Nemotron 3 Ultra
NVIDIA
nvidia/nemotron-3-ultra-550b-a55bNemotron 3 Ultra is NVIDIA's flagship open-weight model in the Nemotron 3 family, a 550B-parameter mixture-of-experts model with 55B active parameters. It is optimized for orchestrating complex, long-running agent workflows, combining frontier reasoning with high inference throughput.
Cost rate
0.7x
Context
512K
Released
Jun 4, 2026
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
No top-ranked categories found.
Performance
Median latency and throughput measured across recent requests.
Throughput132 tok/s
Latency