{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-07-28T06:20:51.496Z","headline":"Hetzner 正在开发 LLM 推理服务","description":"欧洲云服务商 Hetzner 正在开发一项名为 Sliplane 的 LLM 推理服务。该服务旨在为用户提供基于 Hetzner 基础设施的模型推理能力，目前尚未公布具体上线时间、支持的模型列表或定价信息。","url":"https://www.aioga.com/news/cmrz6k3vn0051rox8yn5qrk2u/","mainEntityOfPage":"https://www.aioga.com/news/cmrz6k3vn0051rox8yn5qrk2u/","datePublished":"2026-07-24T14:19:40.181Z","dateModified":"2026-07-24T14:19:40.181Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://sliplane.io/blog/hetzner-inference","https://aihot.virxact.com/items/cmrz6k3vn0051rox8yn5qrk2u"],"canonicalUrl":"https://www.aioga.com/news/cmrz6k3vn0051rox8yn5qrk2u/","directAnswer":{"@type":"Answer","text":"Aioga 编辑摘要：欧洲云服务商 Hetzner 正在开发一项名为 Sliplane 的 LLM 推理服务。 Aioga 将其归入「产品更新」方向，重点关注它对真实使用和行业竞争的影响。","url":"https://www.aioga.com/news/cmrz6k3vn0051rox8yn5qrk2u/","dateCreated":"2026-07-24T14:19:40.181Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"sliplane.io source article","url":"https://sliplane.io/blog/hetzner-inference","datePublished":"2026-07-24T14:19:40.181Z","provider":{"@type":"Organization","name":"sliplane.io","url":"https://sliplane.io/blog/hetzner-inference"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmrz6k3vn0051rox8yn5qrk2u","datePublished":"2026-07-24T14:19:40.181Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmrz6k3vn0051rox8yn5qrk2u"}}],"aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","originalPublisher":{"name":"sliplane.io","url":"https://sliplane.io/blog/hetzner-inference"},"article":{"id":"cmrz6k3vn0051rox8yn5qrk2u","slug":"cmrz6k3vn0051rox8yn5qrk2u","url":"https://www.aioga.com/news/cmrz6k3vn0051rox8yn5qrk2u/","title":"Hetzner 正在开发 LLM 推理服务","title_en":"","summary":"欧洲云服务商 Hetzner 正在开发一项名为 Sliplane 的 LLM 推理服务。该服务旨在为用户提供基于 Hetzner 基础设施的模型推理能力，目前尚未公布具体上线时间、支持的模型列表或定价信息。","source":"Hacker News 热门（buzzing.cc 中文翻译）","sourceUrl":"https://sliplane.io/blog/hetzner-inference","aiHotUrl":"https://aihot.virxact.com/items/cmrz6k3vn0051rox8yn5qrk2u","publishedAt":"2026-07-24T14:19:40.181Z","category":"产品更新","score":40,"selected":false,"articleBody":["Hetzner is experimenting with LLM inference.","That is not a sentence I expected to write, but I think it is pretty interesting :)","Before anyone moves their production AI workloads to Hetzner: this is very much an experiment . There is no billing, no SLA, no production guarantee, and currently only one model. Hetzner says it wants to learn whether people actually want this, how the system scales, which features matter, and what kind of load it can handle.","So this is not a finished product launch. It is Hetzner putting something early in front of users and seeing what happens. I really like that approach.","Hetzner Inference ：https://experiments.hetzner.com is an OpenAI-compatible API running on Hetzner's own infrastructure. You create an API token in the Experiments dashboard, point an OpenAI client at Hetzner's base URL, and use it like most other inference APIs.","Right now, the only available model is Qwen/Qwen3.6-35B-A3B-FP8 ：https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8. It is a 35-billion-parameter Mixture-of-Experts model with 3 billion active parameters. It accepts text and images, has a 262K context window, and uses FP8-quantized weights.","That is a perfectly reasonable model for an experiment. It is small enough to serve without a