googleVision

Google: Gemma 4 26B A4B

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Context

262k tokens

Input / 1M tokens

$0.04

Output / 1M tokens

$0.22

Benchmark

—

Uptime & performance

Loading…

Pricing

Input tokens$0.04 per 1M tokens

Output tokens$0.22 per 1M tokens

Apps and activity

Loading…

Technical details

Model IDgoogle/gemma-4-26b-a4b-it

Context window262k tokens

Input modalitiesimage, text, video

Output modalitiestext

TokenizerGemma

Max output tokens235,929

Use with MegaBrain

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://getmegabrain.com/api/gateway/v1',
  apiKey: process.env.MEGABRAIN_API_KEY,
})

const response = await client.chat.completions.create({
  model: 'google/gemma-4-26b-a4b-it',
  messages: [{ role: 'user', content: 'Hello!' }],
})

Ready to use Google: Gemma 4 26B A4B ?

Try it in the browser first, then get an API key and start making requests in minutes.

Try in chat Get an API key

← All models