DeepInfra is now a supported Inference Provider on the Hugging Face Hub, offering serverless AI inference with over 100 models. The initial integration covers conversational and text-generation tasks, with access to open-weight LLMs including DeepSeek V4 and GLM-5.1. Users can authenticate via custom API keys or route requests through Hugging Face, which passes through provider costs without markup. Support for additional tasks like text-to-image and embeddings is planned.
No score is assigned. Sources and their independence are shown in the citation chain below.