175
cold start
The first request pays for process start. After idle, it pays again. Do not put a 2-second boot on a user click.
What is cold start?
A cold start is the latency of creating a new instance: runtime boot, loading weights or a big module, connecting pools. Scale-to-zero and serverless make cold starts normal. A warm instance does not.
Why does cold start matter when vibe coding?
Models pick serverless for a checkout path and initialize the world inside the handler. Name the boot cost and what must stay warm.
How do you do cold start?
Initialize outside the handler. Avoid huge dependencies on the cold path. If the tail cannot include a cold start, keep a minimum instance. Measure cold and warm separately.
How do you ask a model for cold start?
Keep (work) off the cold start. Initialize clients outside the handler. Do not import a heavy library into this path. If the route is user-facing, set a minimum warm instance or do not scale to zero.
What goes wrong with cold start?
A provisioned concurrency of one, and a burst of fifty. You warmed a single cold start and still have forty-nine.