NVIDIAActive
nemotron-nano-v2-12b
NVIDIA Nemotron Nano v2 12B is a 12-billion-parameter multimodal reasoning model designed for advanced video understanding, document intelligence, and visual reasoning, built with a hybrid Transformer-Mamba architecture for high efficiency and low latency.
Context
128,000
Max output
128,000
Input / 1M
$0.24
Output / 1M
$0.71
Providers
1
01Profile
Profile
Released
2025-10-31
Last updated
2025-10-31
Knowledge cutoff
—
Weights
Closed
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 1 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
3+ recent events since 2025-10-31
2026-08-05Addedcortecsoffering→ new
2026-05-07Removednebiusofferingremoved→ new
2026-02-04Addednebiusoffering→ new