ridiculous GPU cluster, but still useful enough to test the API with real workloads.","Hetzner also published a short tutorial for connecting OpenCode to the API ：https://community.hetzner.com/tutorials/opencode-with-hetzner-inference-api-systemd-sandbox/, if you want to try it without writing any code.","Because the API is OpenAI-compatible, there is almost nothing special about the integration:","The enable_thinking option is worth mentioning. Without it, the model can spend a surprising amount of the completion budget reasoning before it returns a visible answer. The option worked in my tests, but it is not documented by Hetzner, so I would not build anything important around that exact request shape yet.","I ran a few small tests on July 23, 2026. I do not want to turn this post into a giant benchmark report, because the product is experimental and a benchmark against it will probably age badly. But the rough numbers were:","That is fast! It is also just one test from one client at one point in time. It is not an SLA, and it says almost nothing about what happens when many people use the service at once.","The model itself was roughly what I expected. It followed most formatting and retrieval instructions, handled an image correctly, and failed two very simple arithmetic questions. So: a small, slightly shitty LLM :D","The Qwen endpoint is fun, but I do not think the current model is the interesting part.","The interesting part is why Hetzner is testing inference in the first place.","Everything from here on is purely my speculation. I have no insider information, and nobody at Hetzner told me what they are planning. I am just looking at the product and trying to connect a few dots.","Open-weight inference is a commodity market. Everyone can download the same weights, run more or less the same serving software, and expose an OpenAI-compatible API. Switching providers is also easy, especially with products like OpenRouter or LiteLLM for those you self-host.","That makes it hard to build huge margins unless you have some kind of advantage. Usually that means:","Hetzner is very good at buying hardware, putting it into its own data centers, and operating it with a brutally efficient cost structure. That is basically the whole company. If anyone can turn inference into another low-margin infrastructure product, Hetzner is at least a believable candidate.","There is also a nice utilization story here. A rented bare-metal GPU belongs to one customer, whether that customer uses it or not. An inference API can share GPU capacity across many users and keep the hardware busy. If Hetzner has spare GPU capacity — or plans to build a much larger GPU fleet — an inference product could help turn that capacity into revenue.","Again, I have no idea whether this is actually what they are doing. It would just make economic sense to me.","This is where I am not yet convinced.","Hetzner's current public dedicated GPU server lineup ：https://docs.hetzner.com/robot/dedicated-server/server-lines/gpu-server/ uses two GPU types:","Those are capable GPUs, and the 96 GB RTX PRO 6000 is a pretty nice inference machine for small and medium-sized models. The FP8 files for Hetzner's current Qwen model are around 38 GB, with actual VRAM use landing somewhere above that depending on context length, cache size, and serving setup.","But these are workstation GPUs, not the dense