Meta: Llama Guard 4 12B

Meta: Llama Guard 4 12B

meta-llama · Released Apr 30, 2025
28
Our Score

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.

$0.18 / 1M Input Price
$0.18 / 1M Output Price
163,840 tokens Context Window
12B Parameters

Capabilities

Vision

Architecture

ModalityText + Image → Text
TokenizerOther
Parameters12B

Model Information

OpenRouter ID meta-llama/llama-guard-4-12b
Providermeta-llama
Release Date April 30, 2025
Context Length163,840 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.18 $0.000180
Output $0.18 $0.000180

Live Performance

Live endpoint metrics — refreshed every 30 minutes.

100%
Avg Uptime
163ms
Best Latency (TTFT)
17 tok/s
Best Throughput
2/2
Active Endpoints
Available via: DeepInfra, Together