--- title: "Hetzner Experiments Inference API free inference" description: "Free while the provider's public experiment remains active." canonical_url: "https://freeinferencing.com/provider/hetzner_experiments/" md_url: "https://freeinferencing.com/provider/hetzner_experiments.md" last_updated: "2026-09-19" --- # Hetzner Experiments Inference API > Free while the provider's public experiment remains active. ## Classification - **Directory:** Current - **Free access:** Experimental access - **Status:** Available now - **Confidence:** High - **Payment card:** No - **Account:** Required - **Equivalent paid value:** Up to $57,354.89/mo - **API endpoint:** `https://inference.hetzner.com/api/v1` ## Models mentioned - `Qwen/Qwen3.6-35B-A3B-FP8` - `Qwen3.8-27B` ## Limits and terms ```yaml window_seconds: 60 requests: 10 input_tokens: 4000000 output_tokens: 100000 scope: per_api_key ``` ## What happens to your prompts? **Private.** Hetzner documents no ordinary prompt/output retention, no content training right, and EU-hosted processing. Privacy is audited separately from price. Review the current governing terms before sending sensitive or regulated data. ## Data governance and agreements ```yaml data_governance: review_status: reviewed plan_scope: Hetzner Experiments Inference API, a best-effort experimental service for existing Hetzner customers. prompt_retention: Hetzner states it does not retain prompt or response content after processing unless legally compelled. response_retention: Same non-retention statement as prompts. ordinary_logging: Usage metadata is retained for operation and enforcement without prompt or response content. model_training: No retained inference content is available for ordinary model training, and no training right is disclosed for the experimental API. product_improvement: Service telemetry may support operation of the experiment; the product documentation does not authorize content-based improvement. human_or_operator_access: Transient access necessary to process a request is possible; retained content access is limited to a legal-compulsion exception. subprocessors_and_routing: Hetzner provides the hosted inference infrastructure in the EU under its terms and DPA; model licenses can separately restrict use of outputs. deletion_controls: Prompt and response content is not ordinarily retained. Account and personal-data rights are available through Hetzner's privacy and DPA procedures. caveat: This is a non-production experiment without an availability commitment. The legal-compulsion exception and retained usage metadata mean it is not a universal zero-data promise. data_handling: Usage metadata is retained, but prompt and response content is not retained absent legal compulsion. agreements: terms_and_conditions: https://www.hetzner.com/legal/terms-and-conditions privacy_policy: https://www.hetzner.com/legal/privacy-policy data_processing_agreement: https://www.hetzner.com/AV/DPA_en.pdf ``` ## Eligibility ```yaml account_required: true hetzner_customer_required: true payment_for_inference_required: false ``` ## API compatibility and modalities - **Compatibility:** OpenAI Models, OpenAI Completions, OpenAI Chat Completions - **Modalities:** Text generation ## Before you build with Hetzner Experiments Inference API ### Read the classification narrowly This record describes the bounded offer supported by evidence on 2026-09-19; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every account and region. “Experimental access” should be interpreted together with the Current directory placement, High confidence, No payment-card status, and the plan-specific sources below. ### Resolve the live model route The snapshot records 2 model IDs. Match the exact ID against the provider's current catalog before using it in code because zero-price routes, aliases, context limits, and feature support can rotate while an older documentation page remains online. ### Match the quota to the workload shape Translate the allowance into peak requests per minute, input and output tokens, concurrency, retries, and every daily or monthly ceiling that applies to the intended account. The first limit reached by the workload is the practical ceiling. A large token pool can still fail interactive bursts, and a high request limit can still fail long-context work. Include tool calls and retry traffic, test the largest realistic payload, and treat research, experimental, and community access as conditional on their eligibility and fair-use terms. ### Preserve billing and privacy boundaries The recorded payment-card requirement is No, and account access is required. Confirm both in the live signup flow, set provider-side budgets when charges are possible, and observe the balance or usage fields after a complete request. The prompt-handling classification is **Private** because Hetzner documents no ordinary prompt/output retention, no content training right, and EU-hosted processing. Re-read the terms for the exact route and plan before sending sensitive, regulated, or proprietary content. ### Follow the evidence, then re-check it This record links 11 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest and most specific governing document or live catalog when sources disagree. A dated finding can become stale even when the page remains online, so retain the source and snapshot that supported the decision and submit a correction when a provider changes a material term. ### Plan fallback without policy drift A fallback should preserve modality, context length, streaming, structured output, tools, safety controls, and data terms, not only API syntax. Decide which errors may retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. Rotating aliases and free pools can change behavior without changing the endpoint, so retain the response model field and test at least one substitute route before the primary offer becomes unavailable. ### Monitor the offer as a dependency Capture the model ID, response model, rate-limit headers, usage fields, latency, HTTP status, and provider request identifier. Watch authorization failure, quota exhaustion, catalog removal, policy revision, and balance movement as separate failure modes. Re-check the live catalog and governing sources on a schedule proportionate to the workload's importance, and keep an owner and exit path for any production dependency on volatile free capacity. ### Test one complete request before scaling Start with the smallest permitted request using the exact credential, model ID, endpoint, region, and account type intended for deployment. Record the status, headers, usage fields, response model, latency, and dashboard balance movement. Then exercise an invalid model, quota exhaustion, or rate limit so failure is explicit and cannot silently switch to a paid route. Validate streaming, structured output, and tool calls separately because a free model can expose fewer features than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and do not send sensitive data until the observed route matches the reviewed agreement. ## Primary sources - [Inference API](https://docs.hetzner.com/general/company-and-policy/experiments/inference/): Official Docs - [Experiments Platform](https://docs.hetzner.com/general/company-and-policy/experiments/experiments-platform/): Official Docs - [OpenCode with Hetzner Inference API](https://community.hetzner.com/tutorials/opencode-with-hetzner-inference-api-systemd-sandbox/): Official Tutorial - [Hetzner Terms and Conditions](https://www.hetzner.com/legal/terms-and-conditions): Official Terms - [Hetzner Privacy Policy](https://www.hetzner.com/legal/privacy-policy): Official Privacy - [Hetzner Data Processing Agreement](https://www.hetzner.com/AV/DPA_en.pdf): Official Dpa - [OpenRouter qwen/qwen3.8-27b](https://openrouter.ai/qwen/qwen3.8-27b): Router Pricing - [OpenRouter qwen/qwen3.6-35b-a3b](https://openrouter.ai/qwen/qwen3.6-35b-a3b): Router Pricing - [PyPI download stats for the official Hetzner Cloud python library](https://pypistats.org/packages/hcloud): Package Registry Stats - [2024 Stack Overflow Developer Survey technology section](https://survey.stackoverflow.co/2024/technology): Independent Survey - [About Hetzner Online](https://www.hetzner.com/unternehmen/ueber-uns/): Official About ## Sitemap See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.