NVIDIA

NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b

Input Price

$0.08 / 1M

Output Price

$0.45 / 1M

Context Length

262,144

LLM Price Calculator

Enter custom token counts to calculate exact pricing for your specific AI use case.

Input Cost
$0.08
Output Cost
$0.45
Total Cost
$0.53

About this 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...

Try this model in Playground

Test this model's capabilities in different AI playground environments including OpenRouter, Hugging Face, Cloudflare, and Vercel.

FAQ

NVIDIA: Nemotron 3 Super pricing FAQ

Answers about this model's pricing, context window, supported modalities, and where to try it.

How much does NVIDIA: Nemotron 3 Super cost?

Use the calculator above to estimate the cost for your expected workload. Input and output tokens are billed at separate rates, and optional provider features may add extra charges.

What is the context length of NVIDIA: Nemotron 3 Super?

NVIDIA: Nemotron 3 Super supports a context window of up to 262,144 tokens. Your provider may reserve part of that capacity for generated output or system instructions.

Which modalities does NVIDIA: Nemotron 3 Super support?

Listed input modalities: text. Listed output modalities: text. Confirm feature availability with your chosen provider before integrating the model.

Where can I try NVIDIA: Nemotron 3 Super?

Use the Playground links above to check whether the model is currently available from those third-party services. Access, features, and pricing can vary between platforms.