Back to Cohere
Cohere /

Aya Vision 32B
Aya Vision 32B

Open WeightsMultimodaltextimageUpdated March 4, 2025
Some details or benchmark scores on this page are self-reported by developers and unconfirmed.

Aya Vision 32B

📌 Model Overview

Open multilingual vision model for OCR, visual reasoning, and image question answering

Aya Vision 32B is a Open Weights model developed by Cohere, released on 2025-03-04. It is designed primarily for Multimodal General workloads. Featuring a 16K tokens context window and 32B parameter count, it offers robust performance for enterprise integration, developers, and researchers.


✨ Key Features & Capabilities

Specification Table
FeatureDescription
Context Window16K tokens capacity for extended prompts and multi-turn workflows
Primary TaskOptimized for Multimodal General
Deploymentself-hostable, api-only
Modalitytext, image
Max OutputMax Output: 4K tokens

⚙️ Technical Specifications

Specification Table
SpecificationDetails
Developer / LabCohere
Release Date2025-03-04
Model TypeOpen Weights
Parameters32B
Context Window16K tokens
LicenseCC-BY-NC-4.0

🔗 Resources & Links

Specification Table

📜 License & Usage

This model is governed by the CC-BY-NC-4.0 license. Please check official developer guidelines before commercial deployment.

Key Features

Max Output: 4K tokens

Feature 01

You might also want to compare

Verified Sources

Tags

open-weights

Model Specs

open-weights

Parameters

32B

Context Window

16K tokens

License

CC-BY-NC-4.0

Deployment

self-hostableapi-only

Resources & Links

Curator Notes

Skeleton entry imported from models.dev backfill (2026-07-26). Needs manual enrichment and primary-source verification.

Compare Specs

Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.

Compare Model