multi-GPU systems you need for the really large open models.","Take GLM-5 ：https://huggingface.co/zai-org/GLM-5 as an extreme example. It has 754 billion parameters, and the official serving recipe splits it across eight GPUs. Even with aggressive quantization, you are talking about hundreds of gigabytes of VRAM. Realistically, that is B200/B300-class hardware, or something similar, with very fast links between multiple GPUs.","Hetzner does not currently offer that kind of hardware in its public bare-metal lineup.","Of course, that does not tell us what sits behind the experimental API. Hetzner may use completely different internal hardware, and a public inference product does not have to mirror its dedicated-server catalogue.","Still, this is the part I am watching.","If Hetzner keeps serving one or two smaller models, I do not really see it becoming an important inference provider. That would be a cool experiment, but not much more.","If this experiment is the first step toward larger GPU clusters, a proper model catalogue, and B200/B300-class hardware, then it gets much more interesting. Hetzner already has the data centers, network, hardware experience, European positioning, and reputation for aggressive pricing. That combination could make it a serious competitor.","For now, the API is fast, free, and fun to try. For me, the interesting question isn't which small model they add next, but whether Hetzner invests in the hardware needed to serve the big ones.","Jonas Scholz is one of the co-founders of Sliplane, where he focuses mainly on infrastructure and system reliability.","Sliplane is a cloud platform that makes deploying and scaling your apps simple. Launch in minutes and grow as you go, containers included.","Sliplane makes it simple to deploy and scale your apps in the cloud. Start with a container or your favorite framework and grow from there. Try it now and get started in minutes!","Sliplane is not associated with Docker Inc. or any of its products. Prices do not include VAT."],"articleImages":[{"sourceUrl":"https://sliplane.io/images/blog/hetzner-inference/cover.webp","alt":"Hetzner Inference: First Look","afterParagraph":0,"url":"/media/articles/cmrz6k3vn0051rox8yn5qrk2u/e3fb99c95d4f4da3.webp"},{"sourceUrl":"https://sliplane.io/images/people/jonas.webp","alt":"Jonas Scholz - Co-Founder von sliplane.io","afterParagraph":0,"url":"/media/articles/cmrz6k3vn0051rox8yn5qrk2u/68585d7da2a458b2.webp"},{"sourceUrl":"https://sliplane.io/images/blog/hetzner-inference/inference.webp","alt":"The Hetzner Experiments inference dashboard","afterParagraph":6,"url":"/media/articles/cmrz6k3vn0051rox8yn5qrk2u/602da50fef3be14b.webp"}],"mediaStatus":"ok","articleBodyZh":["Hetzner 正在进行大语言模型推理实验。","这不是我预期会写的一句话，但我觉得这非常有趣 :)","在任何人将他们的生产 AI 工作负载迁移到 Hetzner 之前：这完全是一次实验。目前没有计费、没有 SLA、没有生产保证，而且目前只有一个模型。Hetzner 表示，它想了解人们是否真的需要这个系统、系统的扩展性、哪些功能重要，以及它能承受什么样的负载。","所以这不是一个完成的产品发布。这是 Hetzner 把一些早期的东西展示给用户，并观察会发生什么。我非常喜欢这种方法。","Hetzner 推理：https://experiments.hetzner.com 是一个与 OpenAI 兼容的 API，运行在 Hetzner 自己的基础设施上。你可以在实验仪表板中创建一个 API 令牌，将 OpenAI 客户端指向 Hetzner 的基础 URL，并像使用其他推理 API 一样使用它。","目前，唯一可用的模型是 Qwen/Qwen3.6-35B-A3B-FP8：https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8。它是一个拥有 350 亿参数的混合专家模型，其中 30 亿为活跃参数。它可以接受文本和图像输入，拥有 262K 的上下文窗口，并使用 FP8 量化权重。","对于一次实验来说，这个模型是完全合理的。