kbwenLab

Token Visualizer

Paste text to see how it splits into tokens — and whether it fits the model window you pick.

Loading tokenizer…

0 tokens

0 chars 0 words

Token breakdown

  • Word
  • CJK
  • Number
  • Symbol
  • Space

Context window usage

Paste text and this shows how much of the window you use and how much is left for the reply.

Model window data as of May 2026.

Quick guide

Use cases, answers, and nearby tools

Compact below-tool notes that help first-run users and repeated visitors move faster without changing the main interface.

Chinese search: token 計算機、token 計數、tokenizer 工具、上下文視窗計算、prompt token 數、gpt token 計算

How to use

Run a clean first pass

  1. Paste or type text into the input, or drop a .txt / .md file onto it.
  2. Pick a model from the menu — the token count and context window usage update live.
  3. Scroll to the token breakdown to see how the text is actually split into tokens.

Examples

Real jobs this page helps with

  • Check whether a prompt is too longPaste a system prompt or long document before sending it to a model, confirm the token count fits the window, then decide whether to trim it.
  • See the token cost difference between languagesPaste Chinese and English together and watch the blocks and numbers show that CJK text usually costs more tokens than English.

FAQ

What people usually want to know

Are the token counts accurate?

OpenAI models are counted exactly with the real o200k tokenizer, locally. Claude and Gemini have no public in-browser tokenizer, so their numbers are estimates and can drift by ±10–20%.

Is my text uploaded anywhere?

No. All tokenization and counting happen locally in your browser — the text is never sent anywhere.

Which model do the colored blocks use?

The token breakdown always uses GPT's o200k tokenizer, as a way to see roughly how text is chunked. Other models split text slightly differently.

Related tools

Bilingual Tone Checker Character Word Counter JSON Formatter