NNVIDIA · Released Dec 14, 2025
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...
- Released
- Dec 14 2025
- Context window
- 262K 236K out
- Input / 1M tokens
- $0.06 from $0.05
- Output / 1M tokens
- $0.24 from $0.20
Where to run it
2 providers compared
Cheapest: Novita at $0.05 / $0.20 per 1M input / output tokens — 17% less than the priciest option.
| Provider | Input | Output | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|
| NovitaFP4 | $0.05 | $0.20 | 262K | 33K | 98.9%24h | Cheapest |
| NebiusFP8 | $0.06 | $0.24 | 262K | 236K | 99%24h | +20% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Nemotron 3 Nano 30B A3B. Scores appear here automatically once it does.
Specs
Details
- Model ID
nvidia/nemotron-3-nano-30b-a3b- Developer
- NVIDIA
- Release date
- Dec 14, 2025 ·
- Context window
- 262,144 tokens
- Max output
- 235,929 tokens
- API price
- $0.06 / $0.24 per 1M input / output tokens
- Providers
- 2
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.