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.
Free plan at $0 USD; Pro plan at $5 USD per month.
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
Entity-graph spreading activation for cross-vocabulary retrieval
Works with any LLM model
No LLM or GPU in retrieval path
Point-in-time and windowed recall
Timestamped memories
Fixed recall cost as memory grows
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
Reaches answers across unrelated documents that share no keywords, where vector search scores zero
Deterministic retrieval with no model in the path, so results never vary between queries
Constant per-query cost regardless of memory size, even at 32,000 words
No infrastructure to run—no vector database, cluster, or GPU needed
Works with any model, so small local models gain the most from better retrieval