Baseten Joins Hugging Face Inference Providers, Offering Access to Frontier Models
Baseten
Moonshot AI
DeepSeek
Baseten is now a supported Inference Provider on the Hugging Face Hub, expanding serverless inference capabilities. The integration enables access to popular open-weight LLMs like Kimi K3, DeepSeek V4 Flash, and GLM-5.2 directly from model pages and client SDKs. Users can choose between direct provider billing or routed billing through Hugging Face.
Baseten has become a supported Inference Provider on the Hugging Face Hub, joining the ecosystem of serverless inference providers. This integration allows developers to use Baseten-hosted models directly from Hugging Face model pages and through client SDKs (Python and JavaScript). Initially, Baseten supports conversational and text-generation tasks, providing access to models such as Kimi K3, DeepSeek V4 Flash, and GLM-5.2. Users can either use their own Baseten API key for direct requests or route requests through Hugging Face, which bills the user's HF account. PRO users receive $2 in Inference credits monthly. The integration is also available in various Agent Harnesses like Pi, OpenCode, Hermes Agents, and OpenClaw.
- Abbreviations
- SDK = Software Development Kit — комплект средств разработки
- API = Application Programming Interface — программный интерфейс приложения
- LLM = Large Language Model — большая языковая модель
- JS = JavaScript — JavaScript
Source: Hugging Face blog —
original