--- title: NVIDIA: Nemotron Nano 12B 2 VL | Text Generation | ModelsLab description: Compact 12.6B parameter vision-language LLM with 128K token context, multi-image/video support up to 3072x1024 res, excels in OCR, VQA, reasoning on. url: https://modelslab.com/models/nvidia/nvidia-nemotron-nano-12b-v2-vl.md canonical: https://modelslab.com/models/nvidia/nvidia-nemotron-nano-12b-v2-vl.md type: product component: Playground/LLM/Index generated_at: 2026-04-15T00:23:30.168750Z --- NVIDIA: Nemotron Nano 12B 2 VL --- [LLMs.txt](https://modelslab.com/models/open_router/nvidia-nemotron-nano-12b-v2-vl/llms.txt) [.md](https://modelslab.com/models/nvidia/nvidia-nemotron-nano-12b-v2-vl.md) nvidia-nemotron-nano-12b-v2-vl nvidia Closed Source Model $0.400000 / call NVIDIA: Nemotron Nano 12B 2 VL --- Choose a prompt below to get started or type your own message Explain quantum computing in simple terms Write a Python function to sort a list Create a marketing email for a SaaS product Compare REST vs GraphQL APIs Send ### NVIDIA: Nemotron Nano 12B 2 VL nvidia nvidia-nemotron-nano-12b-v2-vl Copy model ID PricingInput $0.20 / 1M tokens Output $0.60 / 1M tokens API EndpointsOpenAI Compatible `https://modelslab.com/api/v7/llm/chat/completions`Endpoint Anthropic Compatible `https://modelslab.com/api/v7/llm/v1/messages`Messages `https://modelslab.com/api/v7/llm/v1/messages/count_tokens`Count Tokens `https://modelslab.com/api/v7/llm/v1/models`Models Use with Claude Code cURL Example ParametersSystem MessageYou are a helpful AI assistant specialized in providing accurate and detailed responses. Temperature0.7 Max Tokens1000 Top P0.9 Frequency Penalty0 Presence Penalty0 Model Info Support Related Models --- Discover similar models you might be interested in [View all LLM Models](https://modelslab.com/models?feature=llmaster) [OG](https://modelslab.com/models/open_router/openai-gpt-5.1-chat)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-5.1 Chat Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-5.1-chat) [ML](https://modelslab.com/models/together_ai/meta-llama-Llama-3-8b-chat-hf)[Together AI](https://modelslab.com/models/together_ai) [Meta Llama 3 8B Instruct Reference Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Llama-3-8b-chat-hf) [DV](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-V3-0324)[Together AI](https://modelslab.com/models/together_ai) [Deepseek V3 0324 Closed Source Model](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-V3-0324) [QQ](https://modelslab.com/models/open_router/qwen-qwen3-coder-30b-a3b-instruct)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3 Coder 30B A3B Instruct Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-coder-30b-a3b-instruct) [H3](https://modelslab.com/models/together_ai/Hcompany-Holo3-35B-A3B)[Together AI](https://modelslab.com/models/together_ai) [Holo3 35B A3b Closed Source Model](https://modelslab.com/models/together_ai/Hcompany-Holo3-35B-A3B) [MD](https://modelslab.com/models/open_router/mistralai-devstral-medium)[Open Router](https://modelslab.com/models/open_router) [Mistral: Devstral Medium Closed Source Model](https://modelslab.com/models/open_router/mistralai-devstral-medium) [DR](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-R1-Distill-Llama-70B)[Together AI](https://modelslab.com/models/together_ai) [DeepSeek R1 Distill Llama 70B Closed Source Model](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-R1-Distill-Llama-70B) [BE](https://modelslab.com/models/open_router/baidu-ernie-4.5-21b-a3b)[Open Router](https://modelslab.com/models/open_router) [Baidu: ERNIE 4.5 21B A3B Closed Source Model](https://modelslab.com/models/open_router/baidu-ernie-4.5-21b-a3b) [KK](https://modelslab.com/models/together_ai/moonshotai-Kimi-K2.5)[Together AI](https://modelslab.com/models/together_ai) [Kimi K2.5 Closed Source Model](https://modelslab.com/models/together_ai/moonshotai-Kimi-K2.5) [MM](https://modelslab.com/models/open_router/minimax-minimax-m2-her)[Open Router](https://modelslab.com/models/open_router) [MiniMax: MiniMax M2-her Closed Source Model](https://modelslab.com/models/open_router/minimax-minimax-m2-her) [![Mixtral-8x7B Instruct v0.1](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/67dabe3d-a00a-4cc4-a158-136c8f189137.png)](https://modelslab.com/models/together_ai/mistralai-Mixtral-8x7B-Instruct-v0.1)[Together AI](https://modelslab.com/models/together_ai) [Mixtral-8x7B Instruct v0.1 Closed Source Model](https://modelslab.com/models/together_ai/mistralai-Mixtral-8x7B-Instruct-v0.1) [QQ](https://modelslab.com/models/open_router/qwen-qwen3-vl-32b-instruct)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3 VL 32B