What is Token?
Last updated May 2026The basic unit of text that AI models process — roughly 4 characters or 0.75 words.
Definition
A token is the smallest unit of text that an AI model processes. In English, one token is roughly 4 characters or about 0.75 words. AI models read, process, and generate text in tokens. API pricing is typically based on the number of input tokens (your prompt) and output tokens (the AI response). Context window sizes are also measured in tokens.
💡 Example
"Hello, world!" contains 4 tokens: "Hello", ",", " world", "!". A 500-word article is approximately 670 tokens. GPT-4o charges $2.50 per million input tokens.
Related concepts
A type of AI trained on massive text datasets to understand and generate human language.
The maximum amount of text an AI model can process in a single conversation.
Why this matters
Tokens are the currency of AI. Every AI tool charges by tokens (input + output), and token limits determine how much context the model can use. Understanding tokens helps you estimate costs and optimize prompts for efficiency.
Real-world example
Roughly 1 token = 0.75 words in English. A 1,000-word blog post = ~1,333 tokens. GPT-4o costs about $2.50 per million input tokens. So processing a 10-page report costs roughly $0.03 — but generating a 50-page document could cost $1-2.
See it in action
A way for developers to programmatically access AI models in their own applications.
What is Token?
A token is the smallest unit of text that an AI model processes. In English, one token is roughly 4 characters or about 0.75 words. AI models read, process, and generate text in tokens. API pricing is typically based on the number of input tokens (your prompt) and output tokens (the AI response). Context window sizes are also measured in tokens.
How does Token work in practice?
"Hello, world!" contains 4 tokens: "Hello", ",", " world", "!". A 500-word article is approximately 670 tokens. GPT-4o charges $2.50 per million input tokens.
How are tokens counted in AI models?
Tokens are not the same as words. Common English words are usually one token, but longer or uncommon words may be split into multiple tokens. A rough estimate is that one token equals about 4 characters or 0.75 words in English. Most AI platforms provide token counting tools.
Why do tokens matter for AI tool pricing?
Most AI APIs charge per token for both input and output. Understanding tokenization helps you estimate costs, optimize prompts to use fewer tokens, and choose between models based on your budget. Input tokens are typically cheaper than output tokens.
Do different AI models tokenize text the same way?
No. Each model family uses its own tokenizer, so the same text produces different token counts across models. GPT models use a different tokenizer than Claude or Gemini. This means cost and context window usage varies by model even for identical inputs.