Nemotron Super 3 120B A12B is NVIDIA's language model with a 1.0M context window and up to 32K output tokens, available from 4 providers, starting at $0.085 / 1M input and $0.4 / 1M output. A 120B-parameter hybrid MoE Nemotron Super 3 model with 12B active parameters, optimized by NVIDIA for compute-efficient reasoning in specialized agentic systems.
Specifications
Canonical IDnvidia-nemotron-super-3-120b-a12b
TypeLanguage
StatusActive
CreatorNVIDIANVIDIA
Providers
Context Window1.0M tokens
Max Output32K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters120B
Release Date · 6 months ago
Benchmarks
Intelligence Index
#166
Coding Index
#96
GPQA
#146
HLE
#118
IFBench
#53
Time to First Token
#439
SciCode
#224
LCR
#172
TerminalBench Hard
#112
TAU2
#156
Output TPS
#64

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning
Adaptive Reasoning·
Function Calling
Parallel Function Calling·
Structured Outputs
Native JSON Schema
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandardFree
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
DeepInfra logo
DeepInfra
deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
$0.085$0.4
Nebius logo
Nebius
nvidia/nemotron-3-super-120b-a12b
$0.3$0.9
OpenRouter logo
OpenRouter
nvidia/nemotron-3-super-120b-a12b
$0.085$0.4N/AN/A
OpenRouter logo
OpenRouter
nvidia/nemotron-3-super-120b-a12b:free
$N/A$N/A
Vercel AI Gateway logo
Vercel AI Gateway
nvidia/nemotron-3-super-120b-a12b
$0.15$0.65

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Nemotron Super 3 120B A12B, ranked by cheapest on-demand price. The model needs about 288 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NC96ads_A100_v4Azure4× NVIDIA A100320 GB$14.69/hr
g7e.24xlargeAWS4× RTX PRO Server 6000384 GB$16.57/hr
g4-standard-192GCP4× nvidia-rtx-pro-6000384 GB$18.00/hr
7 more instances can run Nemotron Super 3 120B A12B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Nemotron Super 3 120B A12B1.0M$0.085$0.400Current
Nemotron Nano 3 30B A3B262K$0.050$0.200Available
Nemotron 3 Ultra262K$0.600$2.40Available
Nemotron Lightning 3.5 30B A3B262K$0.050$0.200Available
Nemotron Nano 2 9B131K$0.040$0.160Deprecated
Nemotron Nano 2 12B131K$0.200$0.200Available

Model IDs

accounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-fp8
accounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-nvfp4
deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
huggingface-llm-nvidia-nemotron-3-super-120b-a12b-bf16
nvidia-nemotron-3-super-120b-a12b
nvidia-nemotron-super-3-120b-a12b
nvidia/nemotron-3-super-120b-a12b
nvidia/nemotron-3-super-120b-a12b:free
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B