Model Library
NVIDIAReleased December 15, 2025NVIDIA Nemotron 3 Nano
NVIDIA · Released December 15, 2025
Intelligence score
14
At a glance
- Intelligence
- 14
- Speed
- 109.8tokens/sec
- Latency
- 1.32stime to first token
- Input price
- $0.05per 1M tokens
- Output price
- $0.20per 1M tokens
- Context window
- 3tokens
- Parameters
- 31.6billions
Summary
Comparison summary
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) scores 14 on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 9). NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) generates output at 109.8 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight models of similar size (median: 101.0 t/s). NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) costs $0.05 per 1M input tokens (very competitive, median: $0.18) and $0.20 per 1M output tokens (very competitive, median: $0.40), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | NVIDIA Nemotron 3 Nano |
|---|---|
| Provider | NVIDIA |
| Release date | December 15, 2025 |
| Intelligence score | 14 |
| Speed | 109.8 tokens/sec |
| Latency (TTFT) | 1.32s |
| Input price | $0.05 / 1M tokens |
| Output price | $0.20 / 1M tokens |
| Context window | 3 tokens |
| Parameters | 31.6B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Nvidia Nemotron Open Model License |
| API availability | — |
| Source | Model Intelligence legacy profile: nvidia-nemotron-3-nano-30b-a3b-reasoning |
Pricing
Token prices
Price per 1M tokens
NVIDIA Nemotron 3 Nano, as listed in the catalog record
- Input$0.05
- Output$0.20
| Token type | Price per 1M |
|---|---|
| Input | $0.05 |
| Output | $0.20 |
Model Intelligence legacy profile: nvidia-nemotron-3-nano-30b-a3b-reasoning
FAQ · 21
Frequently asked questions
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) was released on December 15, 2025.
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) was created by NVIDIA.
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) scores 14 on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 9).
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) generates output at 109.8 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight models of similar size (median: 101.0 t/s).
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) has a time to first token (TTFT) of 1.32s (based on the median across providers serving the model), which is better than average compared to other open weight models of similar size (median: 2.09s).
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) costs $0.05 per 1M input tokens (very competitive, median: $0.18) and $0.20 per 1M output tokens (very competitive, median: $0.40), based on the median across providers serving the model.
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) costs $0.05 per 1M input tokens and $0.20 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.07 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) generated 120M output tokens, which is at the higher end compared to other open weight models of similar size (median: 32M).
Yes, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) supports text input.
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) supports text output.
No, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) does not support image input. It can only process text.
No, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is not multimodal. It only supports text input.
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
Yes, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) has 31.6 billion parameters (3.6 billion active).
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is a Mixture of Experts (MoE) model with 31.6 billion total parameters, but only 3.6 billion active parameters are used during inference.
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is released under the Nvidia Nemotron Open Model License license. This license allows commercial use.
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) achieves a score of 14 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is available via API through 3 providers.
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is available through 3 API providers.