OVHcloud joins Hugging Face Inference Providers — serverless AI Endpoints on HF Hub

AI Impact Summary

OVHcloud is now a supported Inference Provider on Hugging Face Hub, enabling serverless inferences directly from model pages and through the JS and Python SDKs. The integration covers open-weight models like gpt-oss, Qwen3, DeepSeek R1, and Llama, with a concrete example using openai/gpt-oss-120b:ovhcloud to illustrate routing options via your provider key or through HF. OVHcloud AI Endpoints operate from European data centers with €0.04 per million tokens pricing and sub-200ms first-token latency, offering EU data residency and predictable costs, while billing can be through the provider or via HF depending on the routing mode; teams should plan migration and billing strategy accordingly.