By tokenizer (English)
| Tokenizer | Words | Pages |
|---|---|---|
| GPT-5.6 | 147,368 | 295 |
| Claude 5.x | 101,754 | 204 |
| Claude Haiku 4.5 | 133,333 | 267 |
By language (GPT-5.6)
| Language | Words |
|---|---|
| Portuguese | 120,000 |
| Spanish | 125,424 |
| English | 147,368 |
| Code (words ≈ terms) | 110,000 |
Estimates from average characters per token. Real counts vary with vocabulary: technical text, names and numbers produce more tokens.