Cohere Releases Parse 5 (parse-v5.0): A 2.3B Vision Language Model That Turns Enterprise Documents Into Markdown

Cohere has introduced Parse 5, a 2.3B-parameter vision language model designed to convert business documents like PDFs and slides into structured Markdown format. The model extracts elements including HTML tables, image descriptions, and spatial coordinates for enterprise data processing. It is available through an API priced at $1.50 per 1,000 pages or via monthly dedicated Model Vault subscriptions.