它足够小，不需要庞大的 GPU 集群就可以提供服务，但又足够有用，可以用真实工作负载测试 API。","Hetzner 还发布了一个简短的教程，介绍如何将 OpenCode 连接到该 API：https://community.hetzner.com/tutorials/opencode-with-hetzner-inference-api-systemd-sandbox/，如果你想在不写任何代码的情况下尝试。","因为该 API 与 OpenAI 兼容，所以集成几乎没有特别之处：","值得一提的是 enable_thinking 选项。没有它，模型在返回可见答案之前可能会消耗大量推理预算。这个选项在我的测试中有效，但 Hetzner 没有文档记录，所以我不会在关键项目中依赖这个确切的请求形式。","我在 2026 年 7 月 23 日进行了几次小测试。我不想把这篇文章变成一个巨大的基准测试报告，因为该产品处于实验阶段，对其进行基准测试可能很快就过时。但粗略数据如下：","那也太快了！这也只是某个客户在某个时间点做的一个测试。它不是服务水平协议（SLA），而且几乎没有说明多人同时使用服务时会发生什么。","模型本身大致符合我的预期。它遵循了大多数格式和检索指令，正确处理了一张图片，但在两个非常简单的算术题上失败了。所以：一个小型、略微粗糙的语言模型 :D","Qwen 接口很有趣，但我认为当前的模型不是有趣的部分。","有趣的部分在于 Hetzner 为什么要测试推理（inference）。","从这里开始的一切纯属我的猜测。我没有内部信息，也没有 Hetzner 的任何人告诉我他们的计划。我只是看了这个产品并试图把一些点连起来。","开放权重推理是一个商品市场。每个人都可以下载相同的权重，运行或多或少相同的服务软件，并提供兼容 OpenAI 的 API。切换提供商也很容易，尤其是对于自托管的人来说，有 OpenRouter 或 LiteLLM 这样的产品。","这使得要建立巨额利润变得困难，除非你有某种优势。通常这意味着：","Hetzner 非常擅长购买硬件，将其投入自有数据中心，并以极为高效的成本结构运营。这基本上就是整个公司。如果有人可以将推理变成另一个低利润的基础设施产品，Hetzner 至少是一个可信的候选者。","这里还有一个不错的利用率故事。租用的裸机 GPU 属于一个客户，不管该客户是否使用它。推理 API 可以在多个用户之间共享 GPU 容量，让硬件保持忙碌。如果 Hetzner 有多余的 GPU 容量——或者计划建设更大规模的 GPU 阵列——推理产品可以帮助将这些容量转化为收入。","同样，我不知道他们是否真的在做这些。对我来说，这只是符合经济逻辑。","在这一点上，我还没有被说服。","Hetzner 当前公开的专用 GPU 服务器系列：https://docs.hetzner.com/robot/dedicated-server/server-lines/gpu-server/ 使用两种 GPU 类型：","那些都是性能很强的 GPU，而 96 GB 的 RTX PRO 6000 对于小型和中型模型来说，是一台相当不错的推理机器。Hetzner 当前的 Qwen 模型的 FP8 文件大约有 38 GB，实际的显存使用会根据上下文长度、缓存大小和服务设置而有所增加。","但这些是工作站 GPU，而不是你进行真正大型开放模型所需的高密度多 GPU 系统。","以 GLM-5 为极端例子：https://huggingface.co/zai-org/GLM-5。它有 7540 亿参数，官方的部署方案是将其分布在八块 GPU 上。即使进行激进量化，也可能需要数百 GB 的显存。实际上，这类硬件属于 B200/B300 级别，或者类似配置，且多 GPU 之间需要非常快的互联。","Hetzner 目前在其公开裸机产品中并不提供这种硬件。","当然，这并不能告诉我们实验性 API 背后使用了什么硬件。Hetzner 可能使用完全不同的内部硬件，而且一个公共推理产品不必与其专用服务器目录一致。","不过，这正是我关注的部分。","如果 Hetzner 只提供一两个较小的模型，我确实看不到它会成为一个重要的推理提供商。那可能是一个有趣的实验，但不会更进一步。","如果这个实验是迈向更大 GPU 集群、完整模型目录以及 B200/B300 级别硬件的第一步，那么就会变得更有趣。Hetzner 已经拥有数据中心、网络、硬件经验、欧洲的地理位置优势，以及激进定价的声誉。这种组合可能让它成为一个真正的竞争者。","目前，API 运行快速、免费且有趣。对我来说，有趣的问题不是他们下一个添加哪一个小模型，而是 Hetzner 是否会投资于服务大型模型所需的硬件。","Jonas Scholz 是 Sliplane 的联合创始人之一，他主要关注基础设施和系统可靠性。","Sliplane 是一个云平台，使部署和扩展你的应用变得简单。几分钟即可启动，并随需扩展，包括容器功能。","Sliplane 让您可以轻松在云中部署和扩展应用程序。从一个容器或您喜欢的框架开始，然后逐步扩展。立即试用，几分钟即可开始！","Sliplane 与 Docker 公司或其任何产品无关。价格不含增值税。"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"Aioga 编辑摘要：欧洲云服务商 Hetzner 正在开发一项名为 Sliplane 的 LLM 推理服务。 Aioga 将其归入「产品更新」方向，重点关注它对真实使用和行业竞争的影响。","background":"背景分析：产品与工具类动态的价值取决于它是否解决明确场景、能否进入工作流，以及交付、价格和数据安全是否可接受。","viewpoint":"Aioga 判断：这条动态更适合作为行业观察信号，当前信息足以建立线索，但不足以推导长期结论。","implications":"影响分析：对相关团队而言，短期应先核对来源、可用范围和实际成本，再判断是否值得接入或跟进。","nextStep":"后续观察：继续观察产品是否开放使用、用户反馈、定价、集成能力和后续版本更新。","evidenceRefs":["title","summary","articleBody"],"confidence":"medium","status":"published","aiGenerated":false,"autoApproved":true,"generatedBy":"rule-safe-fallback","generatedAt":"2026-07-28T06:29:10.543Z","sourceHash":"fea8edbb2fe7274e","validation":{"passed":true,"mode":"rule-safe-fallback","checks":["schema","length","source-attribution","no-html"]}},"tags":["产品更新","Hacker News 热门（buzzing.cc 中文翻译）"],"translations":{"zh-CN":{"title":"Hetzner 正在开发 LLM 推理服务","summary":"欧洲云服务商 Hetzner 正在开发一项名为 Sliplane 的 LLM 推理服务。该服务旨在为用户提供基于 Hetzner 基础设施的模型推理能力，目前尚未公布具体上线时间、支持的模型列表或定价信息。","category":"产品更新","source":"sliplane.io","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner 正在开发 LLM 推理服务 - Aioga AI资讯","description":"欧洲云服务商 Hetzner 正在开发一项名为 Sliplane 的 LLM 推理服务。