Qwen3Guard: Real-time Safety for Your Token Stream
Source
Qwen Team
Author
Qwen Team
Date
Terms in this piece · Glossary
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
guardrails — The checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.
Why it matters
Qwen3Guard is an open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → guardrail model that classifies both prompts and responses in real time at the tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition →-stream level, with graded risk levels and category labels across English, Chinese, and multilingual inputs — useful if you need self-hostable moderation instead of relying solely on a closed API like OpenAI's guardrailsThe checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.Full definition →.
Key quotes
“We are excited to introduce Qwen3Guard, the first safety guardrail model in the Qwen family.”