Llama Guard 4 12B

About 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 inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated. Llama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Meta Model Lineup

Compare all models from Meta to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Spotlight

Other

Input: $0.18

Output: $0.18

Context: 131k

Qwen3 30B A3B

Alibaba Qwen

Input: $0.08

Output: $0.28

Context: 131k

Devstral Small 1.1

Mistral

Input: $0.07

Output: $0.28

Context: 131k

ERNIE 4.5 21B A3B Thinking

Baidu

Input: $0.07

Output: $0.28

Context: 131k

💡 Cheaper Alternatives

Same Brand (Meta)

Cross Brand

🚀 Quick Start

Get started with Llama Guard 4 12B API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="meta-llama/llama-guard-4-12b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision