nvidia
NVIDIA: Nemotron 3 Super
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
Context
1M tokens
Input / 1M tokens
$0.09
Output / 1M tokens
$0.45
Benchmark
—
Pricing
Input tokens$0.09 per 1M tokens
Output tokens$0.45 per 1M tokens
Technical details
Model IDnvidia/nemotron-3-super-120b-a12b
Context window1M tokens
Input modalitiestext
Output modalitiestext
TokenizerOther
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: 'nvidia/nemotron-3-super-120b-a12b',
messages: [{ role: 'user', content: 'Hello!' }],
})Ready to use NVIDIA: Nemotron 3 Super?
Get an API key and start making requests in minutes.
Get an API key