A million tokens, measured in

Plain text

The baseline everything else is measured in: a million tokens is about 750,000 English words, a stack of 1,500 single-spaced pages, or a thousand Wikipedia articles.

β‰ˆ 4,000,000 characters characters of text, drawn to scale

1 block = 4,000 characters

β‰ˆ 4,000,000 characters

characters of text

One token is roughly 4 characters of English text, so a million tokens is about 4 million characters β€” enough to fill 8,000 standard text messages.

basis: 1 token β‰ˆ 4 characters

β‰ˆ 10,000 paragraphs paragraphs of text, drawn to scale

1 block = 10 paragraphs

β‰ˆ 10,000 paragraphs

paragraphs of text

An average paragraph is about 75 words (~100 tokens). A million tokens is roughly 10,000 paragraphs β€” a library of essays.

basis: ~75 words per paragraph

β‰ˆ 50,000 sentences sentences, drawn to scale

1 block = 50 sentences

β‰ˆ 50,000 sentences

sentences

The average English sentence is about 15 words (~20 tokens). A million tokens is roughly 50,000 sentences.

basis: ~15 words per sentence

β‰ˆ 15,000 IKEA manuals IKEA instruction manuals, drawn to scale

1 block = 10 manuals

β‰ˆ 15,000 IKEA manuals

IKEA instruction manuals

An IKEA manual averages about 50 words of actual text (~67 tokens) β€” they're mostly pictures of confused stick figures. A million tokens is 15,000 of them. You'd still build the shelf wrong.

basis: ~50 words per manual

Text is the native currency of large language models. Every other format β€” images, audio, PDFs β€” eventually gets converted into tokens that look a lot like plain text. Understanding how words, pages, and characters map to tokens gives you the foundation for estimating costs across every use case. Whether you are building a RAG pipeline that ingests documentation or running batch summarization over thousands of articles, these numbers are your starting point.

Common questions about plain text

What would this cost?

Everything on this page is exactly one million tokens. So the price of having a model read β€” or write β€” all of it is simply each model's per-million rate. Updated 2026-07-28.

ModelRead all of it (input)Write all of it (output)
GPT-5.6 Sol$5$30
GPT-5.5 Pro$30$180
Claude Fable 5$10$50
GPT-5.6 Terra$2.50$15
GPT-5.5$5$30
Claude Opus 4.8$5$25
Claude Sonnet 5$2$10
Gemini 3.1 Pro$2$12
Gemini 3.5 Flash$1.50$9
GPT-5.6 Luna$1$6
Claude Haiku 4.5$1$5
Gemini 3 Flash$0.50$3

From $0.50 to $180 for the same million tokens. Try your own budget in the calculator β†’

Frequently asked questions

How many words is 1 million tokens?
One million tokens is approximately 750,000 English words, using the standard conversion of 1 token per 0.75 words.
How many pages is 1 million tokens?
One million tokens is about 1,500 single-spaced pages, at roughly 500 words per page.
1 million tokens to words β€” how do you convert?
Multiply by 0.75. One million tokens times 0.75 equals 750,000 words. One token is roughly 4 characters or three-quarters of an English word.

The same million tokens, measured differently

Or start over with the full picture β€” scale, prices, and the budget calculator.

From the blog