Nemotron 3 Super — NVIDIA | Modeldex

Nemotron 3 Super

Active

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...

Updated 4 days agoStructured data from Modeldex catalog

Long contextBudget

API release

Mar 11, 2026(last month)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

Overview

History

Nemotron 3 Super became available via the NVIDIA API on 2026-03-11.

Training & availability

NVIDIA has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 262K tokens.
Input modalities: text.

Recommended for: long-context, cheap.

Limitations

Text-only — cannot process images, audio, or video inputs.

Pricing

Input: $0.0900 per 1M tokens
Output: $0.4500 per 1M tokens

Use the cost calculator above to estimate monthly spend for your workload.

Quick start

Minimal example using the OpenRouter API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="sk-or-...",
)
resp = client.chat.completions.create(
    model="nvidia/nemotron-3-super-120b-a12b",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $0.09/1M

Output tokens / month2.0M

@ $0.45/1M

Input cost

$0.45

5.0M × $0.09/1M

Output cost

$0.9

2.0M × $0.45/1M

Total / month

$1.35

$16.2 / year

Popularity

Signals from open-source communities — not a quality measure, but useful for gauging adoption among developers.

🤗

HuggingFace downloads

652.6K/ month

HuggingFace likes

232

Integrations & tooling support

Tool calling: Not supported
Structured outputs: Not supported

Price vs quality

Budget pricing

Priced low — good for high-volume tasks. Quality tier pending more benchmark coverage.