Cost (Tokens & Pricing)
AI usage is priced by the token — you pay for what goes in (your prompt plus all context) and what comes out (the response). Different models have very different price points, sometimes by orders of magnitude. At small scale this rarely matters; at production scale, with thousands of requests per day, cost becomes a serious architectural consideration that shapes which models you use and how you design prompts.
Videos explaining this concept
E011Notes on AI
Tokens
AI models don't read words — they read tokens, the basic unit of text a model processes. A token is close to a word but not identical: one word can be one token, several tokens, or several words can merge into one. Everything in AI is measured in tokens: input, output, context window size, and pricing. One token is roughly four characters in English; once you understand tokens, the limits and costs of AI stop feeling arbitrary.
E012Notes on AI
Tokenization
Tokenization is the process of turning raw text into tokens before an AI model processes it. It is preprocessing, not thinking — the model only sees the resulting pieces.