Nemotron Nano 12b V2 Vl
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 memory-efficient sequence modeling for significantly higher throughput and lower latency. The model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets optimized for optical-character recognition, chart reasoning, and multimodal comprehension. Nemotron Nano 2 VL achieves leading results on OCRBench v2 and scores ≈ 74 average across MMMU, MathVista, AI2D, OCRBench, OCR-Reasoning, ChartQA, DocVQA, and Video-MME—surpassing prior open VL baselines. With Efficient Video Sampling (EVS), it handles long-form videos while reducing inference cost. Open-weights, training data, and fine-tuning recipes are released under a permissive NVIDIA open license, with deployment supported across NeMo, NIM, and major inference runtimes.
Pricing
💱 匯率 USD/NTD = 32.34 · 不含稅 · 更新於 2026/07/22
Technical specifications
Quick Start
Use Nemotron Nano 12b V2 Vl via BazaarLink API — just change the base_url:
from openai import OpenAI
client = OpenAI(
base_url="https://bazaarlink.ai/api/v1",
api_key="sk-bl-YOUR_API_KEY",
)
response = client.chat.completions.create(
model="nemotron-nano-12b-v2-vl",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://bazaarlink.ai/api/v1",
apiKey: "sk-bl-YOUR_API_KEY",
});
const response = await client.chat.completions.create({
model: "nemotron-nano-12b-v2-vl",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Why use Nemotron Nano 12b V2 Vl via BazaarLink?
- ✓USD billing (TWD-quoted) + unified invoices — no foreign credit card needed for Taiwan teams
- ✓OpenAI-compatible API — zero code changes required
- ✓Automatic failover — multi-provider redundancy for the same model
- ✓Chinese-language support — local team, instant help
Frequently Asked Questions
What is Nemotron Nano 12b V2 Vl?
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 memory-efficient sequence modeling for significantly higher throughput and lower latency. The model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets optimized for optical-character recognition, chart reasoning, and multimodal comprehension. Nemotron Nano 2 VL achieves leading results on OCRBench v2 and scores ≈ 74 average across MMMU, MathVista, AI2D, OCRBench, OCR-Reasoning, ChartQA, DocVQA, and Video-MME—surpassing prior open VL baselines. With Efficient Video Sampling (EVS), it handles long-form videos while reducing inference cost. Open-weights, training data, and fine-tuning recipes are released under a permissive NVIDIA open license, with deployment supported across NeMo, NIM, and major inference runtimes.
How much does the Nemotron Nano 12b V2 Vl API cost?
Nemotron Nano 12b V2 Vl costs $0.0000 per 1K input tokens and $0.0000 per 1K output tokens when accessed through BazaarLink.
How do I use Nemotron Nano 12b V2 Vl with the OpenAI SDK?
Set base_url to "https://bazaarlink.ai/api/v1" and use model ID "nemotron-nano-12b-v2-vl". All OpenAI SDK methods (chat.completions, embeddings, streaming) work without code changes.
What is the context window for Nemotron Nano 12b V2 Vl?
Nemotron Nano 12b V2 Vl supports a context window of 128,000 tokens.
Is Nemotron Nano 12b V2 Vl available for free?
Yes — Nemotron Nano 12b V2 Vl is available at no cost through BazaarLink's free tier. No credit card required.