该服务旨在为用户提供基于 Hetzner 基础设施的模型推理能力，目前尚未公布具体上线时间、支持的模型列表或定价信息。","url":"https://www.aioga.com/news/cmrz6k3vn0051rox8yn5qrk2u/"},"en":{"title":"Hetzner is developing an LLM inference service","summary":"European cloud service provider Hetzner is developing an LLM inference service called Sliplane. The service aims to provide users with model inference capabilities based on Hetzner's infrastructure. The specific launch time, supported model list, and pricing information have not yet been announced.","category":"Products","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner is developing an LLM inference service - Aioga AI News","description":"European cloud service provider Hetzner is developing an LLM inference service called Sliplane. The service aims to provide users with model inference capabilities based on Hetzner...","url":"https://www.aioga.com/en/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:43:04.557Z"},"ja":{"title":"Hetzner は LLM 推論サービスを開発しています","summary":"ヨーロッパのクラウドサービスプロバイダー Hetzner は、Sliplane と呼ばれる LLM 推論サービスの開発を進めています。このサービスはユーザーに Hetzner のインフラストラクチャに基づくモデル推論能力を提供することを目的としており、現在のところ具体的なリリース日時、対応モデルのリスト、料金情報は公表されていません。","category":"製品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner は LLM 推論サービスを開発しています - Aioga AIニュース","description":"ヨーロッパのクラウドサービスプロバイダー Hetzner は、Sliplane と呼ばれる LLM 推論サービスの開発を進めています。このサービスはユーザーに Hetzner のインフラストラクチャに基づくモデル推論能力を提供することを目的としており、現在のところ具体的なリリース日時、対応モデルのリスト、料金情報は公表されていません。","url":"https://www.aioga.com/ja/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:43:17.776Z"},"ko":{"title":"Hetzner가 LLM 추론 서비스를 개발하고 있습니다","summary":"유럽 클라우드 서비스 제공업체 Hetzner가 Sliplane이라는 이름의 LLM 추론 서비스를 개발하고 있습니다. 이 서비스는 사용자가 Hetzner 인프라를 기반으로 모델 추론 기능을 제공받을 수 있도록 하는 것을 목표로 하고 있으며, 현재 구체적인 출시 시간, 지원되는 모델 목록 또는 가격 정보는 공개되지 않았습니다.","category":"제품 업데이트","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner가 LLM 추론 서비스를 개발하고 있습니다 - Aioga AI 뉴스","description":"유럽 클라우드 서비스 제공업체 Hetzner가 Sliplane이라는 이름의 LLM 추론 서비스를 개발하고 있습니다. 이 서비스는 사용자가 Hetzner 인프라를 기반으로 모델 추론 기능을 제공받을 수 있도록 하는 것을 목표로 하고 있으며, 현재 구체적인 출시 시간, 지원되는 모델 목록 또는 가격 정보는 공개되지 않았습니다...","url":"https://www.aioga.com/ko/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:43:59.598Z"},"es":{"title":"Hetzner está desarrollando un servicio de inferencia LLM","summary":"El proveedor de servicios en la nube europeo Hetzner está desarrollando un servicio de inferencia LLM llamado Sliplane. Este servicio tiene como objetivo proporcionar a los usuarios capacidades de inferencia de modelos basadas en la infraestructura de Hetzner, y hasta ahora no se ha anunciado la fecha de lanzamiento, la lista de modelos compatibles ni la información de precios.","category":"Productos","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner está desarrollando un servicio de inferencia LLM - Aioga Noticias de IA","description":"El proveedor de servicios en la nube europeo Hetzner está desarrollando un servicio de inferencia LLM llamado Sliplane. Este servicio tiene como objetivo proporcionar a los usuario...","url":"https://www.aioga.com/es/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:43:57.041Z"},"fr":{"title":"Hetzner développe un service d'inférence LLM","summary":"Le fournisseur de services cloud européen Hetzner développe un service d'inférence LLM nommé Sliplane. Ce service vise à fournir aux utilisateurs des capacités d'inférence de modèles basées sur l'infrastructure de Hetzner. À ce jour, la date de mise en ligne, la liste des modèles supportés et les