Skip to main content

Parse

CohereProprietary

Description

Cohere Parse (`parse-v5.0`) is a 2.3B-parameter proprietary vision language model for high-volume enterprise document parsing. Proprietary north-micro-vision-instruct architecture (~4.6GB serving footprint); 8192 context. Converts PDF, PPT, and JPEG inputs into structured Markdown (tables as HTML; bounding boxes for tables/images). Stable languages: Arabic, English, French, German, Japanese, Korean, Italian, Portuguese, Spanish. Cohere API price: $1.50 per 1,000 pages (no published token price). Also offered via Model Vault, Microsoft Azure AI Foundry, and AWS SageMaker. Commercial API product; not open-weight.

Release Date
2026-08-27
Parameters
2.3B
Context Length
Modalities
image

Capability Radar

0
general
0
coding
0
reasoning
0
scienceest.
0
agents
70
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Vision

ParseBench79.2%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))

No category score data available

Pricing

No pricing data available

Speed

No speed data available

Provider Price Ranking

External Sources