Private AI
Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture and supports up to 1M context on current hosted routes.
Added Jun 4, 2026
Context Window
1.0M
Max Output
65.5K
Input Price (Auto)
$0.53/1M
Output Price (Auto)
$2.63/1M
Cache Read (Auto)
$0.16/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
No benchmark data is available yet for this model.
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…