Back to Models

NVIDIA Nemotron Nano 12B v2 VL

![NVIDIA](https://artificialanalysis.ai/img/logos/nvidia_small.svg)NVIDIA
10/ 57

Intelligence Score

Intelligence

10

#187 of 212 (top 88%)

Speed

139 tok/s

#52 of 141

Price

$0.30

per M tokens

#46 cheapest of 142

Context Window

128K

tokens

Latency: 1ms (#43)

Score Breakdown

Quality Score17%
Speed Score18%
Cost Score97%

Similar Models

LFM2 24B A2B

![Liquid AI](https://artificialanalysis.ai/img/logos/liquidai_small.svg)Liquid AI

10intelligence

Phi-4

![Microsoft](https://artificialanalysis.ai/img/logos/microsoft_small.svg)Microsoft

10intelligence

Nova Micro

![Amazon](https://artificialanalysis.ai/img/logos/aws_small.svg)Amazon

10intelligence

Phi-4 Multimodal

![Microsoft](https://artificialanalysis.ai/img/logos/microsoft_small.svg)Microsoft

10intelligence

Qwen3.5 0.8B

![Alibaba](https://artificialanalysis.ai/img/logos/alibaba_small.svg)Alibaba

10intelligence

Use This Model

Claude Code

claude --model nvidia-nemotron-nano-12b-v2-vl

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "nvidia-nemotron-nano-12b-v2-vl",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Vercel AI SDK

import { generateText } from "ai";
import { openrouter } from "@openrouter/ai-sdk-provider";

const { text } = await generateText({
  model: openrouter("nvidia-nemotron-nano-12b-v2-vl"),
  prompt: "Hello",
});
Back to Models