Qwen3Guard-Gen-0.6B (beta, listed Free) by OVHcloud AI Endpoints

Call the OpenAI-compatible endpoint without a key: anonymous use is free at 2 requests a minute per IP and per model. With a key you get 400 RPM but pay per token.

Access
Free API tier
Free limits
2 RPM per IP (no key)
Modality
text
Credit card
Not required
Commercial use
Unclear, verify
Context window
32,768 tokens
Rate limit
2 RPM
Model ID
Qwen3Guard-Gen-0.6B
Base URL
https://oai.endpoints.kepler.ai.cloud.ovh.net/v1
Checked
Nov 11, 2026

Quickstart

curl https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions \
  -H "Authorization: Bearer $KEY" \
  -d '{"model":"Qwen3Guard-Gen-0.6B","messages":[{"role":"user","content":"hi"}]}'

Using this model in production?

We wire free-tier and open-weight models into production stacks: evals against your real inputs, failover, cost caps. Book a free 30-minute call.

Frequently asked

Is Qwen3Guard-Gen-0.6B (beta, listed Free) free?

Yes. OVHcloud AI Endpoints offers it as Free API tier with these limits: 2 RPM per IP (no key). No credit card is required.

Can I use Qwen3Guard-Gen-0.6B (beta, listed Free) commercially?

Commercial terms are not clearly documented. Check the provider's current terms before shipping.

How do I start using Qwen3Guard-Gen-0.6B (beta, listed Free)?

Call the OpenAI-compatible endpoint without a key: anonymous use is free at 2 requests a minute per IP and per model. With a key you get 400 RPM but pay per token.

Free monthly update

The monthly free-models update

What is newly free, what got rate-limited, and what to switch to. One email a month. Unsubscribe anytime.

Related free models