Free Tier · verified Sep 5, 2026

Hetzner: Free experimental OpenAI-compatible inference

Hetzner's hosted inference experiment remains free while in experimental status. Live docs (last change 2026-07-24) expose OpenAI-compatible endpoints with Qwen/Qwen3.6-35B-A3B-FP8 and Qwen3.8-27B at $0.

PrototypingMultimodalOpenai Compatible

What you actually get

Eligibility
Anyone with an experiments.hetzner.com account; experimental status only — not for production.
Rate and usage limits
Per API key: 3M input and 60K output tokens per 60 seconds; 500M input and 5M output tokens per 24 hours.
Models
Qwen/Qwen3.6-35B-A3B-FP8
Card requirement
unknown
Regions
Global
After the free allowance
Requests are rate-limited. Hetzner does not promise continued availability.
Data and privacy catch
Check Hetzner's current experiment terms before sending sensitive data.

Do not treat this as guaranteed capacity

The provider describes this access as experimental, rotating, or subject to change. Build a fallback before using it in anything important.