Detailed explanation
LLMs do not read words but tokens — roughly ¾ of a word in English, more in French. API pricing and context window size are measured in tokens. Counting tokens helps predict cost and limits.
Examples
The word 'hello' ≈ 1 token
1,000 English words ≈ 1,300 tokens
GPT-4 priced per million tokens
Frequently asked questions
How do I count my tokens?
Use libraries like tiktoken (OpenAI) or the utilities each vendor provides.
Related terms
Prompt
A natural-language instruction sent to a generative AI model to get a response.
Embedding
An embedding is a numerical vector representation of text, image, or audio data that captures its semantic meaning, enabling similarity search and machine learning on unstructured content.
LLM (Large Language Model)
An LLM is a large language model trained on massive text corpora, capable of understanding and generating natural language across many tasks: writing, summarization, translation, code, reasoning.
Context Window
The maximum number of tokens a model can consider at once across input and output.
Last updated: 7/15/2026