Reference · GlossaryInference endpointHTTP (or gRPC) URL where a deployed model accepts inputs and returns predictions.On this pageWhen to useWhen not toExample#When to useWhen the term shows up in labs, architecture docs, or API docs for AI apps.#When not toWhen a simpler word (prompt, chat, search) is enough for your audience.#ExampleSee the linked lesson for an interactive walkthrough.Learn by doing → Learn by doing →Related termsModel servingLatency← All terms