PromptCorrectlyPromptCorrectly
StudioAI CoursesLibraryBlogPricingAbout
Log inStart free
PromptCorrectlyGLOSSARY · HOW MODELS WORK
Home/Glossary/Token

What is Token?

A token is the unit of text a language model reads and writes — roughly three-quarters of a word in English — and the unit you're billed and limited by.

Models don't process characters or words; they process tokens — chunks produced by a tokenizer. Common words are one token; rarer words, numbers, code and other languages split into several. As a rule of thumb, 1,000 tokens ≈ 750 English words.

Tokens matter for three things: the context window (how much fits), cost (APIs charge per token in and out), and speed (output is generated one token at a time). Asking for a shorter answer is the cheapest way to get a faster, cheaper one.

How to use it well
  1. Estimate: characters ÷ 4 ≈ tokens for English.
  2. Set a max length in the prompt ("under 150 words") rather than relying on defaults.
Go deeper
How to use AI properly
Related terms
Context windowTemperatureLLM (large language model)All terms →

Use it right now

Ask our brain anything on the homepage — it remembers the whole conversation — or write a brief in the Studio and see the prompt it compiles to.

Ask the brainOpen the Studio
promptcorrectly.comFROM VAGUE INTUITION TO STRUCTURED INSIGHTBYOK · ANTHROPIC · OPENAI · GROK
PromptCorrectlyPromptCorrectly

The visual workspace for people who actually use AI. Built in the open, priced for humans, powered by your own keys.

Product
  • Studio
  • AI Courses
  • Library
  • Pricing
Resources
  • How it works
  • Templates
  • Community library
  • Repository
  • All 3,600 prompts
  • How to prompt correctly
  • Prompts for every field
  • AI glossary
Company
  • About
  • Contact
  • FAQ
  • Pricing
© 2026 PromptCorrectly · From vague intuition to structured insight.
TermsPrivacyRefundDisclaimerAcceptable useCookies