Token

A token is a small piece of text, often part of a word, that language models read and generate.

Written by Reflective Data experts · updated Oct 5, 2026

Models are priced and limited by tokens. A rough rule of thumb is that a token is about three quarters of a word in English.

Understanding tokens helps estimate cost and fit content into the context window.

// how we can help

We build company brains, agent harnesses and AI bots on top of data you can trust. AI services → · The data platform behind it

Synthetic data is artificially generated data that mimics the properties of real data.

Chunking is splitting documents into smaller pieces so they can be indexed and retrieved for AI…

Embeddings are numerical representations of text or other data that capture meaning, so similar things are…

Claude is a family of AI models and assistants from Anthropic.

Guardrails are the rules and checks that keep an AI system within safe and intended behaviour.

A vector database stores embeddings and quickly finds the ones most similar to a query.