Cohere Parse released, converting documents to Markdown with an 8K context window

Today we are releasing Cohere Parse.

Parse (model ID: parse-v5.0) turns complex documents into clean, structured Markdown ready for downstream AI workflows. The 2.3B-parameter multimodal model extracts text in reading order, tables, lists, forms, images and captions, page boundaries, and visual element locations.

Outputs include Markdown/HTML content, HTML-formatted tables, bounding boxes, and image descriptions — preserving both document structure and layout for easier rendering and processing.

Key specs: 8K context window · ~4.6GB model size · Markdown output

Availability

Cohere Parse is available through the Parse API, as well as Microsoft Foundry and AWS SageMaker. For deployment on dedicated infrastructure, Parse is also available in Model Vault.

For more details, see the model documentation.