Daily News · 1 min read

Hugging Face AI Updates: August 7, 2026

hugging-face inference-providers baseten deployment

1. Baseten Joins Hugging Face as an Inference Provider

Hugging Face. Hugging Face added Baseten as a supported Inference Provider, letting developers run serverless inference directly from model pages and the client SDKs. At launch Baseten covers conversational and text-generation tasks across open-weight models including DeepSeek V4 Flash, Kimi K3, and GLM-5.2, accessible either with a personal Baseten API key for direct billing or routed through a Hugging Face account at provider rates with no markup. The integration works with the huggingface_hub Python and @huggingface/inference JavaScript libraries and agent frameworks such as Pi and OpenCode, with additional task types planned. Source