model snapshot (LLM)
A fixed, dated version of a hosted model, as opposed to an alias that the provider moves to newer versions.
In more detail
Aliases such as a "latest" name can change behaviour under you overnight. Pin the snapshot in production, rerun your evals before switching, and watch the provider's deprecation schedule for its retirement date.
Related terms
- 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.
- 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.
- prompt versioning — Treating prompts as code: kept in the repository, given a version that travels with each request, reviewed and tested before release.
Taught in
- What An AI Engineer Does — AI Engineering: LLM Apps, RAG & Agents
- Choosing A Model — AI Engineering: LLM Apps, RAG & Agents
- Prompts As Code — AI Engineering: LLM Apps, RAG & Agents
- Agent SDKs And Human Approval — AI Engineering: LLM Apps, RAG & Agents
- Working With AI Coding Assistants — AI Engineering: LLM Apps, RAG & Agents