents
DocuRift is an AI Vision LLM-powered OCR API designed specifically for shipping and logistics documents. Extract structured data from complex documents with 95%+ accuracy in seconds.
What is DocuRift?
DocuRift uses advanced AI vision models to understand and extract information from shipping documents. Unlike traditional OCR that only reads text, DocuRift understands context, layout, and relationships between data fields.
Key capabilities:
- Process 10+ document types (invoices, bills of lading, packing lists, etc.)
- Extract structured JSON from unstructured PDFs and images
- 95%+ accuracy on real-world logistics documents
- Async processing for large document batches
- RESTful API with simple integration
Supported Document Types
DocuRift specializes in shipping and logistics documents:
- Commercial Invoice - Extract line items, totals, parties
- Bill of Lading - Cargo details, container numbers, routing
- Packing List - Item-level packaging information
- Delivery Order - Delivery instructions and recipient details
- Certificate of Origin - Origin declarations and product details
- Customs Declaration - HS codes, duties, values
- Freight Invoice - Shipping charges and breakdowns
- Air Waybill - Air cargo tracking and routing
- Sea Waybill - Ocean freight documentation
- Shipping Manifest - Complete shipment inventory
Use Cases
Invoice Processing
Automatically extract invoice data for accounts payable automation:
- Vendor details (name, address, tax ID)
- Line items with descriptions, quantities, prices
- Totals, taxes, payment terms
- Invoice numbers and dates
Bill of Lading Extraction
Parse complex BOL documents for supply chain tracking:
- Shipper and consignee information
- Container numbers and seal numbers
- Cargo descriptions and weights
- Port of loading/discharge
Customs Clearance
Speed up customs processing with accurate data extraction:
- HS codes and product classifications
- Country of origin
- Declared values
- Duty and tax calculations
Document Digitization
Convert paper/PDF archives to searchable, structured data:
- Batch process historical documents
- Build searchable databases
- Enable data analytics on shipping history
Why DocuRift?
Speed: Process documents in 2-5 seconds, not minutes or hours
Accuracy: 95%+ accuracy on real-world documents with complex layouts
Easy Integration: RESTful API with SDKs for Python, JavaScript, and more
Cost-Effective: Pay only for pages processed. Start with 50 FREE pages (never expire)
Async Support: Handle large batches with webhook notifications
No Training Required: Pre-trained on thousands of logistics documents
Getting Started
Ready to start extracting data from your documents?
- Get your API key - Sign up and get 50 FREE pages
- Make your first API call - Process a document in < 5 minutes
- Explore the API - Full reference documentation
Pricing
Free Tier: 50 pages (never expire) - No credit card required
Pay-as-you-go:
- $0.10 per page (standard documents)
- $0.15 per page (complex multi-page documents)
- Volume discounts available for 10,000+ pages/month
What counts as a page?
- Single-page PDF = 1 page
- Multi-page PDF = number of pages in document
- Image (JPG, PNG) = 1 page