Scaleway on Hugging Face Inference Providers

Scaleway is now a supported Inference Provider on the Hugging Face Hub, enabling serverless inference directly from model pages and via Python/JS SDKs. It provides access to models like gpt-oss, Qwen3, and Gemma 3, with pricing from €0.20 per million tokens and latency under 200ms for first tokens. The article covers two call modes (custom key vs routed by HF) and includes code examples for Python and JS.

Source

HuggingFace Blog

Ingéré

19 SEPT. 2025 · 19:10

Score édito

4.0 / 5