Baseten becomes a Hugging Face Inference Provider with Kimi K3, DeepSeek V4 Flash and GLM-5.2
Hugging Face Blog·medium signal
Announced August 6, Baseten is now an officially supported Inference Provider on the Hugging Face Hub, wired into both the website UI and the Python and JavaScript client SDKs. Initial coverage is conversational and text-generation tasks across open-weight models including Kimi K3, DeepSeek V4 Flash, and GLM-5.2, with more task types planned. Routing through HF costs standard provider rates with no markup, and PRO subscribers get $2 of monthly inference credits usable across providers.