Opus 4.7 Uses 35% More Tokens Than 4.6. Here's What I'm Doing About It.

The new Claude Opus 4.7 tokenizer is silently eating your budget. I ran the same prompts through both 4.6 and 4.7 last week. Identical code, identical context. 4.7 used 33-50% more tokens depending on the language mix. English text gets hit hardest — up to 47% inflation on prose-heavy prompts. This isn't a bug. It's the new tokenizer. the math Same prompt, same output quality: Opus 4.6: 1,000 input tokens → $0.005 Opus 4.7: 1,350 input tokens → $0.00675 That's a 35% effective price increase with