Last refreshed 2026-06-01. Next refresh: weekly.
Why use Nemotron 3 Super-120B-A12B on NVIDIA NIM?
NVIDIA NIM offers Nemotron 3 Super-120B-A12B with pay-as-you-go pricing at $0.10/1M input tokens. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare Nemotron 3 Super-120B-A12B across 6 providers to find the best fit for your use caseInput / 1M
$0.10
Output / 1M
$0.50
Cache
read $0.10
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: nvidia/nemotron-3-super-120b-a12bModel ID
nvidia/nemotron-3-super-120b-a12bRequest example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
nvidia/nemotron-3-super-120b-a12b.Gotchas
- Use provider model ID "nvidia/nemotron-3-super-120b-a12b", not the LLMReference slug "nemotron-3-super-120b-a12b".
Compare Nemotron 3 Super-120B-A12B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Cloudflare Workers AI | — | — |
| DeepInfra | $0.10 | $0.50 |
| NVIDIA NIM | $0.10 | $0.50 |
| OpenRouter | $0.09 | $0.45 |
| Fireworks AI | — | — |
Pricing
| Type | Price (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.
Get Started
Model Specs
Released2026-03-11
Parameters120B
Context1.05m
ArchitectureDecoder Only