AI Token Counter
Paste a prompt or document to estimate its tokens for each model family, how much of the context window it uses and what it costs to send.
Runs in your browser — nothing is uploadedTokens
Estimated tokens
0
Prices as of 2026-09-30. Estimates only — see notes below.
How to use AI Token Counter
- Paste your prompt, document or code.
- Pick the model you plan to use.
- Read the token estimates, context usage and input cost.
Formula & assumptions
- Counts are estimates: the tokenizer approximation was calibrated against OpenAI’s o200k_base (typically within a few percent for English prose and code; up to about 20% off for some other languages). Nothing you paste leaves your browser.
Questions
Why do different models give different counts?
Each provider uses its own tokenizer. Anthropic says its current tokenizer (Claude Opus 4.7 and later) produces about 30% more tokens than earlier Claude models for the same text, so the same prompt can cost more tokens on one model than another.
How accurate is it?
Counts are estimates: the tokenizer approximation was calibrated against OpenAI’s o200k_base (typically within a few percent for English prose and code; up to about 20% off for some other languages). Nothing you paste leaves your browser.
Is my text sent anywhere?
No. Counting happens locally in JavaScript; no AI API is called and nothing is stored.