# Token

> A chunk of text or data that a model reads or writes while processing a prompt or response.

- Category: Context & Memory
- Stage: Established
- Also called: Model token, Text token
- Canonical: https://www.joelcsaji.com/ai-dictionary/token

## Plain English

Models do not read whole words exactly the way people do; they work in smaller pieces called tokens.

## Example

A short sentence may become a dozen tokens, and both input and output tokens usually count toward cost.

## Why it matters

Tokens affect context limits, pricing, latency, truncation, and how much information can fit in a request.

## Related

- [Context Window](https://www.joelcsaji.com/ai-dictionary/context-window)
- [Prompt](https://www.joelcsaji.com/ai-dictionary/prompt)
- [Latency](https://www.joelcsaji.com/ai-dictionary/latency)

## Mentioned in

- [Fable 5, Export Controls, and GLM 5.2](https://www.joelcsaji.com/blog/fable-5-export-controls-and-glm-5-2)

## Sources

- [OpenAI: Advanced Text Generation](https://platform.openai.com/docs/guides/text-generation/parameter-details)
- [Google Cloud Generative AI Glossary](https://docs.cloud.google.com/docs/generative-ai/glossary)