What are tokens in AI and LLMs?

Tokens are the basic units that large language models (LLMs) use to process text. One token roughly corresponds to 4 English characters or about ¾ of a word. Both input and output are billed per token.

How does token counting work?

Different models use different tokenizers. GPT-4o uses the o200k_base encoding while GPT-4 uses cl100k_base. The same text may produce different token counts under different encodings.

Why does token count matter for API costs?

LLM APIs charge per token, typically priced per million tokens. Input and output have different rates, with output usually costing more. Understanding token usage helps optimize prompts and control costs.

Does this tool send my text to a server?

No. All tokenization runs locally in your browser via WebAssembly. Your text never leaves the page — no network requests, no storage, no logs.

How many tokens is 1,000 words of English?

Roughly 750 tokens with o200k_base encoding. Chinese text runs higher — approximately 1.5× to 2× the word count in tokens, because CJK characters often split into multiple subwords.

Token Counter

Estimate tokens & cost

Token Counter

Exact for GPT-4o

INPUT TEXT

Paste text to count tokens

Or try a sample:

Counts use OpenAI tokenizers (o200k / cl100k). Approximate for other providers.

STATS & COST

Enter text to see token stats & visualization

Token counter for GPT-4o, Claude, and Gemini. Supports o200k_base and cl100k_base encodings. All processing runs locally in your browser via WebAssembly.

Ready

o200k_base

Related:String Inspector·LLM Pricing