nvidia
NVIDIA: Nemotron 3 Nano 30B A3B
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
Quality Score
99/100
price + capability + benchmarks
Input Price
$0.05
per 1M tokens
Output Price
$0.20
per 1M tokens
Context Window
262,144
tokens
- Model ID
- nvidia/nemotron-3-nano-30b-a3b
- Vendor
- nvidia
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 228,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
Similar models
nvidia
NVIDIA: Nemotron 3 Nano Omni (free)
Free
256,000 ctx
100
nvidia
NVIDIA: Nemotron 3 Super
$0.09 in / $0.45 out
1,000,000 ctx
99
nvidia
NVIDIA: Nemotron 3 Ultra
$0.50 in / $2.50 out
1,000,000 ctx
98
nvidia
NVIDIA: Nemotron 3 Super (free)
Free
1,000,000 ctx
93
nvidia
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
$0.40 in / $0.40 out
131,072 ctx
91
nvidia
NVIDIA: Nemotron Nano 12B 2 VL (free)
Free
128,000 ctx
89