Claude Token Counter, now with model comparisons
7 hours ago
- #AI models
- #Token comparison
- #Claude upgrades
- The Claude Token Counter tool was upgraded to compare token counts across different Claude models, focusing on Opus 4.7 versus 4.6.
- Opus 4.7 uses a new tokenizer that can increase token counts by 1.0–1.35×, with an example showing a 1.46× increase compared to Opus 4.6, potentially making it about 40% more expensive.
- Opus 4.7 features improved image support, handling up to 2,576 pixels on the long edge, and a test image resulted in a 3.01× token increase compared to Opus 4.6.