Terms of Use

Counters, converters, guides, and methodology pages are for general informational and planning use. They are not legal, financial, or vendor-official advice, and using the site does not create a professional relationship with us or with OpenAI, Anthropic, or Google.

Exact billing, rate limits, and context windows are defined by each provider’s API, console, and invoices — not by this site.

We work to keep encodings, approximate rules, and explanations honest. Still, we make no warranty that any count is complete, current, or identical to a provider’s production tokenizer for every request shape.

OpenAI-style modes aim to match common browser-available encodings. Claude- and Gemini-oriented modes are labeled approximate when we cannot ship an official browser encoding. Chat wrappers, tools, and multi-message formats can change real usage. See the methodology page for details.

You may use the tools freely for personal and work projects, including checking prompts before you send them to an API.

You may not abuse the site with automated traffic that disrupts service, attempt to break security controls, or republish substantial portions of the site’s original copy without permission.

LLM TokenBase is an independent project. It is not an official product of OpenAI, Anthropic, Google, or any other model vendor. Brand names appear only to describe encodings and estimate modes.

To the maximum extent permitted by law, LLM TokenBase and its operators are not liable for losses from relying on counts or estimates — including unexpected API costs, truncated context, rejected requests, or decisions you make from planning numbers on this site.

We may update these terms as the site evolves. Continued use after changes means you accept the updated terms.