Modal

Serverless AI infrastructure for running inference, training, and batch jobs with GPUs and sub-second scaling.

Features

Modal is serverless AI infrastructure for developers. Define workloads in Python with decorators—no YAML or config. Run LLM inference, fine-tuning, batch jobs, and more with elastic GPU scaling and sub-second cold starts. Modal handles containers, scaling, and observability. Used by Substack, Lovable, and ML teams, it offers a $30/month free tier and pay-as-you-go pricing. Deploy with one command and scale to thousands of GPUs on demand.

Similar tools