Baseten Joins Hugging Face as Official Inference Provider

baseten · x · 2026-08-06

AI infrastructure platform Baseten has officially joined Hugging Face's ecosystem as a supported Inference Provider. Users can now run popular open-weight LLMs like Kimi K3, DeepSeek V4 Flash, and GLM-5.2 directly from HF model pages or via the SDK using their HF tokens.

The initial integration focuses on conversational and text-generation tasks, with support for additional modalities rolling out soon. Developers can configure custom API keys in their HF settings or route requests through HF, ordering providers by preference.

Related event: Baseten Becomes Official Hugging Face Inference Provider(2 posts)→

Original post →

More from Infra

Infra channel →