← Glossary
Glossary · models
token
Also: tokens
The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Models don't see letters or words; text is split into tokens ("understanding" might be "under" + "standing"). A rule of thumb: 1,000 tokens is about 750 English words. Code tokenizes less efficiently than prose, which is one reason large codebases strain models.
Tokens are the meter that matters everywhere: context windows are measured in them, API pricing is per million of them, and generation speed is tokens per second.
In the index
- Why a token is not a standard unit of AI pricing
- [AINews] "Laguna S 2.1 Released: Cheaper than Deepseek v4 Flash, Better than V4 Pro"
- Anthropic Subscriptions Offer 5x+ More Value Than OpenAI
- Why nobody generates raw waveform samples anymore
- Stanford CS336 Language Modeling from Scratch | Spring 2025 | Overview and Tokenization