In this article
LLMs process text as sequences of tokens, not words. Tokenisers like BPE (Byte Pair Encoding) split text into sub-word units. A typical English word is 1-3 tokens. Token counts determine API costs, context window limits, and processing speed. Understanding tokenisation is essential for cost estimation and prompt optimisation.
What it means in practice
Token is not just vocabulary; it is a design handle. Use it as a reference point when comparing architecture choices, debugging implementation trade-offs, or explaining system behaviour to another engineer. It helps convert a vague technical conversation into a concrete design question with trade-offs that can be tested.
Why engineers care
- It gives teams a shared name for the behaviour, risk, or architecture choice being discussed.
- It helps separate the goal from the implementation detail, so you can compare alternatives instead of copying a tool pattern blindly.
- It creates a useful checklist for reviews: inputs, outputs, failure modes, ownership, cost, latency, and measurement.
Production watch-outs
Be careful with shallow definitions. The useful meaning usually depends on workload, failure mode, data shape, and who owns the system in production.
Related context
Useful neighbouring concepts: Context Window, Tokeniser, BPE.