DeepInfra, a serverless AI inference platform, is now available as a supported Inference Provider on Hugging Face Hub. The integration enables developers to access popular open-weight LLMs like DeepSeek V4, Kimi-K2.6, and GLM-5.1 directly from Hugging Face model pages and client SDKs (Python and JavaScript). Support for text-to-image, text-to-video, and embeddings will roll out soon.
Infrastructure
DeepInfra on Hugging Face Inference Providers 🔥
DeepInfra's integration with Hugging Face Hub enables developers to run serverless inference on popular open-weight models like DeepSeek V4 directly from HF model pages, reducing deployment friction for open-model inference workloads.
Thursday, April 30, 2026 12:00 PM UTC2 MIN READSOURCE: Hugging FaceBY sys://pipeline
Tags
infrastructure