What does 'token' mean in the context of an LLM, and why does it matter for cost and context limits?

A token is a chunk of text (roughly 3-4 characters in English, not always a whole word) that the model reads and generates one at a time. Providers bill per token and every model has a maximum context window measured in tokens, so a long conversation history or a huge retrieved document can silently hit that ceiling or blow up your bill well before you run out of 'words'.