POMA PrimeCut Pricing — RAG Ingestion & Chunking
PrimeCut Eco
Lightweight ingestion and chunking engine without additional descriptive enrichment. Ideal for high-volume workflows, internal knowledge bases and cost-sensitive deployments where speed and efficiency are prioritized over deep semantic enrichment.
- Rapid document hierarchy detection
- Semantically bounded chunks with ancestor context inheritance
- Ready-to-embed chunksets
- Images and visual elements extracted and placeholdered
- Optimized for low cost
- Simple Title Generation
PrimeCut Pro
Full ingestion, structural parsing and 2:1 intelligent chunking engine with distinctive description layer. Designed for high-precision use cases where document hierarchy, cross-references and contextual dependencies must be preserved with maximum fidelity.
- Full document hierarchy parsing
- Semantically bounded and neighbour-aware chunks with ancestor context inheritance
- Context-aware ready-to-embed chunksets
- Full AI processing — figures, tables, and images parsed as semantic content
- Visual elements both extracted and converted to retrievable, context-aware textual chunks
- Optimized for multimodal accurate hierarchical textual representation of complex content
Choose Eco or Pro on every API request — one balance, two processing modes.
Enterprise
Built for teams of any size that need privacy, control, and security. Deploy POMA in your own dedicated instance or VPC with multi-user access, full data isolation, dedicated technical support, and pricing tailored to your needs.
- Everything in the Paid Plan.
- Multi-user accounts.
- Dedicated instance, VPC or Multi-Tenant SaaS.
- Signed custom DPA.
*Free Plan Includes
- 1,000 free pages
- Up to 250 pages per document.