NVIDIA-Nemotron-Nano-12B-v2-VL

Name: NVIDIA-Nemotron-Nano-12B-v2-VL
Author: DeepInfra

12B

NVIDIA Nemotron 2 Nano VL extends the Nemotron family into multi-modal reasoning and document intelligence. This auto-regressive vision-language model enables multi-image reasoning, video understanding, visual Q&A and document analysis and summarization. Optimized for enterprise AI workflows, it powers multimodal agentic systems such as visual copilots, document assistants, and knowledge automation pipelines.

Context

131K

Input price

$0.2/1M tokens

Output price

$0.6/1M tokens

Capabilities

Show unsupported (5)

Reasoning & Interaction

Reasoning

Tool Calling

Infrastructure

Streaming

Details

Model IDnvidia/NVIDIA-Nemotron-Nano-12B-v2-VL

ProviderDeepInfra

CreatorNVIDIA

Familynemotron

License—

Statusactive

Typechat

Input modalitiestext, image

Output modalitiestext

Open weightYes

Parameters12B

Architecture—

Context window131K tokens

Max input—

Max output—

Reasoning tokensYes

Knowledge cutoff—

Release date—

Sourceofficial

Endpoints

Chat CompletionsPOST

Generate chat responses with messageshttps://api.deepinfra.com/v1/openai/v1/chat/completions

Pricing

Input

$0.2

Output

$0.6

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: nemotron

Model	Caps	Perf	Speed	Context	Max out	Pricing
NVIDIA-Nemotron-Nano-9B-v2	RTJJMS	—	—	131K	—	$0.04$0.16
Nemotron-3-Nano-30B-A3B	RTS	—	—	262K	—	$0.05$0.2
NVIDIA-Nemotron-3-Super-120B-A12B	RTJJMS	—	—	262K	—	$0.09$0.4
NVIDIA-Nemotron-Nano-12B-v2-VL	RS	—	—	131K	—	$0.2$0.6

API

GET/v1/models/deepinfra/nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL