Compare Models
Created by
nvidia
nvidiaReleasedJun 4, 2026
A 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent workflows. It uses a hybrid Mamba-Transformer MoE architecture and supports a 1M token context window.
Limits
Context Length1M
Max Output Tokens65K
Pricing
Pricing (Input)$0.60/M
Pricing (Output)$2.40/M
Caching
Input Modalities
Text
Image
PDF
Audio
Output Modalities
Text
Image
Audio
Features
Reasoning
Tools
Temperature
No model selected
Use the selector above to choose a model.