Bedrock
100.00%Context131.1K
Max output131.1K
p50 latency162 ms
Throughput—
Input price$0.2
Output price$0.6
Zero retentionNo training
Model directory
Baseer model profileLanguage model
nvidia/nemotron-nano-12b-v2-vl
Nvidia Nemotron Nano 12B V2 VL
The model is an auto-regressive vision language model that uses an optimized transformer architecture. The model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&A and summarization capabilities.
Input / 1M tokens$0.2
Output / 1M tokens$0.6
Maximum context131.1K
Inference providers2
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Deepinfra
99.92%Context131.1K
Max output131.1K
p50 latency777 ms
Throughput161.0 t/s
Input price$0.2
Output price$0.6
Zero retentionNo training
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Bedrock | 131.1K | 131.1K | 162 ms | — | 100.000% | $0.2 | $0.6 | |
Deepinfra | 131.1K | 131.1K | 777 ms | 161.0 t/s | 99.922% | $0.2 | $0.6 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageAdvanced reasoningVisionTool useTools
Technical profile
- Model type
- Language model
- Release date
- Oct 28, 2025
- Knowledge cutoff
- —
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
nvidia/nemotron-nano-12b-v2-vlModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.