baseten
Nemotron Ultra
NVIDIA Nemotron 3 Ultra is a 550B hybrid MoE model for multi-agent and complex reasoning workloads.
Provider:
baseten
Model type:
chat
Location:
rest
Context Window
202800
Intelligence Rating
Speed Rating
Cost Efficiency Rating
Pricing
$
0.6
Input tokens per million
$
2.4
Output tokens per million
Features
Tool Calling
Supported
JSON Mode
Supported
Reasoning
Supported
