googleVision
Google: Gemma 4 31B
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Context
262k tokens
Input / 1M tokens
$0.12
Output / 1M tokens
$0.35
Benchmark
—
Pricing
Input tokens$0.12 per 1M tokens
Output tokens$0.35 per 1M tokens
Cache read$0.09 per 1M tokens
Technical details
Model IDgoogle/gemma-4-31b-it
Context window262k tokens
Input modalitiesimage, text, video
Output modalitiestext
TokenizerGemma
Max output tokens262,144
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-4-31b-it',
messages: [{ role: 'user', content: 'Hello!' }],
})