Arena 分析 2.6 万次 Agent 会话：不用缓存成本高出 260%
Your agent would cost 260% more without the cache.
Arena.ai 分析了 2026 年 9 月 12 日至 10 月 23 日间超过 2.6 万次 Agent Arena 会话，覆盖 30 个智能体和 13 家实验室。若所有缓存 token 按模型完整输入价格计费，发往其排名前十智能体的任务成本将变为 3.6 倍（高出 260%）；典型 Claude Fable 5.1 任务当前花费 7.44 美元，无缓存则为 27 美元。样本中单次缓存失效会让典型任务账单增加 5%。
查看原帖https://t.co/gNzLoxDwfc
查看原文
https://t.co/gNzLoxDwfc
正文
Your agent would cost 260% more without the cache.
We analyzed +26K Agent Arena sessions from September 12 to October 23, 2026, spanning 30 agents and 13 labs.
Caching dramatically changes the economics of a typical task. If every cached token were instead billed at the model's full input price, a task sent to one of Agent Arena's top-10 agents would cost 3.6x as much (260% more).
The savings become especially tangible for leading models. A typical Claude Fable 5.1 task costs $7.44 today; without caching, it would cost $27.
Even a coffee break can carry a hidden price: if your cache expires while you’re away, the agent may have to resend the entire conversation at full input price. In our Agent Arena sample, a single cache invalidation translated to a 5% higher bill for a typical task.
Read more findings from our analysis of the hidden AI price war in the article below.