Token counter for AI models
Paste a prompt, a system message, or a source file and get the token count for the model you use, plus characters, words, and how much of the context window it fills. Counts are exact for OpenAI and clearly labeled estimates for every other provider. Your text is counted in memory and never stored or logged.
0
tokens
0
characters
0
words
0
bytes
Your text is counted in memory on our server and is never stored, logged, or used for anything else. OpenAI counts use the tokenizer for the selected model and are exact. No other provider publishes its tokenizer, so those counts are estimates built on the closest public tokenizer (cl100k_base) and are marked estimate in the model list.