Instruct Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-vl-32b-instruct) [MP](https://modelslab.com/models/open_router/mistralai-pixtral-large-2411)[Open Router](https://modelslab.com/models/open_router) [Mistral: Pixtral Large 2411 Closed Source Model](https://modelslab.com/models/open_router/mistralai-pixtral-large-2411) [BS](https://modelslab.com/models/open_router/bytedance-seed-seed-2.0-mini)[Open Router](https://modelslab.com/models/open_router) [ByteDance Seed: Seed-2.0-Mini Closed Source Model](https://modelslab.com/models/open_router/bytedance-seed-seed-2.0-mini) [OG](https://modelslab.com/models/open_router/openai-gpt-5.2-codex)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-5.2-Codex Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-5.2-codex) [MM](https://modelslab.com/models/open_router/minimax-minimax-m1)[Open Router](https://modelslab.com/models/open_router) [MiniMax: MiniMax M1 Closed Source Model](https://modelslab.com/models/open_router/minimax-minimax-m1) [NH](https://modelslab.com/models/open_router/nousresearch-hermes-4-405b)[Open Router](https://modelslab.com/models/open_router) [Nous: Hermes 4 405B Closed Source Model](https://modelslab.com/models/open_router/nousresearch-hermes-4-405b) [Q2](https://modelslab.com/models/together_ai/Qwen-Qwen3-235B-A22B-Thinking-2507)[Together AI](https://modelslab.com/models/together_ai) [Qwen3 235B A22B Thinking 2507 FP8 Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3-235B-A22B-Thinking-2507) About NVIDIA: Nemotron Nano 12B 2 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... ### Technical Specifications Model IDnvidia-nemotron-nano-12b-v2-vlCategoryLLM ModelsTaskText GenerationPrice$0.400000 per million tokensAddedFebruary 20, 2026 ### Key Features - Chat completion and multi-turn conversation API - Streaming response with token-by-token output - Function calling and tool use support - System prompts and role-based messaging - JSON mode and structured output ### Quick Start Integrate NVIDIA: Nemotron Nano 12B 2 VL into your application with a single API call. Get your API key from the [pricing page](https://modelslab.com/pricing) to get started. PythonJavaScriptcURLPHP ``` import requests import json url = "https://modelslab.com/api/v7/llm/chat/completions" headers = { "Content-Type": "application/json" } data = { "model_id": "nvidia-nemotron-nano-12b-v2-vl", "messages": [ { "role": "user", "content": "Hello!" } ], "max_tokens": 1000, "key": "YOUR_API_KEY" } try: response = requests.post(url, headers=headers, json=data) response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX) result = response.json() print("API Response:") print(json.dumps(result, indent=2)) except requests.exceptions.HTTPError as http_err: print(f"HTTP error occurred: {http_err} - {response.text}") except Exception as err: print(f"Other error occurred: {err}") ``` View the [full API documentation](https://modelslab.com/models/nvidia/nvidia-nemotron-nano-12b-v2-vl/api) for SDKs, code examples in Python, JavaScript, and more. ### Pricing NVIDIA: Nemotron Nano 12B 2 VL API costs $0.400000 per million tokens. Pay only for what you use with no minimum commitments. [View pricing plans](https://modelslab.com/pricing) ### Use Cases - AI chatbots and virtual assistants - Code generation and developer tools - Content writing and copywriting automation - Data analysis, summarization, and extraction [Browse LLM Models](https://modelslab.com/models?feature=llmaster) [More from Nvidia](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) NVIDIA: Nemotron Nano 12B 2 VL FAQ --- ### What is NVIDIA: Nemotron Nano 12B 2 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... ### How do I use the NVIDIA: Nemotron Nano 12B 2 VL API? You can integrate NVIDIA: Nemotron Nano 12B 2 VL into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "nvidia-nemotron-nano-12b-v2-vl" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does NVIDIA: Nemotron Nano 12B 2 VL cost? NVIDIA: Nemotron Nano 12B 2 VL costs $0.400000 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the NVIDIA: Nemotron Nano 12B 2 VL model ID? The model ID for NVIDIA: Nemotron Nano 12B 2 VL is "nvidia-nemotron-nano-12b-v2-vl". Use this ID in your API requests to specify this model. ### Does NVIDIA: Nemotron Nano 12B 2 VL have a free tier? Yes, ModelsLab offers a free tier that lets you try NVIDIA: Nemotron Nano 12B 2 VL and other AI models. Sign up to get free API credits and start building immediately. --- *This markdown version is optimized for AI agents and LLMs.* **Links:** - [Website](https://modelslab.com) - [API Documentation](https://docs.modelslab.com) - [Blog](https://modelslab.com/blog) --- *Generated by ModelsLab - 2026-04-15*