Tokens and context
Words to tokens estimator
Estimated token count for a word or character count, on OpenAI's and Anthropic's rules of thumb.
Prices read from the vendor pages on 2026-10-20. Arithmetic on list prices, not advice or a quote.
Saving and exports need Norwell Tools Pro, $9 a month. See what is in it. Everything above is free.
How it works
A thousand English words is about 1,333 OpenAI tokens by OpenAI's rule of thumb and about 1,800 tokens on Anthropic's current tokenizer by its published figure. Budget with the higher number.
The formula
tokens = words / words_per_token (or characters / chars_per_token); low and high are the two vendors' estimatesWorked example
With the inputs the page opens on:
- words: 1000
- characters: 0
gives
- tokens openai: 1,333 tokens
- tokens anthropic: 1,802 tokens
- tokens low: 1,333 tokens
- tokens high: 1,802 tokens
Sources
- https://platform.openai.com/tokenizer (rule of thumb: 1 token is about 4 characters or 0.75 words of English)
- https://platform.claude.com/docs/en/models/overview (1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer)
Prices read from each vendor's own pricing page on 2026-10-20; the page may have changed since. This is arithmetic on published list prices, not advice or a quote. Check the vendor's page before committing a budget.