ModelInfo
English
All models

Aya Vision 32B

32B multimodal model for language, text, and image tasks covering 23 languages.

Coherec4ai-aya-vision-32b2025-03-04Report incorrect data

Specs

Context
16K
Max output
4K
Input price
—
Output price
—
Released
2025-03-04

Context

Context window
16K
Max input
—
Max output
4K

Pricing

Not published

Modalities

Input
TextImage
Output
Text

API

API types
chat

Reasoning

Not published

Info

Status
Active
Released
2025-03-04
Knowledge cutoff
—

Features

Not published
Source · official docsVerified 2026-10-11

How to call

1 provider

coheremodel = c4ai-aya-vision-32b

chat
POSThttps://api.cohere.com/v2/chat

JSON

Standard format
c4ai-aya-vision-32b.json
{
  "id": "c4ai-aya-vision-32b",
  "object": "model",
  "created": 1741046400,
  "owned_by": "cohere",
  "name": "Aya Vision 32B",
  "api": {
    "types": [
      "chat"
    ]
  },
  "limits": {
    "context": 16000,
    "input": null,
    "output": 4000
  },
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "reasoning": {
    "supported": null,
    "efforts": []
  },
  "pricing": null,
  "features": [],
  "info": {
    "status": "active",
    "release_date": "2025-03-04",
    "knowledge_cutoff": null,
    "description": "32B multimodal model for language, text, and image tasks covering 23 languages.",
    "docs": "https://docs.cohere.com/docs/aya-vision",
    "verified_at": "2026-10-11"
  }
}

Official sources

4