Skip to content
NVIDIA

Nemotron 3 Ultra

Nemotron 3 Ultra is NVIDIA's largest open reasoning model, a hybrid Mamba-Transformer MoE with 550B total and 55B active parameters, latent MoE routing, multi-token prediction, and a context window of 1M tokens for long-running agent workflows.

ReasoningTool UseImplicit Caching
index.ts
import { streamText } from 'ai'


const result = streamText({
  model: 'nvidia/nemotron-3-ultra-550b-a55b',
  prompt: 'Why is the sky blue?'
})
OverviewAboutProvidersThroughputLatencyUptimeStatusSimilarFAQ
Throughput

P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.