Modal: High-performance AI infrastructure

# Modal llms.txt > Modal is a platform for running AI workloads in the cloud with minimal > configuration. Key use cases include AI model training and inference, > high-performance batch jobs, and sandboxed code execution. It offers, > fast prototyping, serverless APIs, scheduled jobs, GPU inference, > distributed storage volumes, and highly scalable secure sandboxes. Important notes: - Modal's platform is optimized for AI use cases, but it can support general-purpose cloud workflows. - Modal is a serverless platform, meaning you are only billed for resources used. Containers scale to zero when idle and boot in seconds when needed. - Modal offers official SDKs in Python, Go, and JavaScript/TypeScript, along with a fully-featured CLI for interacting with the platform. You can sign up for free at [https://modal.com] and get $30/month of credits. The docs are organized into three main sections: - _Guide_ pages explain Modal's features, primitives, and workflows - _Examples_ pages contain didactic examples of many different AI applications - _Reference_ pages provide detailed information about the SDKs and CLI ## Guide - [Introduction](https://modal.com/docs/guide) - Custom container images - [Defining Images](https://modal.com/docs/guide/images.md) - [Using existing container images](https://modal.com/docs/guide/existing-images.md) - [Named images](https://modal.com/docs/guide/named-images.md) - [Fast pull from registry](https://modal.com/docs/guide/fast-pull-from-registry.md) - GPUs and other resources - [GPU acceleration](https://modal.com/docs/guide/gpu.md) - [Using CUDA on Modal](https://modal.com/docs/guide/cuda.md) - [Configuring CPU, memory, and disk](https://modal.com/docs/guide/resources.md) - Scaling out - [Scaling out](https://modal.com/docs/guide/scale.md) - [Input concurrency](https://modal.com/docs/guide/concurrent-inputs.md) - [Batch processing](https://modal.com/docs/guide/batch-processing.md) - [Job queues](https://mo