Sonnet finishing up Pro limits faster than before

[condor]

hi @john_wan_ke thank you for your post.

Cursor used to count requests but now consumption of tokens and models counts.

With request based pricing the token consumption was not shown and may have seemed like it is less but the actual consumption has not changed as much.

Note that any context attached to chat like files, rules, MCPs,.. are consuming tokens which may use up your plan faster.

You can find the details in your Dashboard > Usage as summary.

Find more info on token usage and how to optimize your usage.

Understanding LLM Token Usage

Here is a detailed explanation of LLM (AI) token usage in Cursor: Tokens are used every time you interact with AI models in Cursor. For transparency, token counts are shown as processed and reported by the AI provider. You can check your usage in ‎Dashboard > Usage and, if you have Usage Based Pricing, also in ‎Dashboard > Billing. The dashboard is being improved to show all AI usage of a single request in one line, even when multiple tool calls are combined. Tokens are divided into four group…