A recent analysis of Anthropic's Claude Opus 4.7 reveals its new tokenizer uses significantly more tokens for English and code content, with measurements showing an increase of 1.20x to 1.47x compared to Claude 4.6. This means users will consume their context windows and rate limits faster at the same price. Anthropic suggests this change enhances literal instruction following, potentially reducing errors in tasks requiring precise adherence to constraints. AI
影响 Users face increased token costs and faster rate limit consumption with Claude Opus 4.7, potentially impacting operational expenses and workflow efficiency.
排序理由 Analysis of a specific model's tokenizer behavior and its implications for users. [lever_c_demoted from research: ic=1 ai=1.0]
在 HN — claude-code stories 阅读 →
AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →
