Nemotron Ultra
baseten/NVIDIA-Nemotron-3-Ultra-550B-A55B
- Tools
- JSON mode
- Vision
- Streaming
Released Jun 4, 2026
- Context
- 262.1K
- Max out
- 202.8K
- From / 1M
- $0.50
- Intelligence
- 11.8
28th of 33
Providers
- Basetenbaseten/NVIDIA-Nemotron-3-Ultra-550B-A55BInput / 1M$0.50Output / 1M$2.20Cache read / 1M$0.10Speed120.0 t/sFirst token328 ms
- Fireworks AIfireworks-ai/nemotron-3-ultra-nvfp4Input / 1M$0.60Output / 1M$2.40Cache read / 1M$0.119Speed210.2 t/sFirst token404 ms