Paste any prompt or text to see its token count, words, and characters, check how it fits each model's context window, and estimate cost — for ChatGPT, Claude, and Gemini. Free, private, no sign-up.
Token count is an estimate (~4 characters per token). Exact counts vary slightly per model's tokenizer.
Context window usage
Enter your model's input price per 1M tokens to estimate cost.
Tighter prompts = lower cost. Trim yours with the AI Improver
Paste any text and it instantly estimates the token count along with words, characters, and sentences. It also shows how much of each model's context window your text uses and can estimate cost. Everything runs in your browser — nothing is uploaded.
It's a close estimate based on the rule of roughly 4 characters per token for English. Each model (GPT, Claude, Gemini) uses a slightly different tokenizer, so exact counts vary by a few percent, but the estimate is reliable for planning prompts, staying within context limits, and budgeting cost.
A token is the unit AI models read and bill by — roughly ¾ of a word in English (about 4 characters). 'Hello world' is about 2–3 tokens. Both your prompt and the model's reply consume tokens, and models charge per million tokens.
Enter your model's price per 1 million input tokens and the tool multiplies it by the estimated token count. Prices change often and differ for input vs output, so check your provider's current pricing for exact figures.
The tool shows the percentage of each model's context window your text uses (e.g. 128K for GPT-4o, 200K for Claude, 1M for Gemini Pro) and flags when you exceed it — so you know before you hit a limit.
Tighter, better-structured prompts cost less and work better. Grade yours, or start from 30,000+ expert prompts.