informations tarifaires n'ont pas encore été annoncées.","category":"Produits","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner développe un service d'inférence LLM - Aioga Actualités IA","description":"Le fournisseur de services cloud européen Hetzner développe un service d'inférence LLM nommé Sliplane. Ce service vise à fournir aux utilisateurs des capacités d'inférence de modèl...","url":"https://www.aioga.com/fr/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:44:35.786Z"},"de":{"title":"Hetzner entwickelt einen LLM-Inferenzdienst","summary":"Der europäische Cloud-Dienstleister Hetzner entwickelt einen LLM-Inferenzdienst namens Sliplane. Dieser Dienst soll den Nutzern Modellinferenz auf Basis der Hetzner-Infrastruktur ermöglichen. Der konkrete Starttermin, die unterstützten Modelle oder Preisinformationen wurden bisher noch nicht bekanntgegeben.","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner entwickelt einen LLM-Inferenzdienst - Aioga KI-News","description":"Der europäische Cloud-Dienstleister Hetzner entwickelt einen LLM-Inferenzdienst namens Sliplane. Dieser Dienst soll den Nutzern Modellinferenz auf Basis der Hetzner-Infrastruktur e...","url":"https://www.aioga.com/de/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:44:34.329Z"},"pt-BR":{"title":"Hetzner está desenvolvendo um serviço de inferência LLM","summary":"O provedor de serviços em nuvem europeu Hetzner está desenvolvendo um serviço de inferência LLM chamado Sliplane. Este serviço tem como objetivo fornecer aos usuários capacidades de inferência de modelos baseadas na infraestrutura da Hetzner, e até o momento não foram divulgadas informações sobre a data de lançamento, a lista de modelos suportados ou os preços.","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner está desenvolvendo um serviço de inferência LLM - Aioga Notícias de IA","description":"O provedor de serviços em nuvem europeu Hetzner está desenvolvendo um serviço de inferência LLM chamado Sliplane. Este serviço tem como objetivo fornecer aos usuários capacidades d...","url":"https://www.aioga.com/pt-BR/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:45:20.347Z"},"ru":{"title":"Hetzner разрабатывает сервис вывода LLM","summary":"Европейский облачный провайдер Hetzner разрабатывает сервис для вывода LLM под названием Sliplane. Этот сервис предназначен для предоставления пользователям возможностей инференса моделей на инфраструктуре Hetzner. Конкретная дата запуска, список поддерживаемых моделей и информация о ценах пока не объявлены.","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner разрабатывает сервис вывода LLM - Aioga Новости ИИ","description":"Европейский облачный провайдер Hetzner разрабатывает сервис для вывода LLM под названием Sliplane. Этот сервис предназначен для предоставления пользователям возможностей инференса...","url":"https://www.aioga.com/ru/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:45:12.352Z"},"ar":{"title":"Hetzner正在开发LLM推理服务","summary":"مزود الخدمات السحابية الأوروبي Hetzner يعمل على تطوير خدمة استدلال LLM تُسمى Sliplane. تهدف هذه الخدمة إلى تزويد المستخدمين بقدرات استدلال النماذج بناءً على بنية Hetzner التحتية، ولم يتم بعد الإعلان عن الوقت المحدد للإطلاق أو قائمة النماذج المدعومة أو معلومات التسعير.","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner正在开发LLM推理服务 - Aioga أخبار الذكاء الاصطناعي","description":"مزود الخدمات