Nvidia
NVIDIA: Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b-20230311:freeHugging Face ↗
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...
NVIDIA: Nemotron 3 Super usage over time
OpenRouter share of tokens, by day.
NVIDIA: Nemotron 3 Super holds 0.20% today, down from 0.40% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
NVIDIA: Nemotron 3 Super's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-09-02, NVIDIA: Nemotron 3 Super holds 0.2% of OpenRouter token share, down 0.29pp over 30 days. Source: Tidelines (OpenRouter).
Cost per session
Median dollars spent on one NVIDIA: Nemotron 3 Super session, by coding agent and session length.
Token rate sets the price; session length and reasoning set the bill.
| Agent | 1 turn | 2–9 turns | 10–49 turns | 50+ turns |
|---|---|---|---|---|
| Hermes Agent | $0.0021 | $0.0098 | $0.076 | $0.420 |
Where to run it
NVIDIA: Nemotron 3 Super pricing by provider
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
NVIDIA: Nemotron 3 Super is served by 2 tracked endpoints on OpenRouter. The cheapest output price is $0.40 per million tokens from DeepInfra, and the most expensive is $0.65 from DigitalOcean. The largest context window offered is 1000k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfra | $0.08 | $0.40 | 262k | 100.00% |
| DigitalOcean | $0.30 | $0.65 | 1000k | 99.29% |