nvidia
NVIDIA: Nemotron 3 Ultra
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...
Input Cost
$0.50
per 1M tokens
Output Cost
$2.50
per 1M tokens
Context Window
1,000,000
tokens
Developer ID: nvidia/nemotron-3-ultra-550b-a55b
Related Models
nvidia
$0.04/1M
NVIDIA: Nemotron Nano 9B V2
NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA,...
nvidia
$0.10/1M
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model...
nvidia
$0.05/1M
NVIDIA: Nemotron 3 Nano 30B A3B
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficien...