googleVision
Google: Gemini 4 Argon
Try in chat →Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...
Context
1M tokens
Input / 1M tokens
$4.40
Output / 1M tokens
$22
Benchmark
—
Uptime & performance
Loading…
Pricing
Input tokens$4.40 per 1M tokens
Output tokens$22 per 1M tokens
Cache read$0.22 per 1M tokens
Cache write$0.41 per 1M tokens
Image$4.40 per image
Apps and activity
Loading…
Technical details
Model IDgoogle/gemini-4-argon
Context window1M tokens
Input modalitiesaudio, file, image, text, video
Output modalitiestext
TokenizerGemini
Max output tokens943,718
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/gemini-4-argon',
messages: [{ role: 'user', content: 'Hello!' }],
})Ready to use Google: Gemini 4 Argon?
Try it in the browser first, then get an API key and start making requests in minutes.