Token Counter
Estimate token counts for GPT-4, Claude, and other LLMs. Plan your prompts and calculate costs. All processing happens in your browser.
0
Characters
0
Words
0
Lines
0
Sentences
Char-based (~4 chars/token)
0
Word-based (~0.75 tok/word)
0
Average Estimate
~0
Token counts are estimates. Actual counts depend on the model's tokenizer (BPE for GPT, SentencePiece for others). Estimates are most accurate for plain English text.
About Token Estimation
Tokens are the basic units that language models process. A token can be as short as one character or as long as a word. For English text, a rough rule of thumb is 1 token per ~4 characters, or ~0.75 tokens per word. Code, special characters, and non-English text often use more tokens. Prices shown are approximate and subject to change.