Baseten Joins Hugging Face Inference Providers

Baseten, an AI infrastructure platform, has become an official Inference Provider on the Hugging Face Hub, enhancing the serverless inference capabilities of the ecosystem. This collaboration enables developers to utilize a variety of models directly from model pages and via Hugging Face SDKs (huggingface_hub >= 1.26.1 for Python and @huggingface/inference for JavaScript). Currently, Baseten focuses on conversational and text-generation tasks, featuring well-known open-weight LLMs such as Kimi K3, DeepSeek V4 Flash, and GLM-5.2, with plans for more tasks in the future. Users can either set their own API keys or route requests through Hugging Face, incurring charges to their HF account. The integration is compatible with agent harnesses like Pi, OpenCode, Hermes Agents, and OpenClaw. PRO users receive $2 in monthly Inference credits, while free users have a limited quota. Feedback is welcomed through a discussion platform.