Token Counter
Paste any text and see the token count, then what it actually costs per model at your volume. Every other tokenizer tool stops at the count.
Nothing is sent anywhere. Counting happens entirely in your browser.
Counted with the o200k_base tokenizer (GPT-4o and newer); the cl100k_base count (GPT-3.5 / GPT-4 era) is 0. Anthropic and Google do not publish an open tokenizer, so the Claude and Gemini costs below price this same count against their public rates, not an exact count from their own tokenizer.
E.g. a system prompt or a retrieved document included in every call.
How this tool counts and prices
Three things worth knowing before you trust the number.
Two tokenizers, one number
The headline count uses o200k_base (GPT-4o and newer); the cl100k_base count (GPT-3.5/GPT-4 era) is shown alongside it, since which one matters depends on which model you are actually calling.
Priced, not just counted
Every other tokenizer tool stops at the count. This one prices it, per model, at the volume you actually send it, using the same rates as the rest of the cost tools on this site.
Nothing leaves your browser
Counting runs client-side. Paste a contract, a codebase, or a system prompt with real customer data in it; none of it is transmitted anywhere.
Text sent on every request, a system prompt, a retrieved document, deserves the context engineering treatment: measured, not assumed. For the caching saving specifically, size it with the prompt caching calculator, or compare every model's effective price with the LLM pricing comparison.
Token counter FAQ
How many tokens is a page?+
A typical single-spaced page of English text, around 500 words, runs about 650 to 700 tokens with a modern tokenizer, since one token is usually a bit less than one word. Dense technical text with code, numbers or unusual formatting tokenizes less efficiently and can run noticeably higher.
How many words is 1,000 tokens?+
Roughly 750 words of plain English, using the common rule of thumb that one token is about four characters or three-quarters of a word. The exact ratio shifts with vocabulary and formatting, which is why this tool counts your actual text instead of applying a fixed multiplier.
Does Claude use the same tokenizer as GPT?+
No. Anthropic and Google both use their own tokenizers and have not published them openly, so an exact Claude or Gemini count is not available client-side. This tool prices the OpenAI o200k_base count against Claude and Gemini rates as the closest available estimate, stated plainly rather than presented as an exact figure.
What is a token in AI, in plain terms?+
A token is the unit a language model actually reads and bills by, usually a word, part of a word, or a punctuation mark, not a full word every time. "Tokenization" is common and "un-", "believ", "able" is three tokens for one uncommon word, which is why token counts and word counts diverge more on technical or unusual text.
Why does this tool show a cost, not just a count?+
Because the count alone answers half the question. A token count that stays a count leaves you to do the pricing math by hand, per model, per plan. This tool prices your exact text at your stated volume across Claude, GPT, Gemini and DeepSeek in the same table, using the pricing data behind the rest of the cost tools on this site.
Is my text sent anywhere when I use this tool?+
No. Counting runs entirely in your browser using a JavaScript tokenizer; the text you paste is never transmitted to a server. That also means very long pastes, a full document or a codebase, count instantly without an upload step.
Know what your context actually costs
Counting tokens is the first step. We design the retrieval, caching and memory architecture that keeps the bill from growing with every feature you ship. Book a free scoping call.