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?'})Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
 Together AI | 1M | 0.3s | 192tps | $0.60/M | $3.60/M | Read:$0.2/M Write:— | — | — | +1 | 06/04/2026 | ||
 DeepInfra | 262K | 0.7s | 74tps | $0.50/M | $2.50/M | Read:$0.15/M Write:— | — | — | +1 | 06/04/2026 | ||
 Blackbox | 1M | 1.3s | 178tps | $0.37/M | $1.08/M | Read:$0.14/M Write:— | — | — | +1 | 06/04/2026 | ||
 Baseten | 1M | 0.3s | 159tps | $0.60/M | $2.40/M | Read:$0.12/M Write:— | — | — | +1 | 06/04/2026 |