Cohere Parse: 2.3B Document Model at $1.50 per 1,000 Pages
Cohere Parse is a 2.3B vision language model that turns enterprise documents into Markdown for RAG, at $1.50 per 1,000 pages. Specs, scores, costs and limits.

Turning PDFs and scanned documents into data AI can use. Posts cover document parsing and visual retrieval for production RAG, and Cohere's Parse 5, a 2.3B vision-language model for enterprise document processing.
Cohere Parse is a 2.3B vision language model that turns enterprise documents into Markdown for RAG, at $1.50 per 1,000 pages. Specs, scores, costs and limits.

Document Parsing and Visual Retrieval for Production RAG: Architecture, Benchmarks, and Serving Trade-Offs for Docling, Marker, MinerU, and ColPali The retrieval quality of a Retrieval-Augmented Generation (RAG) system is strictly bounded by the fidelity of its document ingestion pipeline. In enterprise environments, the vast majority of domain knowledge remains locked in unstructured Portable Document Format (PDF) files, scanned reports, technical manuals, and multi-column research papers. Na
