Modelspublished

Cohere’s Parse 5 Turns Enterprise Documents Into Markdown for $1.50 per 1,000 Pages

The compact vision model is built for high-volume retrieval and document-processing pipelines, but its headline benchmark result leaves out chart and visual-grounding tests.

By 3 min read
Cohere’s Parse 5 Turns Enterprise Documents Into Markdown for $1.50 per 1,000 Pages

Listen to this story

The audio brief

About 1:28
0:001:28
Read transcript
Cohere is putting a clear price on a painful enterprise bottleneck: Parse 5 turns document pages into structured Markdown for $1.50 per 1,000 pages. The 2.3-billion-parameter vision model is aimed at retrieval-augmented generation, or RAG, where companies first have to make messy source files usable by search and AI systems. Parse 5 accepts PDFs, PowerPoints, and JPEG pages, then processes each page in one pass. It preserves reading order, tables, lists, form fields, image descriptions, and the coordinates of page elements. Tables are represented as HTML inside the Markdown, so the output retains more layout than plain text, without requiring a separate OCR step. Cohere says the model is stable across nine languages, and it is generally available through Cohere’s API, Microsoft Foundry, AWS SageMaker, and the single-tenant Model Vault service. The important caveat is the headline score. Cohere reports a 79.2 average on three ParseBench dimensions: tables, content faithfulness, and semantic formatting. That excludes charts and visual grounding, so it is not a full five-dimension leaderboard result. The handoff also remains imperfect: there are no confidence scores or hierarchy labels, the output is Markdown rather than JSON, and each invocation has an 8,192-token limit. The thing to watch is whether that low price and layout-rich output outweigh the downstream work required for fixed schemas and extraction certainty.

Story brief

3 key points

Cohere is making Parse 5 generally available as a low-cost document-ingestion option for enterprise RAG pipelines, with API pricing of $1.50 per 1,000 pages. Its 2.3B-parameter model handles PDFs, PowerPoints and JPEGs in one pass, preserving reading order, tables, forms, images and coordinates in Markdown. The tradeoff is incomplete handoff data: no confidence scores or hierarchy labels, Markdown instead of JSON,...

  1. 01

    Parse 5 supports Arabic, English, French, German, Italian, Japanese, Korean, Portuguese and Spanish.

  2. 02

    Cohere reports 79.2 across three ParseBench dimensions; the score excludes charts and visual grounding.

  3. 03

    The model is available through Cohere’s API, Microsoft Foundry, AWS SageMaker and single-tenant Model Vault.

Cohere has released Parse 5, a 2.3-billion-parameter vision-language model that converts enterprise document pages into structured Markdown for $1.50 per 1,000 pages. The product targets a costly step in retrieval-augmented generation, or RAG: turning source documents into material that AI systems can search and use.

Parse 5, also called parse-v5.0, accepts PDF, PowerPoint and JPEG pages as base64-encoded data URIs. It returns reading-order text, lists, form key-value pairs, image descriptions and bounding-box coordinates, alongside tables rendered as HTML within Markdown.

One pass, layout included

The model performs document text recovery without a separate OCR stage before it. Its output is designed to retain enough structure for document search, retrieval workflows and downstream processing: tables keep their HTML representation, while bounding boxes locate content on a page.

Cohere says nine languages are stable: Arabic, English, French, German, Italian, Japanese, Korean, Portuguese and Spanish. The model is generally available through the Cohere Parse API, Microsoft Foundry, AWS SageMaker and the single-tenant Model Vault offering, without a waitlist.

A selective benchmark comparison

Cohere reports a 79.2 ParseBench score averaged over tables, content faithfulness and semantic formatting. On that same three-dimension comparison, Mistral OCR 4 scored 74.5, Azure Document Intelligence 74.3 and Databricks AI Parse 72.4.

ParseBench evaluates five dimensions across about 2,078 human-verified enterprise pages: tables, charts, content faithfulness, semantic formatting and visual grounding. Parse 5’s reported average excludes charts and visual grounding, so it should not be read as an all-dimensions leaderboard position.

The handoff still needs work

  • Parse 5 does not provide confidence scores for extracted content.
  • It does not identify header or font hierarchy, limiting information available for section-aware processing.
  • It produces Markdown rather than structured JSON, and its 8,192-token context window limits processing per invocation.

Those limits define the boundary of Cohere’s pitch. Parse 5 can supply structured page output, but applications that need a fixed schema or a measure of extraction certainty require capabilities the model does not return directly.

Price is the commercial argument

The API price is $1.50 per 1,000 pages. Cohere’s Model Vault option is listed at $2,500 per month for a Medium instance and $4,300 per month for XL, offering a separate single-tenant deployment route from metered API use.

The central question for prospective users is therefore document-specific rather than settled by the 79.2 figure: whether Parse 5’s selective benchmark result, layout-rich Markdown output and stated limitations fit the documents and downstream controls in their own ingestion pipeline.

Sources

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