Nemotron 3 Ultra

Available

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
262.1K tokens
Max output
182.5K tokens
Input / 1M tokens
$0.60per 1M tokens
Output / 1M tokens
$2.40per 1M tokens
Listed since
Jun 4, 2026

Prices and model data from OpenRouter

Where it's availableProviders · 1

ProviderInput / 1M tokensOutput / 1M tokensStatus
OpenRouter$0.60$2.40Available

Published benchmark results

From independent leaderboards, each credited to its publisher.