Nemotron 3 Super (free)
NVIDIA's Nemotron 3 Super (free) is a chat model. 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...
by NVIDIA · 262K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Nemotron 3 Super (free) in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your NVIDIA API key. osFoundry discovers Nemotron 3 Super (free) automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
Run Nemotron 3 Super (free) yourself
Nemotron 3 Super (free) is also available as open weights — self-host it for full data control and no per-token cost. See that page for GPU requirements and a cost comparison against API pricing.
Nemotron 3 Super (free) vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Nemotron 3 Super (free) | NVIDIA | — | 262K | Free | API only |
| GLM 5 Turbo | Z.ai | — | 203K | $ 1.20 /1M | API only |
| MiniMax M2.7 | MiniMax | — | 197K | $ 0.279 /1M | API only |
| Mercury 2 | Inception | — | 128K | $ 0.250 /1M | API only |
Licence
Hosted — usage subject to provider terms — Hosted-only model — usage governed by the provider's API terms. Bring your own provider key.
No weights distributed; usage subject to provider terms.
Frequently asked about Nemotron 3 Super (free)
How much does Nemotron 3 Super (free) cost?
Nemotron 3 Super (free) is metered at Free for input, and Free for output. Bring your own NVIDIA API key — osFoundry passes through provider pricing without markup.
Can I use Nemotron 3 Super (free) commercially?
Commercial use is allowed with conditions. Hosted-only model — usage governed by the provider's API terms. Bring your own provider key. No weights distributed; usage subject to provider terms.
What is the context window of Nemotron 3 Super (free)?
Nemotron 3 Super (free) supports a 262K token context window.
Can I run Nemotron 3 Super (free) locally?
No — Nemotron 3 Super (free) is hosted only and accessed via the NVIDIA API. An open-weights equivalent is available to self-host — see the cross-link above.
What is Nemotron 3 Super (free) best at?
Nemotron 3 Super (free) is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Nemotron 3 Super (free) in osFoundry?
Paste your NVIDIA API key in the key dialog (or deploy the open weights for self-hostable models), assign Nemotron 3 Super (free) to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by NVIDIA on March 11, 2026. Source: https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b:free