السحابية الأوروبي Hetzner يعمل على تطوير خدمة استدلال LLM تُسمى Sliplane. تهدف هذه الخدمة إلى تزويد المستخدمين بقدرات استدلال النماذج بناءً على بنية Hetzner التحتية، و...","url":"https://www.aioga.com/ar/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:45:59.385Z"},"hi":{"title":"Hetzner LLM अनुवाद सेवा विकसित कर रहा है","summary":"यूरोपीय क्लाउड सेवा प्रदाता Hetzner एक LLM अनुमान सेवा नामक Sliplane विकसित कर रहा है। यह सेवा उपयोगकर्ताओं को Hetzner इन्फ्रास्ट्रक्चर पर आधारित मॉडल अनुमान क्षमता प्रदान करने का उद्देश्य रखती है, वर्तमान में इसके लॉन्च की विशिष्ट समय, समर्थित मॉडल सूची या मूल्य जानकारी घोषित नहीं की गई है।","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner LLM अनुवाद सेवा विकसित कर रहा है - Aioga AI समाचार","description":"यूरोपीय क्लाउड सेवा प्रदाता Hetzner एक LLM अनुमान सेवा नामक Sliplane विकसित कर रहा है। यह सेवा उपयोगकर्ताओं को Hetzner इन्फ्रास्ट्रक्चर पर आधारित मॉडल अनुमान क्षमता प्रदान करने का...","url":"https://www.aioga.com/hi/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:45:58.752Z"},"it":{"title":"Hetzner sta sviluppando un servizio di inferenza LLM","summary":"Il fornitore di servizi cloud europeo Hetzner sta sviluppando un servizio di inferenza LLM chiamato Sliplane. Il servizio mira a fornire agli utenti capacità di inferenza dei modelli basate sull'infrastruttura di Hetzner; al momento non sono ancora state rese note la data di lancio, l'elenco dei modelli supportati o le informazioni sui prezzi.","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner sta sviluppando un servizio di inferenza LLM - Aioga Notizie IA","description":"Il fornitore di servizi cloud europeo Hetzner sta sviluppando un servizio di inferenza LLM chiamato Sliplane. Il servizio mira a fornire agli utenti capacità di inferenza dei model...","url":"https://www.aioga.com/it/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:46:45.397Z"},"nl":{"title":"Hetzner ontwikkelt een LLM-inferentieservice","summary":"De Europese cloudprovider Hetzner ontwikkelt een LLM-inferentieservice genaamd Sliplane. Deze service is bedoeld om gebruikers modelinference-mogelijkheden te bieden op basis van de infrastructuur van Hetzner. Op dit moment zijn de specifieke lanceringsdatum, de lijst van ondersteunde modellen en prijsinformatie nog niet bekendgemaakt.","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner ontwikkelt een LLM-inferentieservice - Aioga AI-nieuws","description":"De Europese cloudprovider Hetzner ontwikkelt een LLM-inferentieservice genaamd Sliplane. Deze service is bedoeld om gebruikers modelinference-mogelijkheden te bieden op basis van d...","url":"https://www.aioga.com/nl/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:46:40.022Z"},"tr":{"title":"Hetzner, LLM çıkarım hizmeti geliştiriyor","summary":"Avrupa bulut hizmet sağlayıcısı Hetzner, Sliplane adlı bir LLM çıkarım servisi geliştiriyor. Bu servis, kullanıcıların Hetzner altyapısına dayalı model çıkarım yeteneklerinden yararlanmalarını sağlamayı amaçlıyor; şu anda belirli bir lansman zamanı, desteklenen model listesi veya fiyat bilgisi açıklanmadı.","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner, LLM çıkarım hizmeti geliştiriyor - Aioga AI Haberleri","description":"Avrupa bulut hizmet sağlayıcısı Hetzner, Sliplane adlı bir LLM çıkarım servisi geliştiriyor. Bu servis, kullanıcıların Hetzner altyapısına dayalı model çıkarım yeteneklerinden