Loading…
Public AI on Hugging Face Inference Providers 🔥
Hugging FaceJoseph Low, Joshua Tan, Célina Hanouti, Julien Chaumond, Simon Brandeis, Lucain Pouget
Summary
Hugging Face has integrated Public AI as a supported Inference Provider on the Hugging Face Hub. Public AI operates as a nonprofit, open-source project providing access to sovereign and public models from institutions such as the Swiss AI Initiative and AI Singapore. Its distributed infrastructure combines a vLLM-powered backend serving OpenAI-compatible APIs across partner-donated clusters with a global load-balancing routing layer. Users can access these models through the Hugging Face web UI, Python client SDK, and JavaScript SDK using either direct provider API keys or routed Hugging Face tokens. At the time of announcement, inference through the Public AI provider is free of charge, supported by donated GPU time and advertising subsidies.
Context
Public and sovereign artificial intelligence model builders, such as the Swiss AI Initiative and AI Singapore, require accessible infrastructure to distribute their models for serverless inference.
Approach / What changed
Hugging Face integrated Public AI as an Inference Provider across its Hub model pages and client SDKs in Python and JavaScript. Public AI uses a distributed infrastructure combining a vLLM-powered backend with OpenAI-compatible APIs deployed across partner-donated compute clusters, managed by a global load-balancing layer.
Takeaways
- Public AI runs on distributed compute clusters donated by national and industry partners, utilizing a vLLM backend with OpenAI-compatible APIs and global load balancing.
- Hugging Face Inference Providers support two calling modes: direct access using a custom provider API key, or automatic routing through a Hugging Face authentication token.
- Python integration with Public AI requires huggingface_hub version 0.34.6 or later when invoking the InferenceClient.
Related reading
Scaleway on Hugging Face Inference Providers 🔥
Scaleway is integrated as a supported serverless Inference Provider on the Hugging Face Hub, expanding model deployment options across Hub model pages and official client SDKs for JavaScript and Python. Operating out of European data centers located in Paris, France, Scaleway Generative APIs host open-weight models including gpt-oss, Qwen3, DeepSeek R1, and Gemma 3 with structured outputs, function calling, multimodal processing, and sub-200ms first-token response times. Developers can route inference requests using their Hugging Face tokens or supply direct Scaleway API keys. Billing for routed requests charges standard provider rates starting at €0.20 per million tokens without markups, while direct requests bill to Scaleway accounts. Hugging Face PRO subscribers receive two dollars of monthly inference credits applicable across providers.
Guillaume Noale, Franck Pagny, Fred Bardolle, Guillaume Calmettes, Constance Morales, Célina Hanouti, Julien Chaumond, Simon Brandeis, Lucain Pouget