NVIDIA · Model identity
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...
1pricing route
What published route metadata supports
Hugging FaceReasoningStructured outputTool use
Input modalities
Text
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Only source-backed fields are filled
Release dateNot independently verified
Knowledge cutoffNot independently verified
Open weightsNot independently verified
OpenRouter catalog date2026-03-11
LLMPrice does not infer a release date, knowledge cutoff, or open-weight status from a model name, Hugging Face link, or pricing route.
Could this workload cost less?Compare Nemotron 3 Super with cheaper models using the same workload.
Find cheaper alternatives →| Endpoint / route | Model ID | Input | Cached | Output | Context | Source |
|---|---|---|---|---|---|---|
| OpenRouterStandard | nvidia/nemotron-3-super-120b-a12b | $0.075 | — | $0.4 | 262K | OpenRouter API ↗ |
Hugging Face references
Presence of a Hugging Face ID is not treated as proof that model weights are open.
3 verified price changes since Aug 26, 2026
1 route availability change recorded. No earlier prices are inferred.
Input / 1M$0.075Aug 26, 2026 → Nov 6, 2026
Output / 1M$0.4Aug 26, 2026 → Nov 6, 2026
- Nov 6, 2026OpenRouter · Standard
Input $0.3 → $0.075 · Cached input $0.15 → — · Output $2.4 → $0.4
- Oct 27, 2026OpenRouter · Free
Pricing route removed
- Oct 24, 2026OpenRouter · Standard
Input $0.08 → $0.3 · Cached input — → $0.15 · Output $0.45 → $2.4
- Sep 16, 2026OpenRouter · Standard
Input $0.085 → $0.08 · Output $0.4 → $0.45