model selection
Choosing a model by first rejecting candidates that break hard limits, then weighing the rest on quality, latency and cost measured on your own tasks.
In more detail
Hard filters such as licence, data residency and required features are applied before any scoring, so a good score can never outvote them. Record the decision in a rerunnable file, because new models, prices and deprecations will force you to choose again.
Related terms
- model card — A document published with a model that describes its intended use, training data, evaluation results, limits and licence.
- AI eval — A repeatable test of an AI feature: a set of inputs, a way to grade each output, and a score you track across changes.
- model snapshot (LLM) — A fixed, dated version of a hosted model, as opposed to an alias that the provider moves to newer versions.
Taught in
- What An AI Engineer Does — AI Engineering: LLM Apps, RAG & Agents
- Choosing A Model — AI Engineering: LLM Apps, RAG & Agents
- Embedding Models — AI Engineering: LLM Apps, RAG & Agents
- Retrieval That Finds The Right Thing — AI Engineering: LLM Apps, RAG & Agents