LLM Reference
Cohere API

Using Cohere Parse v5.0 on Cohere API

Implementation guide · Cohere Parse · Cohere

Serverless

Cohere API exposes Cohere Parse v5.0 through model ID parse-v5.0. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-09-01. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Cohere API and generate an API key.
  2. 2
    Use the Cohere API SDK or REST API to call parse-v5.0 — see the documentation for request format.
API PortalDocumentationPricing

Code Examples

See Cohere API documentation for integration details.

Pricing on Cohere API

Capabilities

VisionMultimodal

About Cohere Parse v5.0

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.

Full model details →

Model Specs

Released2026-08-27
Parameters2.3B
Context8k

Provider

Cohere API
Cohere API

Cohere

Toronto, Ontario, Canada