plugmyagent

Hetzner Inference API

AI & ML Free account (no card)

AuthenticationFree account (no card)
Rate limitFree while experimental: 500M input / 5M output tokens per 24h. No SLA, not for production.

Documentation: experiments.hetzner.com ยท Checked Oct 12, 2026

About

Hetzner's experimental inference API is one of the most generous free inference endpoints anywhere: OpenAI-compatible, serving Qwen3.6-35B with a 262k context window and vision support, with limits of 500M input and 5M output tokens per day. It is free while experimental with just a Hetzner account (no credit card), but there is no SLA and it is not for production. Perfect for prototyping agents and running free-tier coding agents at real scale.

Details

Free to start. You may need a free key, but no credit card.

Auth: Free account (no card)

Rate limit: Free while experimental: 500M input / 5M output tokens per 24h. No SLA, not for production.

Verified: 2026-10-12

Best for: developer automation

Read the docs Back to catalog

Setup

  1. Create a Hetzner account and open the inference console.
  2. Issue a free API token (no credit card).
  3. Point any OpenAI-compatible client at inference.hetzner.com/api/v1.
  4. Set the model to Qwen/Qwen3.6-35B-A3B-FP8.
  5. Build and prototype; move to a paid provider before production.
Sign up