Explore this Domino Model APIs section for orientation.
When a Domino model is published to an endpoint hosted as a Domino Model API, Domino first runs the script containing the function. The process then waits for input, so any objects or functions from the script remain available in memory. Each call to the endpoint runs the function within this same process. Because the script is only sourced once — at publish time — any more expensive initialization can happen upfront rather than on each call.
After a model is published, it’s referred to as a model API. A model API can have multiple versions.