Baseten on Hugging Face Inference Providers 🔥
huggingface ·
Hugging Face has officially integrated Baseten as a new serverless inference provider within its hub ecosystem. This partnership allows developers to access a wide array of frontier AI models directly through model pages, Python and JavaScript SDKs, and various agent frameworks without requiring additional configuration. Initially, the integration supports conversational and text-generation workloads, featuring prominent open-weight models such as Kimi K3, DeepSeek V4 Flash, and GLM-5.2. Users can customize their experience by setting personal API keys or opting for Hugging Face to route requests and handle billing directly on their accounts. For those using Hugging Face tokens, costs are passed through at standard provider rates, while PRO subscribers benefit from complimentary monthly inference credits. The announcement also notes that expanded task support and additional model compatibility will be introduced in upcoming releases. Developers are encouraged to test the integration and share feedback through official discussion channels.
huggingface