Foundations
Model-Agnostic Architecture
A model-agnostic architecture lets an application swap or route between LLM providers without a rewrite.
It protects against price changes, deprecations, and capability shifts from any single vendor.
It also lets different workloads route to whichever model is cheapest or best suited.
It is a deliberate design decision, not a default most teams start with.
Most teams retrofit it only after their first vendor lock-in scare.
← Back to the full glossaryRelated terms
More in Foundations
Retrieval-Augmented Generation (RAG) Retrieval-Augmented Generation (RAG) retrieves relevant passages at query time and feeds them into an LLM's context. Embeddings Embeddings are numeric vectors that place similar content close together in vector space. Context Window The context window is the maximum text, measured in tokens, a model can consider at once. Token A token is the basic unit of text an LLM reads and writes.