yara...","url":"https://www.aioga.com/tr/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:47:23.840Z"},"vi":{"title":"Hetzner đang phát triển dịch vụ suy luận LLM","summary":"Nhà cung cấp dịch vụ đám mây châu Âu Hetzner đang phát triển một dịch vụ suy luận LLM có tên gọi Sliplane. Dịch vụ này nhằm cung cấp cho người dùng khả năng suy luận mô hình dựa trên cơ sở hạ tầng của Hetzner, hiện vẫn chưa công bố thời gian ra mắt cụ thể, danh sách các mô hình được hỗ trợ hoặc thông tin định giá.","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner đang phát triển dịch vụ suy luận LLM - Tin tức AI Aioga","description":"Nhà cung cấp dịch vụ đám mây châu Âu Hetzner đang phát triển một dịch vụ suy luận LLM có tên gọi Sliplane. Dịch vụ này nhằm cung cấp cho người dùng khả năng suy luận mô hình dựa tr...","url":"https://www.aioga.com/vi/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:47:23.112Z"},"id":{"title":"Hetzner sedang mengembangkan layanan inferensi LLM","summary":"Penyedia layanan cloud Eropa Hetzner sedang mengembangkan layanan inferensi LLM bernama Sliplane. Layanan ini bertujuan untuk memberikan kemampuan inferensi model berbasis infrastruktur Hetzner kepada pengguna, saat ini belum diumumkan waktu peluncuran, daftar model yang didukung, atau informasi harga secara spesifik.","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner sedang mengembangkan layanan inferensi LLM - Berita AI Aioga","description":"Penyedia layanan cloud Eropa Hetzner sedang mengembangkan layanan inferensi LLM bernama Sliplane. Layanan ini bertujuan untuk memberikan kemampuan inferensi model berbasis infrastr...","url":"https://www.aioga.com/id/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:48:02.123Z"},"th":{"title":"Hetzner กำลังพัฒนาบริการการให้เหตุผล LLM","summary":"ผู้ให้บริการคลาวด์ยุโรป Hetzner กำลังพัฒนาบริการการสืบสวน LLM ที่ชื่อว่า Sliplane บริการนี้มีเป้าหมายเพื่อมอบความสามารถในการสืบสวนโมเดลให้กับผู้ใช้บนโครงสร้างพื้นฐานของ Hetzner ปัจจุบันยังไม่เปิดเผยเวลาที่จะเปิดใช้ รายชื่อโมเดลที่รองรับ หรือข้อมูลราคา","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner กำลังพัฒนาบริการการให้เหตุผล LLM - ข่าว AI Aioga","description":"ผู้ให้บริการคลาวด์ยุโรป Hetzner กำลังพัฒนาบริการการสืบสวน LLM ที่ชื่อว่า Sliplane บริการนี้มีเป้าหมายเพื่อมอบความสามารถในการสืบสวนโมเดลให้กับผู้ใช้บนโครงสร้างพื้นฐานของ Hetzner ปัจ...","url":"https://www.aioga.com/th/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:48:06.437Z"},"pl":{"title":"Hetzner opracowuje usługę wnioskowania LLM","summary":"Europejski dostawca usług w chmurze Hetzner opracowuje usługę wnioskowania LLM o nazwie Sliplane. Usługa ta ma na celu zapewnienie użytkownikom możliwości wnioskowania modeli opartych na infrastrukturze Hetznera, obecnie nie podano jeszcze konkretnego czasu uruchomienia, listy obsługiwanych modeli ani informacji o cenach.","category":"产品更新","source":"Hacker News 热门（buzzing.cc 中文翻译）","aggregationSource":"Hacker News 热门（buzzing.cc 中文翻译）","pageTitle":"Hetzner opracowuje usługę wnioskowania LLM - Aioga Wiadomości AI","description":"Europejski dostawca usług w chmurze Hetzner opracowuje usługę wnioskowania LLM o nazwie Sliplane. Usługa ta ma na celu zapewnienie użytkownikom możliwości wnioskowania modeli opart...","url":"https://www.aioga.com/pl/news/cmrz6k3vn0051rox8yn5qrk2u/","contentTranslated":true,"sourceHash":"25e0e42779eedd4b","translatedAt":"2026-07-27T21:48:52.729Z"}}}}