Nemotron 3 Ultra
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
The figures
- Made by
- NVIDIA
- Model ID
- nvidia/nemotron-3-ultra-550b-a55b
- Input
- $0.5 per million tokens
- Output
- $2.2 per million tokens
- Context window
- 262K tokens
- Longest answer
- 16K tokens
- Takes in
- text
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- No
- Open weights
- Yes
- Released
- 4 Jun 2026
Read on 3 Oct 2026.