NVIDIA: Nemotron 3 Super (free) API Pricing
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...
Input / 1M tokens
Free
Output / 1M tokens
Free
Cost per request (1K in / 500 out)
Free
~$0.00 per 1M tokens mixed
Specifications
Context Window 1.0M tokens
Max Output Tokens 262,144
Vision Support No
Function Calling No
Streaming Yes
Modality text
Release Date 2026-03-11
Price history will appear here after the first price change is detected.
More from NVIDIA
Input / 1M tokens
$0.40
Output / 1M tokens
$0.40
Context: 131K Streaming
Input / 1M tokens
$0.05
Output / 1M tokens
$0.20
Context: 262K Streaming
Input / 1M tokens
Free
Output / 1M tokens
Free
Context: 256K Streaming
Multimodal
Input / 1M tokens
Free
Output / 1M tokens
Free
Context: 256K Vision Streaming
Input / 1M tokens
$0.09
Output / 1M tokens
$0.45
Context: 1.0M Streaming
Similar Models from Other Providers
Input / 1M tokens
Variable
Output / 1M tokens
Variable
Context: 128K Streaming
Input / 1M tokens
Variable
Output / 1M tokens
Variable
Context: 128K Streaming
Input / 1M tokens
Variable
Output / 1M tokens
Variable
Context: 2.0M Streaming
Input / 1M tokens
Free
Output / 1M tokens
Free
Context: 33K Streaming
Input / 1M tokens
Free
Output / 1M tokens
Free
Context: 33K Streaming