Llama Guard 3
by Meta Moderation
Llama Guard 3 is Meta's safety classifier, fine-tuned to judge whether a prompt or a reply breaks a fixed hazard taxonomy covering violent and non-violent crime, sexual content, child safety, hate, self-harm, privacy and elections. The 1B size is built for fast text checks and names the categories it finds, making it a light first line of content filtering.
- Publisher
- Meta (opens in a new tab)
- API model name
- llama-guard3:1b
- Context window
- 128K tokens
- Sizes
- 1B, 8B
- Licence
- llama3.2
Run Llama Guard 3
Install it on a Pendra worker, then call it through our SDK with your pdr_sk_ API key.
from pendra import Pendra
client = Pendra(api_key="pdr_sk_...")
result = client.moderations.create(
model="llama-guard3:1b",
input="Explain how to break into a locked car that belongs to someone else.",
)
print(result.results[0].flagged)
Related models
Llama 3.3
Meta
llama3.3
Meta’s 70B workhorse
Chat · Tools
Llama 4 Scout
Meta
llama4-scout
Llama 4 Scout is Meta's natively-multimodal mixture-of-experts model, activating 17B parameters per token from a larger expert pool for efficient inference. It reads images as well as text and supports an exceptionally long, million-token context, aimed at long-document and multimodal workloads.
Chat · Vision · Tools
Muse Glimmer
Meta
muse-glimmer
Muse Glimmer is Meta Superintelligence Labs' compact multimodal model — a dense vision-language transformer distilled for agentic work on consumer hardware. It pairs a text decoder with a dedicated perception encoder to read images alongside text, and targets fast local inference across a 128K-token context.
Chat · Vision · Tools · Thinking
Run Llama Guard 3 on infrastructure you trust.
Deploy a worker, install Llama Guard 3, and start serving it through one private API.