Qwen3Guard

by Alibaba Moderation

Qwen3Guard is Alibaba's open safety classifier for prompts and replies, trained across 119 languages. It rates content safe, unsafe or controversial and names the category, from violence, illegal acts and sexual content to self-harm, personal data, politically sensitive topics and jailbreak attempts. The 0.6B size is the fastest and the 8B size the most accurate.

API model name
qwen3guard:0.6b
Context window
32K tokens
Sizes
0.6B, 4B, 8B
Licence
Apache 2.0

Run Qwen3Guard

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="qwen3guard:0.6b",
    input="Explain how to break into a locked car that belongs to someone else.",
)

print(result.results[0].flagged)

Run Qwen3Guard on infrastructure you trust.

Deploy a worker, install Qwen3Guard, and start serving it through one private API.