Nemotron 3 Ultra
A 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent workflows. It uses a hybrid Mamba-Transformer MoE architecture and supports a 1M token context window.
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 | 1.6s | 532tps | $0.15/M | $0.65/M | Read:— Write:$0.06/M | — | — |   | 03/18/2026 | ||||
| 131K | 0.2s | 116tps | $0.06/M | $0.23/M | — | — |  | 08/18/2025 | |||||
| 262K | 0.3s | 91tps | $0.05/M | $0.24/M | — | — | | 12/01/2024 | |||||
| 131K | 0.2s | $0.20/M | $0.60/M | — | — | +1 | | 12/01/2024 |
