AI Glossary
What is Token?
The basic unit of text that AI models process — roughly equivalent to a word or word fragment. AI usage is typically measured and billed in tokens.
Token explained
Language models don't read text word by word — they process "tokens", which are chunks of text (typically 3-4 characters). A rough rule: 100 tokens ≈ 75 words ≈ ~1 paragraph. Every model has a "context window" limit — the maximum number of tokens it can process in one request. Understanding tokens helps you write more efficient prompts and stay within model limits when working with long documents.
Frequently asked questions
What is a token in AI?
A token is the basic unit of text that AI language models process. It's roughly equivalent to a word or word fragment. AI API usage is measured in tokens.
How many tokens is 1000 words?
Approximately 1300-1400 tokens for English text. Different languages tokenize differently.
What is a context window?
A context window is the maximum number of tokens an AI model can process in one request (both your input and its output combined). Claude 3.5 has a 200K token context; GPT-4o has 128K.
Browse ⚙️ engineering AI skills on Geni Kart
Find expert-crafted token prompts and skill packs, ready to use in ChatGPT, Claude, or Gemini.
Browse engineering skills →Related terms
System Prompt
A special set of instructions given to an AI model before a conversation starts, used to d…
Prompt Engineering
The practice of designing and refining text inputs (prompts) to get the best possible outp…
LLM
Large Language Model — a type of AI trained on vast amounts of text to understand and gene…