Methodology & sources

Where our numbers come from, how often we check them, and how the tools work them out.

Our rules for data

Primary sources only. Prices, plan limits and context windows come from the provider’s own pricing pages, documentation or help centre, not from news articles, forums or other comparison sites.
Every figure is dated. Each figure is stored with its source URL and the date we last read that page. Pages show a “last checked” date.
No guessing. If a provider doesn’t publish a number (for example, Anthropic doesn’t publish a context window for Claude’s Free plan), we leave it out rather than estimate it.
Estimates are labelled. Anything calculated rather than measured is marked as approximate.

How often we check

API prices: weekly.
Subscription plans, usage limits and context windows: monthly, and whenever a provider announces a change.
Local AI model recommendations: monthly.

Current sources

Chatbot context windows (used by the token counter), last checked 26 Sept 2026:

ChatGPT: ChatGPT pricing (plan comparison table) (checked 26 Sept 2026)
Claude: Claude Help Center (checked 26 Sept 2026)
Gemini: Gemini Apps Help (checked 26 Sept 2026)

How the tools calculate

Token counts

We count tokens with OpenAI’s open-source o200k_base tokenizer, which OpenAI’s tiktoken library maps to GPT-4o and the GPT-5 family. It runs in your browser. Anthropic and Google don’t publish tokenizers that can run in a browser, so for Claude and Gemini the count is an approximation and is marked “≈”.

Tokens to words

We use OpenAI’s published rule of thumb for English: one token is about four characters, or three quarters of a word (source). Pages assume 500 words per single-spaced page.

Reading and speaking time

Reading time uses 238 words per minute, the average silent reading rate for English non-fiction reported by Brysbaert (2019), How many words do we read per minute? A review and meta-analysis of reading rate, Journal of Memory and Language. Speaking time uses 150 words per minute, a typical presentation pace.

Text cleaning

The AI Text Cleaner removes Markdown syntax and invisible Unicode characters with fixed rules that run in your browser. It never rewrites your words.

Corrections

If you spot an outdated or wrong figure, email [email protected] with a link to the source. We check it against the provider’s page and update both the figure and its “last checked” date.