Count the words before you prompt.
A calm, local word and character counter for shaping AI prompts before you send them. It counts the text you provide; it does not claim to calculate model-specific tokens.
Prompt scratchpad
Use the count as a check.
A longer prompt is not automatically a better prompt. Look for the smallest context and constraint set that lets another person review the request.
Brief-first check
- Is the task specific?
- Is the audience named?
- Are constraints visible?
- Can the output be reviewed?
Why this belongs in the workflow.
Small tools are useful when they make a review step clearer, not when they promise to replace judgment. This utility keeps the work visible and processes the input locally in your browser.
Related tools and guides.
Continue with a small utility or a practical guide that supports the same step in your workflow.
How to use the AI prompt counter.
- Paste a draft prompt into the scratchpad.
- Compare words, characters, and the approximate token count.
- Use the result as a planning signal, then check the final prompt in the model you actually use.
Important: All processing happens locally in this browser. Token counts are estimates, not official model billing measurements.
Does this show the exact GPT-4 token count?
No. Tokenization varies by model and tokenizer. This page uses a transparent character-based estimate to help with rough planning.
When should I use the estimate?
Use it before comparing prompt length or planning context. Always verify limits and usage in the model's own interface or documentation.