Free plan with 10,000 monthly credits; Starter at $50/month with 40,000 credits; Pro at $500/month with 400,000 credits; Enterprise with custom pricing. Additional pay-as-you-go credits available. Pricing based on a credit system where 1,000 credits equals $1.25.
Not given
Key features
Agentic OCR parsing with semantic understanding for complex document layouts
Support for 130+ file formats including PDFs, Office docs, images, and spreadsheets
Structured data extraction with schema-based, LLM-powered agents
Document classification and splitting based on natural language rules
Enterprise-grade RAG indexing and retrieval pipeline
Handwritten text parsing and structured extraction
Table and chart extraction with structured row and column relationships
Cloud SaaS or VPC deployment with flexible data residency options
Memory system with self-managing advanced memory
Isolated per-tenant instances with version rollback
Portable context server with files, notes and links
Sub-document multi-modal hybrid search
Structured data extraction from PDFs, websites and images
Autonomous agents for knowledge base automation
99.9% uptime SLA
AES-256 encryption at rest and SSL in transit
TypeScript SDK and REST API
Model-agnostic and framework-agnostic
What makes it different
4x cheaper than frontier labs, 5x more accurate than other APIs
Auto-correction loops with recursive checks that detect and fix errors automatically
Task-specific specialist agents that route content to the right expert
HIPAA, GDPR, and SOC2 compliant with enterprise-grade security
Cut token spend by up to 81% through persistent agent memory instead of full context window stuffing
State-of-the-art on two leading AI memory benchmarks
Full-stack data layer eliminating need for multiple services
Production-tested at scale powering Fabric platform
Self-improving memory that tracks relationships and resolves contradictions