About
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...
Related Models
Nemotron 3 Ultra 550B A55B (Reasoning)2026-06-04NVIDIA: Nemotron 3 Ultra2026-06-04NVIDIA: Nemotron 3 Ultra (free)2026-06-04NVIDIA: Nemotron 3.5 Content Safety (free)2026-06-04Nemotron 3 Nano Omni 30B A3B Reasoning2026-04-29NVIDIA: Nemotron 3 Nano Omni (free)2026-04-28Nemotron Cascade 2 30B A3B2026-03-19NVIDIA: Nemotron 3 Super (free)2026-03-11
Pricing
Input
$0.08
per 1M tokens
Output
$0.40
per 1M tokens
Blended
$0.16
per 1M tokens
Cheaper than 74% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.16
Monthly
$4.91
vs. Similar Models
Qwen: Qwen3 30B A3B Thinking 2507
$0.16-2%
Meta: Llama 3.3 70B Instruct
$0.15-5%
GLM-4.7-Flash (Non-reasoning)
$0.15-7%
MiMo-V2.5
$0.17+7%
Performance
Context Window
1.0M
tokens
Larger than 80% of models
Max Output
16K
tokens
2% of context
Context Window Comparison
Anthropic: Claude Fable 5
1.0MSame
Anthropic: Claude Opus 4.8
1.0MSame
Anthropic: Claude Opus 4.7
1.0MSame