Llama Guard 4 12B
Meta developed Llama Guard 4 12B as a multimodal model specifically fine-tuned for content safety classification. It processes both text and image inputs to help identify and categorize content according to safety guidelines.
Llama Guard 4 12B specs and pricing
- Provider: Meta
- Released: April 30, 2025
- Context window: 164K tokens
- Max output: 16K tokens
- Input: images, text
- Output: text
- Price: $0.18 input / $0.18 output per 1M tokens
What Llama Guard 4 12B is good at
- Classifying text content for safety
- Analyzing images for potential policy violations
- Automating content moderation workflows
To-dos to try with Llama Guard 4 12B
- Scan this uploaded image to determine if it violates safety policies.
- Categorize the following text prompt based on standard safety classification labels.
- Evaluate a series of user-generated inputs to flag potentially harmful content.
FAQ
- What is the primary purpose of Llama Guard 4 12B? It is a specialized model designed for content safety classification and moderation.
- Can this model process images? Yes, Llama Guard 4 12B is a multimodal model capable of accepting both image and text inputs.
- How much does Llama Guard 4 12B cost? Llama Guard 4 12B costs $0.18 per million input tokens and $0.18 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.53 credits ($1 = 100 credits).
- What is the context window of Llama Guard 4 12B? Llama Guard 4 12B can read up to 164K tokens at once and write up to 16K tokens in one reply.
- Can I use Llama Guard 4 12B without coding? Yes. In todo.is you pick Llama Guard 4 12B as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.