Model Library
NVIDIAReleased August 18, 2025NVIDIA Nemotron Nano 9B V2
NVIDIA · Released August 18, 2025
Intelligence score
7
At a glance
- Intelligence
- 7
- Speed
- 133.9tokens/sec
- Latency
- 1.35stime to first token
- Input price
- $0.05per 1M tokens
- Output price
- $0.20per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 9billions
Summary
Comparison summary
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6). NVIDIA Nemotron Nano 9B V2 (Non-reasoning) generates output at 133.9 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). NVIDIA Nemotron Nano 9B V2 (Non-reasoning) costs $0.05 per 1M input tokens (very competitive, median: $0.15) and $0.20 per 1M output tokens (very competitive, median: $0.32), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | NVIDIA Nemotron Nano 9B V2 |
|---|---|
| Provider | NVIDIA |
| Release date | August 18, 2025 |
| Intelligence score | 7 |
| Speed | 133.9 tokens/sec |
| Latency (TTFT) | 1.35s |
| Input price | $0.05 / 1M tokens |
| Output price | $0.20 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 9B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | NVIDIA Open Model License Agreement |
| API availability | — |
| Source | Model Intelligence legacy profile: nvidia-nemotron-nano-9b-v2 |
Pricing
Token prices
Price per 1M tokens
NVIDIA Nemotron Nano 9B V2, 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-nano-9b-v2
FAQ · 19
Frequently asked questions
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) was released on August 18, 2025.
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) was created by NVIDIA.
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) scores 7 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6).
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) generates output at 133.9 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) has a time to first token (TTFT) of 1.35s (based on the median across providers serving the model), which is better than average compared to other open weight non-reasoning models of similar size (median: 1.54s).
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) costs $0.05 per 1M input tokens (very competitive, median: $0.15) and $0.20 per 1M output tokens (very competitive, median: $0.32), based on the median across providers serving the model.
NVIDIA Nemotron Nano 9B V2 (Non-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 $0.06 per 1M tokens. Pricing may vary by provider.
No, NVIDIA Nemotron Nano 9B V2 (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) supports text input.
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) supports text output.
No, NVIDIA Nemotron Nano 9B V2 (Non-reasoning) does not support image input. It can only process text.
No, NVIDIA Nemotron Nano 9B V2 (Non-reasoning) is not multimodal. It only supports text input.
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, NVIDIA Nemotron Nano 9B V2 (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) has 9 billion parameters.
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) is released under the NVIDIA Open Model License Agreement license. This license allows commercial use.
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) achieves a score of 7 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, NVIDIA Nemotron Nano 9B V2 (Non-reasoning) is available via API through 2 providers.
NVIDIA Nemotron Nano 9B V2 (Non-reasoning) is available through 2 API providers.