By tokenizer (English)
| Tokenizer | Words | Pages |
|---|---|---|
| GPT-5.6 | 368,421 | 737 |
| Claude 5.x | 254,386 | 509 |
| Claude Haiku 4.5 | 333,333 | 667 |
By language (GPT-5.6)
| Language | Words |
|---|---|
| Portuguese | 300,000 |
| Spanish | 313,559 |
| English | 368,421 |
| Code (words ≈ terms) | 275,000 |
Estimates from average characters per token. Real counts vary with vocabulary: technical text, names and numbers produce more tokens.