AI token counter and energy estimator
AI models read and write in tokens, small pieces of words. The longer the answer, the more tokens the model has to produce and the more energy it uses.
Paste a text below. The tool counts characters and words, estimates tokens, and gives the energy a model would use to generate a text of that length.
Result
- Characters
- 183
- Words
- 33
- Energy to generate this text
- 0.0391 Wh
- CO2 on the average European grid
- 8.33 mg CO2
These are estimates. Real figures depend on the model, the data center and the length of the answer.
How this is calculated
- Our assumptions. One token is about 4 characters of English text, and a 400 token answer uses the typical 0.34 Wh.
- OpenAI (2025). Sam Altman states an average ChatGPT query uses about 0.34 Wh and 0.32 mL of water. blog.samaltman.com
- Ember, Global Electricity Review 2025. Carbon intensity of electricity in 2024 (Poland 2023). France and Sweden come from a study based on Ember data and are approximate. ember-energy.org
Questions
What is a token?
A token is a piece of text the model handles as one unit. In English it is about four characters, or three quarters of a word. Other languages often need more tokens for the same sentence.
Is the count exact?
No. Each model family has its own tokenizer and the real count can differ by 10 to 30 percent. The estimate is good enough to compare two texts or size a prompt.