AI Dictionary › AI Fundamentals
A token is the basic unit with which language models read and process text. It does not exactly correspond to a word: in English, a token is roughly 3-4 characters on average. The word "intelligence" is about 2-3 tokens; "AI" is 1 token; a space counts separately.
Language models have a token limit they can handle in a single interaction, this limit is called the context window. Keeping track of the number of tokens in your prompt matters both for cost reasons (commercial APIs are priced per token) and quality reasons (an overly long prompt can dilute key instructions).
In Grace, Token Efficiency (weight: 5% of the total score) measures how much each word in your prompt contributes to the quality of the output. Cutting greetings, apologies, repetitions and vague phrasing improves your score and builds the habit of communicating more effectively with any AI.
From our network
INDACO TMS: Transport Management for European Logistics
Shipment tracking, multi-carrier EDI and automated invoicing in one cloud platform. Invoices generated in under 10 seconds.
Visit indacotms.com →From the Agora Intelligence blog
📱 Download the Android app (beta) iOS coming soon
Say what you mean. Get what you need.
Grace Certified, the AI coach that trains and certifies your prompt engineering, by Agora Intelligence.