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...
15 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
10 providers
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
15 providers
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
11 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| NVIDIA: Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b | NVIDIA |
23.4 | 256K | $0.625 | $3.125 | 2026-06-04 | ||
| NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning | NVIDIA |
13.6 | 262.144K | $0.08 | $0.2 | 2026-08-11 | ||
| NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b | NVIDIA |
13.6 | 262.144K | $0.085 | $0.4 | 2026-03-11 | ||
| NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | NVIDIA |
8.9 | 262.144K | $0.05 | $0.2 | 2025-12-15 |