Nemotron 3 Super
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...
Updated 5 h ago · first seen 11 Sept 2026
model_01M294WW36WFAQ03K4PKME22N5
Overview
Identity
Identity block not returned by the API for this entity.
Openness
Openness not classified yet — no sourced evidence to place this model in the ontology.
Key facts
- Release date
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
- Openrouter id
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Architecture
- Hugging Face repo
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Capabilities
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
Source:OpenRouter public model & pricing listingT2observed 9 h agomedium
- Max output
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Benchmarks9
Compare with another model →Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric
No benchmark results recorded
Providers & Pricing2
All offers in the price terminal →USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Price history
Output price · USD / 1M tokens 1 provider
- NVIDIA NIM / build.nvidia.com
- NVIDIA NIM / build.nvidia.com$0.40 → $011 Sept 2026
- NVIDIA NIM / build.nvidia.comfirst observed $0.4011 Sept 2026
Input price · USD / 1M tokens 1 provider
- NVIDIA NIM / build.nvidia.com
- NVIDIA NIM / build.nvidia.com$0.085 → $011 Sept 2026
- NVIDIA NIM / build.nvidia.comfirst observed $0.08511 Sept 2026
Timeline14
Full timeline →Nemotron 3 Super: context length changed from 1000000 to 262144
Context window1M tokens→262.1K tokensopenrouterNemotron 3 Super scores 28.79% on Terminal-Bench
artificial_analysisNemotron 3 Super scores 38.58% on Terminal-Bench
artificial_analysisNemotron 3 Super scores 0% on Terminal-Bench
artificial_analysisNemotron 3 Super scores 67.84% on τ²-bench
artificial_analysisNemotron 3 Super scores 71.5% on IFBench
artificial_analysisNemotron 3 Super scores 36.23% on SciCode
artificial_analysisNemotron 3 Super scores 20.76% on Humanity's Last Exam
artificial_analysisNemotron 3 Super scores 13.55 on Artificial Analysis Intelligence Index
artificial_analysisNemotron 3 Super: context length changed from 262144 to 1000000
Context window262.1K tokens→1M tokensartificial_analysisNVIDIA NIM / build.nvidia.com lists Nemotron 3 Super at $0 in / $0 out per 1M tokens
openrouterNVIDIA NIM / build.nvidia.com lists Nemotron 3 Super at $0.085 in / $0.4 out per 1M tokens
openrouter
Change history16
Viewing AI Atlas as of 12 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →Attributes as of 12 Sept 2026 19 claims in force
- Release date
- 11 Mar 2026
- Openness
- open-weights
- Context window
- 262.1K tokens
- Max output
- 16.4K tokens
- Modalities
- text
- Input modalities
- text
- Output modalities
- text
- Hugging Face repo
- nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
- Aa context window
- 1,000,000
- Aa openness
- open-weights
- Aa median output tokens per second
- 154.7
- Openrouter id
- nvidia/nemotron-3-super-120b-a12b
- Openrouter listed at
- 11 Mar 2026
- Reasoning
- Yes
- Structured output
- Yes
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- Tool calling
- Yes
- Weights available
- Yes
Release daterelease_date1
Opennessopenness1
Context windowcontext_length2
Max outputmax_output_tokens1
Modalitiesmodalities1
Input modalitiesmodalities_input1
Output modalitiesmodalities_output1
Hugging Face repohf_repo1
Descriptiondescription1
Aa median output tokens per secondmetric.aa_median_output_tokens_per_second1
Openrouter idopenrouter_id1
Reasoningreasoning1
Structured outputstructured_output1
Supported parameterssupported_parameters1
Tool callingtool_calling1
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Provenance
Attributed facts
16
Source tiers
T216
Freshest observation
5 h ago
Conflicts
None
Source documents 2
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.
Data quality (56/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →