Always free · no sign-upCount the tokens before you send it
Paste your prompt and see exactly how many tokens GPT-5, GPT-4.1, GPT-4o, the o-series or GPT-3.5 will read it as — the number your API call is actually billed on. It updates as you type.
Free with no limit · nothing is stored · plain text or a chat conversation
Tokens
0
Why it matters
Tokens are the unit that costs you money
It is what you are billed on
OpenAI charges per token, not per word or per character. The count here is the number on the invoice.
Every model has a limit
Go over a model’s context window and the call fails outright. Check the prompt before you ship it, not after.
Trim with something to aim at
Editing a long prompt down is guesswork until you can watch the number move as you cut.
Questions
Tokens, explained
What is a token?
A token is the chunk of text a model actually reads. It is usually part of a word — roughly four characters of English — so "tokenizer" might be two or three tokens while "cat" is one. Models count tokens, not words, which is why a word count is never quite right.
Why does the count change when I change the model?
Different model families use different tokenizers. GPT-4o and everything newer use one called o200k; GPT-4 and GPT-3.5 use the older cl100k. The same sentence can come out as a different number of tokens on each.
What is the difference between plain text and chat messages?
Plain text counts exactly what you paste. Chat messages counts a conversation the way the API does, which adds a few tokens for framing each message and a few more to prime the reply. If you are working out the cost of a real API call, use chat messages.
Is anything I paste here stored?
No. The text is counted and thrown away. There is no account, no history and nothing written down.
Why is this one free when the other tools are not?
Because it runs no AI model. Counting tokens is a calculation we do on our own server, so a count costs us nothing and there is nothing to charge for. The other tools call paid models from OpenAI, which is why those run on tokens.
This one is free. The others are free to get started.
Screen a stack of resumes, or turn one idea into a week of social posts. Those call paid models, so they run on tokens — you get a batch free to start.
What we actually do
This tool is the small version. We build the whole thing.
The token counter does one job, for free, for anyone. Our actual work is building AI systems that run inside a business — the automations, the internal tools your team uses every day, and the parts that talk to the software you already have.
Not sure what is worth automating?
Write one paragraph about your business. We read it, ask a few questions, and show you which work a computer can do for you — and which work it should not touch. Free, and there is nothing to install.
About five minutes
Results by email
No sales calls
Already know what you want built?
Tell us in one line. We will say whether we can build it, what it would take, and we say no if it is not a fit.
Same people who built the tool you just used.