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

Cohere has released Parse ( parse-v5.0 ) , a document parsing model aimed at high-volume enterprise ingestion. It is a 2.3B-parameter vision language model with an 8,192-token context window and a ~4.6GB footprint, built on Cohere Labs’ North-Micro-Vision-Instruct architecture. Parse takes a PDF, PPT or JPEG page as a base64-encoded data URI and returns Markdown containing text in reading order, tables rendered as HTML, lists, form key-value pairs, image descriptions and bounding box coordinates. There is no separate OCR stage in front of it. Cohere prices the Parse API at $1.50 per 1,000 pages and positions the model on price-performance rather than peak accuracy — a claim the company supports with a self-reported ParseBench score of 79.2 that, as we detail below, measures three of that benchmark’s five dimensions.

Yes , in production. Parse is generally available through the Cohere Parse API, Microsoft Foundry, AWS SageMaker , and single-tenant Model Vault . There is no waitlist and no research license.

Parse is a 2.3B-parameter vision language model built on Cohere Labs’ North-Micro-Vision-Instruct architecture, with an 8,192-token context window and a ~4.6GB footprint. It accepts PDF, PPT and JPEG pages as base64-encoded data URIs and returns Markdown containing document text, lists, tables rendered as HTML, bounding box coordinates and image descriptions.

There is no separate OCR stage in front of it. The model recovers text and reading order, tables, lists, forms and key-value pairs, images and captions, and the locations of page boundaries and visual elements in one pass. Nine languages are listed as stable — Arabic, English, French, German, Italian, Japanese, Korean, Portuguese and Spanish — with zero-shot support elsewhere at lower accuracy.

Two output modes matter in practice. The default returns a Markdown string per page. Setting output_format="blocks" returns typed blocks, where a table block carries its HTML, its bounding box and a description. That second mode is what makes citation-level traceability possible.

Cohere reports a ParseBench score of 79.2 for Parse, averaged across tables, content faithfulness and semantic formatting, ahead of Mistral OCR 4 (74.5), Azure Document Intelligence (74.3) and Databricks AI Parse (72.4).

ParseBench is a LlamaIndex benchmark of ~2,078 human-verified enterprise pages scored on five dimensions: tables, charts, content faithfulness, semantic formatting and visual grounding. Cohere’s figure averages three of them and drops charts and visual grounding — the two dimensions where most parsers collapse.

Against the public leaderboard , the same vendors score far lower on the full five-dimension overall: Mistral OCR 4 at 60.68, Databricks AI Parse at 60.68, Azure Document Intelligence (Layout) at 59.64. Azure’s three-dimension average works out to 74.3, which matches Cohere’s figure exactly and confirms the methodology. Cohere Parse is not currently listed on that leaderboard, where LlamaParse Agentic leads at 84.88.