About Modal
A cloud platform for running ML workloads (inference, training, batch jobs) with fast cold-starts, autoscaling, and a developer-oriented programmable infrastructure.
Key Features
- Container-based programmable infra — define environments and hardware in code.
- Sub-second cold starts and instant autoscaling for containers and functions.
- Support for inference, training, and batch processing on GPU/CPU.
- Unified observability (logging, metrics) and security/governance features.
Use Cases & Best For
AI engineers who need low-latency, scalable infrastructure for inference and training
Teams that want to define runtime and hardware in code and ship containers quickly
About Model Serving & APIs
Deploy and serve ML models