Nemotron 3 Nano 30B A3B
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...
Nemotron 3 Nano 30B A3B ranks #76 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.12 blended per million tokens, it is cheaper than 90% of models with published API pricing. Its 262,144-token context window is about the catalog median (262,144 tokens).
open weightstexttext->text
Context
Max context: 262144
Max output: 235929
Max output: 235929
Pricing
Input / 1M: 0.05
Output / 1M: 0.20
Blend / 1M: 0.12
Output / 1M: 0.20
Blend / 1M: 0.12
Quality
Quality index: —
Provider
Provider: NVIDIA
Moderated: no
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.12per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $0.12 |
| 10,000,000 | $1.25 |
| 100,000,000 | $12.50 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from NVIDIA
- Nemotron 3 Nano Omni$0.00 / 1M
- Nemotron 3.5 Lightning$0.14 / 1M
- Nemotron 3.5 Content Safety$0.20 / 1M
- Nemotron 3 Super$0.24 / 1M
- Nemotron 3 Ultra$1.88 / 1M
Closest API price
- Granite 4.2 8B$0.13 / 1M
- Qwen3.5-9B$0.13 / 1M
- DeepSeek V4 Flash 0731$0.12 / 1M · Q 86.3
- Qwen3 30B A3B Instruct 2507$0.12 / 1M
- Ling 3.0 Flash Fin$0.12 / 1M