NouveauNom
85 天前
不是的，只是改成了更不透明的计算方式。
Rate Limits 速率限制
Cursor meters rate limits based on underlying compute usage, and limits reset every few hours.
光标根据底层计算使用情况测量速率限制，并且每隔几个小时重置一次限制。
How do rate limits work?
速率限制如何运作？
By default all plans are subject to rate limits on Agent. There are two types of limits: burst rate limits and local rate limits. Burst rate limits can be dipped into at any time for particularly bursty sessions but are slow to refill. Local rate limits refill fully every few hours.
默认情况下，所有套餐均受 Agent 的速率限制。限制分为两种类型：突发速率限制和本地速率限制。对于突发性极高的会话，可以随时使用突发速率限制，但恢复速度较慢。本地速率限制每隔几小时就会完全恢复。
Rate limits are based on the total compute you use during a session. This can vary based on the model you select, the length of your messages, including the length of files you attach and length of current conversation.
速率限制取决于您在会话期间使用的总计算能力。这可能会根据您选择的型号、消息长度（包括您附加的文件长度以及当前对话的长度）而有所不同。
How do you offer this much compute?
您如何提供如此多的计算能力？
To launch Pro and Ultra, we’ve worked closely with the model providers to offer significantly more compute than list prices.
为了推出 Pro 和 Ultra ，我们与模型提供商密切合作，提供远高于标价的计算能力。
What if I hit a limit?
如果我达到极限怎么办？
If a user uses up both their local and burst limits, they’ll be notified explicitely and shown a message that gives them three options:
如果用户用完了本地和突发限制，他们将收到明确通知，并显示一条消息，其中包含三个选项：
Switch to models which have higher rate limits (e.g. Sonnet is higher than Opus)
切换到具有更高速率限制的模型（例如 Sonnet 高于 Opus ）
Upgrade to a higher tier
升级到更高级别
Switch on usage-based pricing to pay for requests that exceed the rate limits
启用基于使用情况的定价来支付超出速率限制的请求
What if I’d like just a lumpsum of requests?
如果我只想一次性提出请求怎么办？
You’re free to stick with legacy Pro Plan if you’d like! You can control this setting at Dashboard > Settings > Advanced. The new Pro should be preferrable for most users.
如果您愿意，可以继续使用旧版专业版！您可以在“控制面板 ”>“设置”>“高级”中控制此设置。新版专业版应该更适合大多数用户。