Region Selection

5 posts · May 2024 – Aug 2026

What this trail covers

Modal's platform allows users to select cloud regions for Function execution, offering granular control over deployment locations to meet regulatory requirements, reduce egress fees, and minimize latency by co-locating compute with data or users. This feature supports specifying regions at various levels of detail, from broad continents to specific data centers. Region selection is now available on all plans. Recent work has focused on validating the benefits of a distributed control plane to further optimize region selection and resource allocation.

All Modal trails

Aug 2026Bringing serverless functions closer to the speed of wire | Modal BlogIntroduced a geographically distributed I/O plane with regional routing capabilities for Modal Functions. This change routes Function inputs and outputs through regional I/O servers instead of a central us-east server, reducing network latency for cross-region calls. Implemented asynchronous processing for non-critical tasks and minimized interactions with shared storage on the hot path. Rewrote the server layer in Go for better concurrency and adopted Valkey's I/O multithreading for Redis streams to improve CPU utilization.
Jun 2026Product updates: VM Sandboxes, Lower latency routing, RBAC, and more | Modal BlogIntroduced lower latency routing by allowing Functions to run closer to where they are called from, with options to route inputs through US West, EU West, or Asia Pacific South. This reduces network latency for requests outside of US East and helps maintain data residency.
Apr 2026Real-time inference for robots at Physical Intelligence | Modal BlogThis post details how Physical Intelligence (Pi) built a specialized QUIC-based portal running over UDP with automatic NAT traversal for real-time robotic inference. This system establishes a persistent, bidirectional channel between the robot runtime and Modal GPU containers, streaming observations and receiving action outputs over a single channel. It utilizes Modal Dict for rendezvous and STUN discovery for NAT traversal, enabling direct robot-to-container connections without custom relay infrastructure. The implementation in Rust provides high throughput and minimal latency, adding approximately 10-15 ms of network overhead. Additionally, Pi leverages Modal Volumes for fast checkpoint loading (under 30 seconds) and region-pinning for inference deployments to minimize round-trip latency.
Feb 2025Product updates: Logs v2, live container profiling, and region selection on all plansRegion selection is now available on all plans, with usage priced with a multiplier on top of base prices. This expands the accessibility of granular control over deployment locations for regulatory compliance, egress fee reduction, and latency minimization.
Dec 2024Dogfooding Modal: What we learned at our internal hackathonThe Glodal team prototyped a distributed control plane for Modal, demonstrating a 100x reduction in latency by comparing a single us-east control plane to a distributed one. This validated the benefits of keeping client requests and worker communication within the same continent, reducing latency from 268ms to 3ms in a simulated eu-west scenario. This work is now being incorporated into the platform.
Advertisement
Jul 2024Product updates: Datadog integration, lower function latency & moreIntroduced the ability to select cloud regions for function execution, enabling users to meet regulatory requirements, control egress fees, and minimize latency by co-locating compute with data or users.
May 2024Introducing: Region selectionIntroduces the ability for users to specify cloud regions for Modal Function execution. This feature is available on Team and Enterprise plans and can be configured with varying levels of granularity (broad to specific). Use cases include meeting regulatory requirements, reducing egress fees, and minimizing latency. The post provides code examples and a table of region options.