HackerNews中文版

发帖是因为我花了太长时间才弄清楚发生了什么，真希望早点看到这样的帖子。我刚刚取消了两个 Cursor Ultra 计划。我的使用费用从每月稳定在 60-100 美元左右，几天内飙升到 500 美元以上，预计每月将达到 1600 美元以上。客服告诉我这是“预料之中”。我并没有突然开始做 10 倍的工作量。Cursor 显示 20 万的上下文窗口，并表示内容会被总结以保持在限制范围内。定价以每百万个 token 计算。基于此，我监控了我的调用次数，并认为自己很小心。但我没有意识到的是： - Cursor 构建了一个非常大的隐藏提示状态：对话历史、工具追踪、代理状态、扩展推理、代码库上下文。 - 该状态被提示缓存。 - 每次调用时，都会重放整个缓存的前缀。 - Anthropic 会对每次重放收取缓存读取 token 的费用。 - 即使该内容随后在推理前被总结或截断，也会收取缓存读取费用。所以界面显示“最大 20 万上下文”，但账单却并非如此我使用的一个具体例子：MAX 模式：关闭实际用户输入：约 4000 个 token 缓存读取 token：约 2100 万总计账单 token：约 2200 万单次调用的费用：约 12 美元Claude 从未处理过 2100 万个 token。但我还是为此付费了。这不仅仅发生在 Opus 上。Sonnet 也有这种情况。客服解释说，API 的计费方式就是这样的，所以没有错误，我应该更小心地使用这些模型，因为它们在思考时可能会消耗大量 token。但这是有极限的，而我被收取的费用太高了。关于缓存的使用方式，几乎没有任何透明度。而且缓存断点是由 Cursor 决定的，所以我不认为把责任推给 Anthropic 是公平的。危险之处在于，费用与你作为用户可以看到或可以推理的任何东西脱钩了。你认为自己是在 20 万的窗口内操作，但你却要为不断重放的更大的隐藏历史付费。我并不是在声称 Anthropic 的 API 存在错误。这是一个产品透明度问题。如果一个工具由于隐藏的缓存行为，可以悄无声息地将几百美元的使用费用变成四位数，那么用户就需要更好的可见性和控制。客服建议使用支出控制，但我实际上是在抱怨我的预付费套餐是如何被消耗掉的。如果你使用 Cursor 进行长时间的聊天、代理或大型代码库，请仔细检查你的缓存读取 token。界面不会警告你。你唯一能看到的就是在订阅几天后，“你预计将在几天内用完你的使用额度”我已经取消并转移了，尝试使用 Claude Code，直到这个问题得到解决。发帖是为了让其他人不要以这种惨痛的方式发现问题。

查看原文

Posting this because it took me way too long to figure out what was going on, and I wish I had seen a post like this earlier.I just canceled two Cursor Ultra plans. My usage went from a steady ~$60–100/month to $500+ in a few days, projecting ~$1,600/month. Support told me this was “expected.”I did not suddenly start doing 10x more work.Cursor shows a 200k context window and says content is summarized to stay within limits. Pricing is shown as $ per million tokens. Based on that, I monitored my call count and thought I was being careful.What I did not realise: - Cursor builds a very large hidden prompt state: conversation history, tool traces, agent state, extended reasoning, codebase context. - That state is prompt-cached. - On every call, the entire cached prefix is replayed. - Anthropic bills cache read tokens for every replay. - Cache reads are billed even if that content is later summarised or truncated before inference.So the UI says “max 200k context”, but billing says otherwiseConcrete example from my usage:MAX mode: off Actual user input: ~4k tokens Cache read tokens: ~21 million Total tokens billed: ~22 million Cost for one call: about $12Claude never attended to 21M tokens. I still paid for them.This was not just Opus. It happened with Sonnet too.Support explained that this is exactly how the API is billed so there wasn't an error and I should just use these models more carefully as they could consume a lot of tokens when they are thinking. But there is a limit to that and what I was charged was way high. There is ZERO transparency about how the cache is used. And the cache breakpoints are decided by Cursor so I don't think it's fair to throw the ball to Anthropic here.The dangerous part is that cost becomes decoupled from anything you can see or reason about as a user. You think you are operating inside a 200k window, but you are paying for a much larger hidden history being replayed over and over.I am not claiming a bug in Anthropic’s API. This is a product transparency issue. If a tool can silently turn a few hundred dollars of usage into four figures because of hidden caching behaviour, users need much better visibility and controls. Support suggested spend controls but I am actually complaining about how my pre-paid package was consumed.If you use Cursor with long-running chats, agents, or large codebases, check your cache read tokens carefully. The UI will not warn you. The only thing you will see is a few days into your subscription "Your are projected to run out of your usage allowance in a few days"I canceled and moved on, giving Claude Code a shot until this is fixed. Posting so others do not find out the hard way.

已取消 2x Cursor Ultra 计划，原因如下