Qwen3Guard-Gen-0.6B

by Alibaba

Qwen3Guard-Gen-0.6B is the smallest generative model in Alibaba's Qwen3Guard family, a safety moderation series built on Qwen3 and trained on 1.19 million prompts and responses labelled for safety. Send a user prompt, or a prompt with a model's reply, and it answers in a fixed text format with a safety label and the categories that apply. Its three-tier labels add Controversial between Safe and Unsafe, so a deployment can decide how strict to be for content whose harm depends on context. Categories cover violence, non-violent illegal acts, sexual content, personal information, suicide and self-harm, unethical acts, politically sensitive topics, copyright violation and jailbreak attempts. When it checks a response, it also reports whether the reply was a refusal. Its small size suits high-volume or latency-sensitive screening of inputs and replies; Qwen also publishes 4B and 8B versions of the same classifier. It is a classifier, not a chat assistant: the answer is a label, and the policy that acts on it is yours. The context window is 32,768 tokens.

Pricing from—/ 1M input—/ 1M output33Kcontext

Call Qwen3Guard-Gen-0.6B on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Available routes

Qwen3Guard-Gen-0.6B runs on 1 route through the Opper gateway.

ProviderRegionZero data retentionTrainingInputOutputCache read
EUNo——Input price

Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by OVHcloud (France). See every Qwen model hosted in the EU.

Live routes and prices as JSON: api.opper.ai/v3/models?q=ovhcloud%2FQwen3Guard-Gen-0.6B

Key info

Input
Output
Features
Context window
33K
Max output
—
Input price
— /1M
Output price
— /1M
  • EU residency available
  • Zero data retention on pay-as-you-go
  • No training by default

Data handling per route

Each route hosting Qwen3Guard-Gen-0.6B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

OVHcloud — France🇫🇷

Zero data retention: nothing is logged or used for training. No training on customer data. EU.

Zero data retention
Yes. Nothing is logged or used for training.
Training
No training on customer data.
Logging
None
Transfer mechanism
Not applicable — data stays in EU

Get started

Call Qwen3Guard-Gen-0.6B through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Qwen3Guard-Gen-0.6B is a free model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "ovhcloud/Qwen3Guard-Gen-0.6B",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Use Qwen3Guard-Gen-0.6B in your apps

Pick your tool, then choose Qwen3Guard-Gen-0.6B to see how to run it through Opper.

Compare Qwen3Guard-Gen-0.6B with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Alibaba

Start building with 700+ models

One API key for every major provider, up and running in minutes.

Get startedView Documentation