Nemotron 3 Super (120B A12B): Benchmarks, Pricing & Context Window
Nemotron 3 Super (120B A12B) is a language model from Nvidia, released in March 2026, with a 262K-token context window, and pricing from $0.085/M input and $0.400/M output.
Nemotron 3 Super is a 120B total / 12B active parameter hybrid Mamba-Attention Mixture-of-Experts model optimized for agentic reasoning, coding, planning, tool calling, and long-context analysis. It introduces LatentMoE (projecting tokens
Nemotron 3 Super (120B A12B) benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Nemotron 3 Super (120B A12B) across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Nemotron 3 Super (120B A12B) holds up as conversations get longer.
Quality Tracker
Nemotron 3 Super (120B A12B) Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Sep 11 2026Nemotron 3 Super (120B A12B) pricing
Providers
Nemotron 3 Super (120B A12B) starts at $0.0850 per million input tokens and $0.400 per million output tokens via DeepInfra.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.0850 | — | $0.400 | 262.1K/262.1K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Nemotron 3 Super (120B A12B) model size
Nemotron 3 Super (120B A12B) has 120 billion parameters and was trained on 25 trillion tokens. See how it compares to other models in the same parameter range.
Nemotron 3 Super (120B A12B) context window
Input and output token limits for Nemotron 3 Super (120B A12B), plus how it ranks on long-context understanding.
Try now
huggleMake it with
Nemotron 3 Super (120B A12B).
Nemotron 3 Super (120B A12B) latency
Nemotron 3 Super (120B A12B) time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Nemotron 3 Super (120B A12B) examples
Recent arena outputs from Nemotron 3 Super (120B A12B), picked from the highest-ranked matchups.
Nemotron 3 Super (120B A12B) license
Nemotron 3 Super (120B A12B) is released under the NVIDIA Open Model License Agreement license, which permits commercial use, has 120.0B parameters, has a knowledge cutoff of June 2025.
- License
- NVIDIA Open Model License Agreement
- Commercial use allowed
- Parameters
- 120.0B
- Knowledge cutoff
- June 2025
NVIDIA Open Model License Agreement
Nemotron 3 Super (120B A12B) resources
Official sources for Nemotron 3 Super (120B A12B): provider documentation, paper or system card, official launch post, source repository, model weights.
Nemotron 3 Super (120B A12B) vs other models
The most-compared alternatives to Nemotron 3 Super (120B A12B) are Grok-3 Mini, K-EXAONE-236B-A23B, LongCat-Flash-Thinking. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Nemotron 3 Super (120B A12B)
Models ranked just above and below Nemotron 3 Super (120B A12B) by LLM Stats score.
FAQ
Common questions about Nemotron 3 Super (120B A12B).