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?'})More models by NVIDIA
| Model |
|---|
| 256K | 1.5s | 216tps | $0.15/M | $0.65/M | Read:$0.06/M Write:— | — | — |   | 03/11/2026 | ||||
| 262K | 0.3s | 75tps | $0.05/M | $0.24/M | — | — |  | 12/15/2025 | |||||
| 131K | 0.2s | 205tps | $0.20/M | $0.60/M | — | — | +1 | | 10/28/2025 | ||||
| 131K | 0.2s | 145tps | $0.06/M | $0.23/M | — | — | | 08/18/2025 |
