Models/NVIDIA/Nemotron 3 Super

Nemotron 3 Super

NVIDIA · Open weights · Released Mar 11, 2026 · nvidia/nemotron-3-super-120b-a12b
Best $0.08 in / $0.40 out via DekaLLM · fp8
CompareEstimate cost
262K contextToolsReasoningStructured outputOpen weights
Available from 2 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 24 HOURS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
PROVIDERINPUTOUTPUTCACHECONTEXTQUANTTTFTTPSUPTIME
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 24 hours ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.08 / $0.45
per MTok in / out
FREE
Free / Free
per MTok in / out
Recent changesRSS ↗
Sep 12, 2026endpoint added · dekallm1 → 2
Sep 9, 2026endpoint removed · digitalocean2 → 1
Sep 9, 2026context changed1000000 → 262144
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...

Specifications
Context window262,144
Max output16,384
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedMar 11, 2026
TokenizerOther
WeightsHugging Face ↗
Open weights
Hugging Facenvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 ↗
Downloads64K
Likes283
Licenseother
safetensorspytorch
Related
Nemotron 3.5 Lightning$0.039 / $0.14Nemotron 3.5 Content Safety$0.20 / $0.20Nemotron 3 Ultra$0.50 / $2.20Nemotron 3 Nano 30B A3B$0.05 / $0.20
Embed badge
Nemotron 3 Super price and speed badge
[![Nemotron 3 Super](https://modelindex.ai/badge/nvidia/nemotron-3-super-120b-a12b)](https://modelindex.ai/models/nvidia/nemotron-3-super-120b-a12b)
Sources
OpenRouter API23 minutes ago
AGGREGATOR
Hugging Face23 minutes ago
COMMUNITY
ModelIndex benchmarks12 days ago
MEASURED
Verified 23 minutes ago · list prices, not negotiated rates.