Nemotron 3 Super (free) pricing & benchmarks
Released Mar 11, 2026 · served by 1 provider
What Nemotron 3 Super (free) is
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...
- Model ID:
nvidia/nemotron-3-super-120b-a12b:free - Modality: text->text
- Tool calling: supported · Structured output: supported
- Weights:
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8on Hugging Face
Providers and prices for Nemotron 3 Super (free)
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| Nvidiacheapest | Free | Free | 262K | — | 99.7% | — |
FAQ
How much does the Nemotron 3 Super (free) API cost?
Free per 1M input tokens and Free per 1M output tokens.
Is Nemotron 3 Super (free) free?
Yes — it is served at $0 for both input and output tokens on OpenRouter, subject to rate limits.
Which provider is cheapest for Nemotron 3 Super (free)?
Nvidia at Free input / Free output per 1M tokens.
Can I self-host Nemotron 3 Super (free)?
Yes — weights are published as nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 on Hugging Face, so you can run it on your own hardware.