LLM Reference

Cohere Parse v5.0

Released
2026-08-27
Last refreshed
2026-09-01
Status
Researched today
ProprietaryCommercial use: conditionalMultimodalVision

Cohere Parse v5.0 is worth evaluating for vision when its provider route and context window match the workload.

Use it for

  • Teams evaluating vision
  • Workloads that can use a 8k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Strict JSON or tool-calling flows
Specifications
Released
2026-08-27
Context
8k
Parameters
2.3B
Specialization
document-ai
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Created by

Empowering developers with advanced language AI.

Toronto, Ontario, Canada
Founded 2022
Website
Pricing
Output / 1M
-
Input / 1M
-

Cheapest of 1 route · Cohere API

About

Cohere Parse v5.0 (API id parse-v5.0) is a specialized document vision language model, not a chat LLM. Announced and generally available August 27, 2026. It converts page images into reading-order Markdown (tables as HTML) or typed blocks with bounding boxes for tables and images, via POST https://api.cohere.com/v2/parse. First-party docs: 2.3B parameters, ~4.6GB serving size, 8192 context, architecture described as proprietary north-micro-vision-instruct. Stable on nine languages (ar, en, fr, de, ja, ko, it, pt, es). Live API currently accepts document.type=image_url only (data URI or remote image URL); PDF/file URL inputs are not yet supported on the reference.

Top use-case fit

Vision

Included by capability and metadata signals in the decision map.

Capabilities

VisionMultimodal

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

parse-v5.0