Model Library
NVIDIAReleased October 28, 2025NVIDIA Nemotron Nano 12B v2 VL
NVIDIA · Released October 28, 2025
Intelligence score
5
At a glance
- Intelligence
- 5
- Speed
- 241.4tokens/sec
- Latency
- 1.07stime to first token
- Input price
- $0.20per 1M tokens
- Output price
- $0.60per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 13.2billions
Summary
Comparison summary
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 6). NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) generates output at 241.4 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) costs $0.20 per 1M input tokens (somewhat higher than average, median: $0.15) and $0.60 per 1M output tokens (somewhat higher than average, median: $0.32), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | NVIDIA Nemotron Nano 12B v2 VL |
|---|---|
| Provider | NVIDIA |
| Release date | October 28, 2025 |
| Intelligence score | 5 |
| Speed | 241.4 tokens/sec |
| Latency (TTFT) | 1.07s |
| Input price | $0.20 / 1M tokens |
| Output price | $0.60 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 13.2B |
| Reasoning | No |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | Yes |
| License | Nvidia Open Model License |
| API availability | — |
| Source | Model Intelligence legacy profile: nvidia-nemotron-nano-12b-v2-vl |
Pricing
Token prices
Price per 1M tokens
NVIDIA Nemotron Nano 12B v2 VL, as listed in the catalog record
- Input$0.20
- Output$0.60
| Token type | Price per 1M |
|---|---|
| Input | $0.20 |
| Output | $0.60 |
Model Intelligence legacy profile: nvidia-nemotron-nano-12b-v2-vl
FAQ · 19
Frequently asked questions
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) was released on October 28, 2025.
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) was created by NVIDIA.
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 6).
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) generates output at 241.4 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) has a time to first token (TTFT) of 1.07s (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 12B v2 VL (Non-reasoning) costs $0.20 per 1M input tokens (somewhat higher than average, median: $0.15) and $0.60 per 1M output tokens (somewhat higher than average, median: $0.32), based on the median across providers serving the model.
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) costs $0.20 per 1M input tokens and $0.60 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 $0.24 per 1M tokens. Pricing may vary by provider.
No, NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) supports text and image input.
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) supports text output.
Yes, NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) supports image input and can analyze, describe, and answer questions about images.
Yes, NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) is multimodal. It can process text and image input and generate text output.
NVIDIA Nemotron Nano 12B v2 VL (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 12B v2 VL (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) has 13.2 billion parameters.
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) is released under the Nvidia Open Model License license. This license allows commercial use.
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) achieves a score of 5 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) is available via API through 2 providers.
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) is available through 2 API providers.