Token
A token is the chunk of text a language model actually reads and writes: on average about three quarters of an English word, converted to a number from a fixed vocabulary before the model can process it.
No jargon, no math
In plain words, what is it?
Models do not see letters or words. A tokenizer chops your text into tokens: “unbelievable” becomes “un”, “believ”, “able”. Each token maps to a number from a fixed vocabulary of roughly 50,000 to 250,000 entries, and the model only ever computes with those numbers. Costs, speed and memory are all counted in tokens: your context window is a token budget, and most APIs bill per million tokens. It breaks unevenly: English averages about 0.75 words per token, and a language the tokenizer was not tuned for can cost two or three times more tokens for the same sentence. Check before you budget.
Terms that live nearby.
Tokenization
Tokenization is the step that turns text into tokens, the small units a language model actually reads: the input is split according to a fixed vocabulary and each token is mapped to a number, so the model processes IDs instead of words.
ReadContext Window
The context window is the model's working memory, measured in tokens: everything in a single prompt (instructions, documents, the conversation so far) must fit inside it, and anything beyond the limit is simply invisible to the model.
ReadInference
Inference is using a trained model: you send input in, the model applies what training encoded in its parameters, and you get an answer out, one token at a time.
Read§ 03
Want this running in your stack?
We design and ship AI systems with permissions, logs and human approval. It starts with a 30-minute scoping call.