--- title: Meta: Llama Guard 4 12B API | Text Generation | ModelsLab description: 12B parameter multimodal LLM safety classifier for text/image content moderation in prompts/responses, 164K context window, MLCommons-aligned.[1][2][4] url: https://modelslab.com/models/meta-llama/meta-llama-llama-guard-4-12b/api.md canonical: https://modelslab.com/models/meta-llama/meta-llama-llama-guard-4-12b/api.md type: product component: Playground/LLM/Index generated_at: 2026-04-15T02:10:18.009560Z --- Meta: Llama Guard 4 12B --- [LLMs.txt](https://modelslab.com/models/open_router/meta-llama-llama-guard-4-12b/llms.txt) [.md](https://modelslab.com/models/meta-llama/meta-llama-llama-guard-4-12b.md) meta-llama-llama-guard-4-12b meta-llama Closed Source Model $0.180000 / call Meta: Llama Guard 4 12B --- 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 ### Meta: Llama Guard 4 12B meta-llama meta-llama-llama-guard-4-12b Copy model ID PricingInput $0.18 / 1M tokens Output $0.18 / 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) [MK](https://modelslab.com/models/open_router/moonshotai-kimi-k2)[Open Router](https://modelslab.com/models/open_router) [MoonshotAI: Kimi K2 0711 Closed Source Model](https://modelslab.com/models/open_router/moonshotai-kimi-k2) [MS](https://modelslab.com/models/mistral_ai/mistralai-Mistral-Small-24B-Instruct-2501)[ModelsLab](https://modelslab.com/models/mistral_ai) [Mistral Small (24B) Instruct 25.01 Closed Source Model](https://modelslab.com/models/mistral_ai/mistralai-Mistral-Small-24B-Instruct-2501) [OG](https://modelslab.com/models/open_router/openai-gpt-5.1-codex)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-5.1-Codex Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-5.1-codex) [L2](https://modelslab.com/models/together_ai/LiquidAI-LFM2-24B-A2B)[Together AI](https://modelslab.com/models/together_ai) [LFM2-24B-A2B Closed Source Model](https://modelslab.com/models/together_ai/LiquidAI-LFM2-24B-A2B) [L3](https://modelslab.com/models/together_ai/meta-llama-Llama-3.2-1B)[Together AI](https://modelslab.com/models/together_ai) [Llama 3.2 1B Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Llama-3.2-1B) [MW](https://modelslab.com/models/open_router/mancer-weaver)[Open Router](https://modelslab.com/models/open_router) [Mancer: Weaver (alpha) Closed Source Model](https://modelslab.com/models/open_router/mancer-weaver) [GG](https://modelslab.com/models/open_router/google-gemini-2.0-flash-001)[Open Router](https://modelslab.com/models/open_router) [Google: Gemini 2.0 Flash Closed Source Model](https://modelslab.com/models/open_router/google-gemini-2.0-flash-001) [G3](https://modelslab.com/models/google_deepmind/google-gemma-3n-E4B-it)[ModelsLab](https://modelslab.com/models/google_deepmind) [Gemma 3N E4B Instruct Closed Source Model](https://modelslab.com/models/google_deepmind/google-gemma-3n-E4B-it) [OG](https://modelslab.com/models/open_router/openai-gpt-4.1-nano)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-4.1 Nano Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-4.1-nano) [OG](https://modelslab.com/models/open_router/openai-gpt-4o-mini)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-4o-mini Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-4o-mini) [OG](https://modelslab.com/models/together_ai/openai-gpt-oss-20b)[Together AI](https://modelslab.com/models/together_ai) [OpenAI GPT-OSS 20B Closed Source Model](https://modelslab.com/models/together_ai/openai-gpt-oss-20b) [MM](https://modelslab.com/models/open_router/mistralai-mistral-small-2603)[Open Router](https://modelslab.com/models/open_router) [Mistral: Mistral Small 4 Closed Source Model](https://modelslab.com/models/open_router/mistralai-mistral-small-2603) [AA](https://modelslab.com/models/arcee_ai/arcee-ai-coder-large)[ModelsLab](https://modelslab.com/models/arcee_ai) [Arcee AI Coder-Large Closed Source Model](https://modelslab.com/models/arcee_ai/arcee-ai-coder-large) [![GPT OSS 120b](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/32ccebf4-aaac-46b2-af6a-b19d11fcf8fa.webp)](https://modelslab.com/models/openai/gpt-oss-120b)[Open Ai](https://modelslab.com/models/openai) [GPT OSS 120b Closed Source Model](https://modelslab.com/models/openai/gpt-oss-120b) [DD](https://modelslab.com/models/open_router/deepseek-deepseek-chat-v3.1)[Open Router](https://modelslab.com/models/open_router) [DeepSeek: DeepSeek V3.1 Closed Source Model](https://modelslab.com/models/open_router/deepseek-deepseek-chat-v3.1) [ML](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-70B-Instruct-Turbo)[Together AI](https://modelslab.com/models/together_ai) [Meta Llama 3.1 70B Instruct Turbo Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-70B-Instruct-Turbo) [Q3](https://modelslab.com/models/together_ai/Qwen-Qwen3.5-35B-A3B)[Together AI](https://modelslab.com/models/together_ai) [Qwen3.5 35B A3b Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3.5-35B-A3B) [QQ](https://modelslab.com/models/open_router/qwen-qwen3.5-flash-02-23)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3.5-Flash Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3.5-flash-02-23) About Meta: Llama Guard 4 12B --- Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM... ### Technical Specifications Model IDmeta-llama-llama-guard-4-12bCategoryLLM ModelsTaskText GenerationPrice$0.180000 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 Meta: Llama Guard 4 12B 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": "meta-llama-llama-guard-4-12b", "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/meta-llama/meta-llama-llama-guard-4-12b/api) for SDKs, code examples in Python, JavaScript, and more. ### Pricing Meta: Llama Guard 4 12B API costs $0.180000 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 [Learn more about Meta: Llama Guard 4 12B](https://modelslab.com/meta-llama-guard-4-12b) [Browse LLM Models](https://modelslab.com/models?feature=llmaster) [More from Meta Llama](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) Meta: Llama Guard 4 12B FAQ --- ### What is Meta: Llama Guard 4 12B? Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM... ### How do I use the Meta: Llama Guard 4 12B API? You can integrate Meta: Llama Guard 4 12B into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "meta-llama-llama-guard-4-12b" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does Meta: Llama Guard 4 12B cost? Meta: Llama Guard 4 12B costs $0.180000 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the Meta: Llama Guard 4 12B model ID? The model ID for Meta: Llama Guard 4 12B is "meta-llama-llama-guard-4-12b". Use this ID in your API requests to specify this model. ### Does Meta: Llama Guard 4 12B have a free tier? Yes, ModelsLab offers a free tier that lets you try Meta: Llama Guard 4 12B 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*