nvidia
NVIDIA: Nemotron 3 Ultra
Try in chat →NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
Context
262k tokens
Input / 1M tokens
$0.40
Output / 1M tokens
$1.76
Benchmark
—
Uptime & performance
Loading…
Pricing
Input tokens$0.40 per 1M tokens
Output tokens$1.76 per 1M tokens
Cache read$0.08 per 1M tokens
Apps and activity
Loading…
Technical details
Model IDnvidia/nemotron-3-ultra-550b-a55b
Context window262k tokens
Input modalitiestext
Output modalitiestext
TokenizerOther
Max output tokens182,520
Use with MegaBrain
import OpenAI from 'openai'
const client = new OpenAI({
baseURL: 'https://themegabrain.ru/api/gateway/v1',
apiKey: process.env.MEGABRAIN_API_KEY,
})
const response = await client.chat.completions.create({
model: 'nvidia/nemotron-3-ultra-550b-a55b',
messages: [{ role: 'user', content: 'Hello!' }],
})Ready to use NVIDIA: Nemotron 3 Ultra?
Try it in the browser first, then get an API key and start making requests in minutes.