By tokenizer (English)
| Tokenizer | Words | Pages |
|---|---|---|
| GPT-5.6 | 736,842 | 1,474 |
| Claude 5.x | 508,772 | 1,018 |
| Claude Haiku 4.5 | 666,667 | 1,333 |
By language (GPT-5.6)
| Language | Words |
|---|---|
| Portuguese | 600,000 |
| Spanish | 627,119 |
| English | 736,842 |
| Code (words ≈ terms) | 550,000 |
Estimates from average characters per token. Real counts vary with vocabulary: technical text, names and numbers produce more tokens.