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.

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.

Read the quickstart

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)

Run Llama Guard 3 on infrastructure you trust.

Deploy a worker, install Llama Guard 3, and start serving it through one private API.