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
$0.06
Output / 1M tokens
$0.33
Benchmark

Pricing

Input tokens$0.06 per 1M tokens
Output tokens$0.33 per 1M tokens

Technical details

Model IDgoogle/gemma-4-26b-a4b-it
Context window262k tokens
Input modalitiesimage, text, video
Output modalitiestext
TokenizerGemma

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 ?

Get an API key and start making requests in minutes.

Get an API key