Modal

Modal is a serverless platform designed for running generative AI models, batch jobs, and data pipelines in the cloud. It makes it easy to run code in the cloud without managing infrastructure, with a focus on AI/ML workloads. Key features include serverless GPU access with automatic scaling, container-based execution environment, simple Python decorator-based API, pay-per-second billing with no idle costs, fast cold starts under 1 second, built-in parallelization for batch jobs, scheduled and triggered functions, web endpoints for serving models, persistent storage and volumes, and integration with popular ML frameworks. Modal is used by AI companies and developers to run inference, training, data processing, and web scraping tasks without infrastructure management overhead.