Cohere: Aya Vision 32B

stable

Aya Vision 32B is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

c4ai-aya-vision-32bc4ai-aya-vision-32breleased Mar 4, 2025

Provider Quick start

Context

16K

tokens

Max output

tokens

Input

per 1M

Output

per 1M

Activity

Daily period usage

Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M

Cohere

16K--

Pricing

Item	Price	Unit
Input	-	per 1M tokens
Output	-	per 1M tokens

Performance

Reliability

Compare

Compare usage and performance

Place this model beside up to three other catalog models.

Capabilities

Modalities

Input

Output

Details

Model ID: c4ai-aya-vision-32b
Family: c4ai-aya-vision-32b
Status: stable
Knowledge: -
Released: Mar 4, 2025

Gateway Config

API: 2024-01-01
Auth: COHERE_API_KEY
Discovery: static
Provider type: static

Quick Start

index.ts

import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@cohere/c4ai-aya-vision-32b",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL

https://api.cohere.com

Chat completions

https://api.cohere.com/chat/completions

Model

c4ai-aya-vision-32b

Auth env

COHERE_API_KEY

Aya Vision 32B FAQ

What is the context window of Aya Vision 32B?

Aya Vision 32B accepts up to 16K tokens of context and returns up to 4K output tokens on Cohere.

What can Aya Vision 32B do?

Aya Vision 32B supports chat and image input. It accepts text and image input.

How do I call Aya Vision 32B through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @cohere/c4ai-aya-vision-32b. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.