Using Nemotron 3 Super-120B-A12B on NVIDIA NIM

Implementation guide · Nemotron 3 · NVIDIA AI

ServerlessOpen Weights

NVIDIA NIM exposes Nemotron 3 Super-120B-A12B through model ID nvidia/nemotron-3-super-120b-a12b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-01. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at NVIDIA NIM and generate an API key.
  2. 2
    Use the NVIDIA NIM SDK or REST API to call nvidia/nemotron-3-super-120b-a12b — see the documentation for request format.
  3. 3
    You'll be billed $0.10/1M input, $0.50/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See NVIDIA NIM documentation for integration details.

Pricing on NVIDIA NIM

TypePrice (per 1M)
Input tokens$0.10
Output tokens$0.50

Capabilities

Structured Outputs

About Nemotron 3 Super-120B-A12B

NVIDIA Nemotron 3 Super-120B-A12B is a 120B total / 12B active hybrid Latent MoE model with interleaved Mamba-2 and MoE layers for agentic, reasoning, and conversational tasks. Fireworks lists the NVFP4 variant for on-demand deployment with 262k context.

Full model details →

Model Specs

Released2026-03-11
Parameters120B
Context1.05m
ArchitectureDecoder Only

More Models on NVIDIA NIM

Nemotron 3 NanoLlama 3.3 Nemotron Super 49B v1Llama 3.1 Nemotron 70B Reward
All models on NVIDIA NIM →

Also available on(5)

OpenRouter$0.09/1MDeepInfra$0.10/1MVercel AI Gateway$0.15/1M
Compare all providers →

Provider

NVIDIA NIM

NVIDIA

Santa Clara, California, United States