{
 "id": "hetzner-inference-experiment",
 "provider": "hetzner",
 "provider_label": "Hetzner",
 "offer_type": "limited_free",
 "model": "Hetzner Inference Experiment (Qwen small models)",
 "model_key": "hetzner-inference-experiment",
 "family": "Hetzner",
 "detail": "Free-of-charge, OpenAI-spec hosted inference API on Hetzner's Experiments Platform. Explicitly experimental and volatile: large models (DeepSeek-V4-Flash, GLM-5.2, Kimi-K2.7-Code) were withdrawn within the first week, leaving small Qwen models. Numeric rate limits are not published on a readable surface (the docs page is CAPTCHA-gated).",
 "url": "https://llmpriceindex.smelterlabs.ai/free-access/hetzner-inference-experiment/",
 "verified_at": "2026-10-09",
 "ends_at": null,
 "active": true,
 "recheck_days": 7,
 "record_kind": "access_program",
 "status": "verified",
 "program_name": "Hetzner Inference Experiment",
 "models_detail": "On the Inference API docs page (2026-09-17): Qwen/Qwen3.6-35B-A3B-FP8 and Qwen3.8-27B, both 262,144-token context with text and image input. The models endpoint is the definitive list and the selection changes during the experiment; GLM-5.2, DeepSeek-V4-Flash-0731 and Kimi-K2.7-Code were served at launch and dropped when Hetzner paused large models in August 2026.",
 "free_terms": "Free hosted inference while the Inference API is in experimental status; Hetzner says it will notify users in advance by email if that status changes. Rate limits are applied per API key and the API returns HTTP 429 when any of them is exceeded, but as of 2026-09-23 the Inference API docs page no longer publishes the numeric request and token figures. Performance and availability are not guaranteed, requests can queue at peak, and the platform is not for production use.",
 "signup": "required; Hetzner account sign-in to the Hetzner Experiments Platform, then generate an auth token in the Inference tab at experiments.hetzner.com",
 "card": "not required: Hetzner's account-creation guide lists an email address, contact details and a billing address as the requirements, with adding a payment method only an optional later step",
 "region": "Hetzner states that it hosts the Experiments platform on its own hardware in its own data centres. The Inference API pages do not state which countries or regions that hardware sits in, and the only EU-based description in Hetzner's material refers to the earlier OpenClaw Experiment rather than the public Inference API. No user-region restriction is stated.",
 "data_treatment": "The Inference API FAQ states: \"We do only keep data that is necessary in order to track usage and (in the future) bill usage: request timestamps, token counts etc.\" It also states: \"We do not store the content of request and response and we do not plan on doing so in the future (unless some law requires us to do so).\" Hetzner's blog post on the experiment adds, \"We do not log any prompt data.\" No page states anything about using customer data for model training.",
 "clock": "Explicitly an experiment with fewer guarantees than mature products and no committed end date; scope was already reduced once, so treat as volatile.",
 "evidence_urls": [
  "https://www.hetzner.com/blog/inference-experiment/",
  "https://docs.hetzner.com/general/company-and-policy/experiments/inference/",
  "https://docs.hetzner.com/general/company-and-policy/experiments/experiments-platform/",
  "https://docs.hetzner.com/general/billing-and-account-management/account-getting-started/"
 ],
 "card_required": "no",
 "training_use": "no",
 "access_clock": "limited_undated",
 "signup_required": "yes",
 "access": {
  "setup_url": "https://experiments.hetzner.com/",
  "payment": "none",
  "limits": {
   "rpm": 10,
   "tpm": 4000000
  },
  "at_exhaustion": "blocked",
  "openai_compatible": "yes",
  "evidence": {
   "payment": {
    "quote": "As long as the Inference API remains in experimental status, it is free of charge. Should this status change, we will notify you in advance via email with detailed information.",
    "url": "https://docs.hetzner.com/general/company-and-policy/experiments/inference/"
   },
   "limits": {
    "quote": "Timeframe Input Tokens Output Tokens\n60s 4M 100k\nAdditionally, we enforce request-level rate-limits as follows:\nTimeframe Requests\n60s 10",
    "url": "https://docs.hetzner.com/general/company-and-policy/experiments/inference/"
   },
   "at_exhaustion": {
    "quote": "If you exceed any of the rate limits, the API will respond with HTTP Status Code 429.",
    "url": "https://docs.hetzner.com/general/company-and-policy/experiments/inference/"
   }
  }
 },
 "correction_terms_hash": "58f955bb2f751163",
 "overlay_applied": "2026-10-05",
 "bank_verified_at": "2026-09-01",
 "overdue_days": 0,
 "program_type": "limited_free",
 "state": "verified",
 "child_count": 0,
 "access_summary": {
  "allowance": "Not stated by the provider",
  "tightest_limit": "10 requests / min",
  "payment": "No payment needed",
  "unlock": "",
  "setup_url": "https://experiments.hetzner.com/"
 },
 "children": [],
 "generated": "2026-10-09T11:30:13+00:00",
 "provider_url": "https://www.hetzner.com/blog/inference-experiment/",
 "license": "CC BY 4.0"
}