Digital Event Horizon
OVHcloud has joined the Hugging Face Inference Providers ecosystem to provide access to advanced AI capabilities through its fully managed serverless service offering. With competitive pay-per-token pricing, OVHcloud enhances the Hub's model pages with a wide variety of models from popular open-weight models.
OVHcloud has partnered with Hugging Face to enhance serverless inference capabilities on the Hub's model pages. The partnership provides access to popular open-weight models like gpt-oss, Qwen3, DeepSeek R1, and Llama. The service supports advanced features including structured outputs, function calling, and multimodal capabilities for both text and image processing. Users can access OVHcloud's services by accessing the hub's model pages or exploring OVHcloud's organization on the hub.
OVHcloud, a leading cloud computing provider, has recently joined the growing ecosystem of inference providers on the Hugging Face Hub. This strategic partnership aims to enhance the breadth and capabilities of serverless inference directly on the Hub's model pages. The move is expected to provide users with access to a wide variety of models from popular open-weight models like gpt-oss, Qwen3, DeepSeek R1, and Llama, right from Hugging Face.
The Hugging Face Hub is an extensive platform that offers a range of features for natural language processing (NLP) tasks, including text generation, sentiment analysis, and question answering. The hub's ecosystem has grown significantly over the years, with various providers contributing their models and infrastructure to enhance the capabilities of the platform.
In this article, we will delve into the details of OVHcloud's partnership with Hugging Face, exploring how it enhances serverless inference capabilities, how users can utilize its services, and what implications this move has for the broader AI research community.
The Integration of OVHcloud with Hugging Face Inference Providers
OVHcloud joins a growing list of inference providers that have partnered with Hugging Face to offer their models and infrastructure to the hub's user base. This integration allows users to access popular open-weight models from leading research labs via simple API calls, providing them with a more streamlined and efficient way to leverage these advanced AI capabilities.
The OVHcloud AI Endpoints service is a fully managed, serverless solution that provides users with competitive pay-per-token pricing starting at €0.04 per million tokens. This service runs on secure infrastructure located in European data centers, ensuring data sovereignty and low latency for European users. The platform supports advanced features including structured outputs, function calling, and multimodal capabilities for both text and image processing.
To utilize OVHcloud's services, users can access the hub's model pages, where they can browse trending supported models specifically available through OVHcloud's infrastructure. Users can also explore OVHcloud's organization on the hub at https://huggingface.co/ovhcloud to discover more about its offerings and capabilities.
The OVHcloud Partnership: Enhancing Serverless Inference Capabilities
The partnership between Hugging Face and OVHcloud aims to enhance serverless inference capabilities directly on the Hub's model pages. This integration allows users to access a wide variety of models, including those from popular open-weight models like gpt-oss, Qwen3, DeepSeek R1, and Llama.
In the website UI, users can set their own API keys for the providers they've signed up with, enabling them to customize their experience. Users can also order providers by preference, which affects the widget and code snippets in the model pages.
There are two modes when calling Inference Providers: custom key and routed by HF. When using a custom key, users' requests go directly to the inference provider, using their own API key of the corresponding inference provider. In contrast, routed requests utilize Hugging Face authentication, with charges applied directly to the user's account.
The client SDKs also benefit from this integration. Users can leverage OVHcloud as an Inference Provider in Python and JavaScript using huggingface_hub and @huggingface/inference, respectively. The following example shows how to use OpenAI's gpt-oss-120b using OVHcloud as the inference provider.
In summary, the partnership between Hugging Face and OVHcloud enhances serverless inference capabilities directly on the Hub's model pages, providing users with a wide variety of models from popular open-weight models like gpt-oss, Qwen3, DeepSeek R1, and Llama. This integration also offers users competitive pricing and a more streamlined experience.
Related Information:
https://www.digitaleventhorizon.com/articles/OVHcloud-Joins-Hugging-Face-Inference-Providers-Ecosystem-Enhancing-Serverless-Inference-Capabilities-deh.shtml
https://huggingface.co/blog/OVHcloud/inference-providers-ovhcloud
Published: Wed Dec 3 07:42:12 2025 by llama3.2 3B Q4_K_M
