{"slug": "hetzner-open-weights-inference-api", "title": "Hetzner: Open Weights Inference API", "summary": "Hetzner Online GmbH launched an Experiments platform offering a free, OpenAI-compatible inference API for an Open-Weight LLM and a hosted OpenClaw AI assistant, both running on Hetzner's own hardware in its data centres. The company invites all Hetzner customers to test the prototypes at no cost, with no guarantees, and warns users about data risks and lack of liability for OpenClaw's behaviour.", "body_md": "For internal use cases, we are constantly developing and testing new and exciting approaches that we’d love to share with you.\n\nTo give you access to our prototypes, ideas and experiments, we’ve launched the [Experiments platform](https://experiments.hetzner.com).\n\nWe invite all Hetzner customers to try out our solutions, which we host on our own hardware in our data centres. No guarantees, but no cost either.\n\nWe offer an inference API that provides access to an Open-Weight LLM via an OpenAI-compatible REST API. You can use the API with any OpenAI-compatible development environment and easily integrate it into your own projects.\n\nYou can find a setup guide for OpenCode in the [Community Tutorial](https://community.hetzner.com/tutorials/opencode-with-hetzner-inference-api-systemd-sandbox). We pre-configured the LLM, Open-Weight. The quality of the responses is probably not as good as that of the major providers, but it’s often sufficient for initial experiments.\n\nBuilding on the Inference API, our second experiment is an OpenClaw platform that we host entirely, including our own pre-configured models. You can configure your own OpenClaw exactly as you wish and also connect other inference providers. Try out the OpenClaw AI assistant as an alternative to Claude or ChatGPT and retain control over your data.\n\nA word on OpenClaw in particular and AI in general: be aware of the risks when you provide your data to OpenClaw. We have no influence over the OpenClaw code and accept no liability for OpenClaw’s behaviour. In the event of high demand, our experiments may no longer be available or may not perform as expected.\n\nBecause we do not create backups, you should back up your configurations separately and avoid setting up production environments on the Inference API.\n\nWe hope the Experiment Platform will provide us with both concrete feedback and opportunities to shape the project, as well as various types of metrics: How well does our approach scale?\n\nIs there a need for and interest in Software-as-a-Service offerings operated by us? Which (additional) features are particularly important to you? You can also deliberately test the limits in this experiment. This provides us with valuable data, showing, for example, what load our setup can withstand.\n\nPlease be sure to share any feedback, questions or experiences with us via a support request from within [Experiments](https://experiments.hetzner.com/support), or feel free to discuss them on the [Hetzner Forum](https://forum.hetzner.com/index.php?board/123-experiments/).", "url": "https://wpnews.pro/news/hetzner-open-weights-inference-api", "canonical_source": "https://docs.hetzner.com/general/company-and-policy/experiments/experiments-platform/", "published_at": "2026-08-11 18:02:08+00:00", "updated_at": "2026-08-11 18:13:18.619727+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "generative-ai", "ai-products", "ai-infrastructure"], "entities": ["Hetzner Online GmbH", "OpenAI", "OpenClaw", "OpenCode"], "alternates": {"html": "https://wpnews.pro/news/hetzner-open-weights-inference-api", "markdown": "https://wpnews.pro/news/hetzner-open-weights-inference-api.md", "text": "https://wpnews.pro/news/hetzner-open-weights-inference-api.txt", "jsonld": "https://wpnews.pro/news/hetzner-open-weights-inference-api.jsonld"}}