LLM
Nemotron 3 Nano Omni 30B A3B Reasoning
NVIDIA
Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error
Specifications
- Type
- LLM
- Released
- April 29, 2026
- Output speed
- 301 tok/s
- Latency (TTFT)
- 0.58s
- API pricing
- $0.10 in · $0.30 out / 1M tokens
Benchmarks
Reasoning
| GPQA Diamond | 46.9 |