Anyscale Endpoints is a modern AI infrastructure trusted by leading AI teams worldwide, including OpenAI and Uber. It offers a serverless API for serving and fine-tuning state-of-the-art open LLMs such as Llama-2 and Mistral. Anyscale Endpoints is part of the Ray ecosystem, the most popular open-source framework for scaling and productionizing AI workloads. It provides high performance, lower cost, and quick scalability. The platform is used for a wide range of AI workloads, from generative AI and LLMs to computer vision.