Learn

How tokenization works and why LLMs measure text in tokens, not characters.

How input/output token pricing works and what actually drives your bill.

What counts toward a model's context window and how usage adds up.

How retrieval-augmented generation works and why applications use it.

What embeddings are, how embedding pricing works, and how costs scale.

Why documents are split into chunks before retrieval, and how it's done.

Practical guidance for picking chunk size and overlap for your own documents.

A worked example combining LLM, embedding, and infrastructure cost for RAG.

What each classification metric measures and when to prioritize which one.

A framework for estimating the full monthly cost of an AI application.