Back to Explore
NVIDIA: Nemotron Nano 12B 2 VL
NVIDIA·Released 2025-10-28
Open Source131K ctxMultimodal
About
NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...
Related Models
Nemotron 3 Ultra 550B A55B (Reasoning)2026-06-04NVIDIA: Nemotron 3 Ultra2026-06-04NVIDIA: Nemotron 3 Ultra (free)2026-06-04NVIDIA: Nemotron 3.5 Content Safety (free)2026-06-04Nemotron 3 Nano Omni 30B A3B Reasoning2026-04-29NVIDIA: Nemotron 3 Nano Omni (free)2026-04-28Nemotron Cascade 2 30B A3B2026-03-19NVIDIA: Nemotron 3 Super2026-03-11
Pricing
Input
$0.20
per 1M tokens
Output
$0.60
per 1M tokens
Blended
$0.30
per 1M tokens
Cheaper than 62% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.30
Monthly
$9.00
vs. Similar Models
Seed-OSS-36B-Instruct
$0.300%
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)
$0.300%
Olmo 3.1 32B Instruct
$0.300%
Mistral: Saba
$0.300%
Performance
Context Window
131K
tokens
Larger than 27% of models
Max Output
16K
tokens
13% of context
Context Window Comparison
DeepSeek: DeepSeek V3.2
131KSame
OpenAI: gpt-oss-120b
131KSame
MoonshotAI: Kimi K2 0711
131KSame