ModelRefs / Token — AI Glossary
Token — AI Glossary
The atomic unit an LLM reads and writes — typically a sub-word fragment of 3–4 characters. Pricing, context windows, and latency are all denominated in tokens.
Overview
Tokens are produced by a tokenizer that splits text into integer IDs the model can process. Pricing, context windows, and latency are all denominated in tokens. 1,000 tokens ≈ 750 English words.
Reference details
| Topic | core |
|---|---|
| Last reviewed | 2026-06-24 |
Related terms
Example: The model cannot see the letters
English runs roughly 0.75 words per token, so a 500-word document is about 500 / 0.75 ≈ 667 tokens, and a 200,000-token context window holds on the order of 150,000 words. The more consequential fact is what a token *is*: the model receives integer IDs for word fragments, not characters. Asking how many times a letter appears in a word is therefore asking it to report on something it never received — it can often infer the answer, but it is inference, not inspection. The same mechanism explains why arithmetic on long numbers is unreliable: the digits were grouped into fragments before the model saw them.
Commonly confused with
A token is not a word, a syllable or a character, and the mapping is different for every tokenizer. Counts do not transfer between providers even for identical text, and languages not written in Latin script frequently cost several tokens per character — which makes the same meaning materially more expensive to send. Always count with the tokenizer of the model you are actually calling.
When to use it
Reach for it when:
- Every cost, latency and context-fit estimate — tokens are the unit all three are billed in
- Deciding chunk sizes, truncation points and how much history to carry
- Explaining character-level and arithmetic failures, which are usually tokenization artifacts
Reach for something else when:
- Estimating non-English cost from an English words-per-token ratio
- Assuming a provider's count matches another's, or that a rough estimate is close enough at the context limit
- Character-level tasks, which are better served by doing the string operation in code
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Token — AI Glossary.
Frequently asked questions
What is Token?
The atomic unit an LLM reads and writes — typically a sub-word fragment of 3–4 characters.
What concepts are related to Token?
Closely related concepts include tokenizer, context window, inference cost.