# Ran out sonnet 4.0 in 35 requests - any ideas on how to to get back old pricing option? **URL:** \ **Category:** Feedback\ **Created:** [August 8, 2025, 1:56pm UTC](https://forum.cursor.com/t/ran-out-sonnet-4-0-in-35-requests-any-ideas-on-how-to-to-get-back-old-pricing-option/127390 "2025-08-08T13:56:29Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![umerqr](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/umerqr/32/67160_2.png) [@umerqr](https://forum.cursor.com/u/umerqr)\ **Post date:** [August 8, 2025, 1:56pm UTC](https://forum.cursor.com/t/ran-out-sonnet-4-0-in-35-requests-any-ideas-on-how-to-to-get-back-old-pricing-option/127390/1 "2025-08-08T13:56:29Z")
![image](https://us1.discourse-cdn.com/cursor1/original/3X/8/5/850673abc217ac07fd5bd867decee4b896fa1c1d.png) All this and gone in 1 day, what’s the point of new pricing system? not even max mode, and all it was doing was fixing unit tests. Is there a way to still opt for 500 requests per month? ---
**Author:** ![condor](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/condor/32/73148_2.png) [@condor](https://forum.cursor.com/u/condor)\ **Post date:** [August 8, 2025, 2:35pm UTC](https://forum.cursor.com/t/ran-out-sonnet-4-0-in-35-requests-any-ideas-on-how-to-to-get-back-old-pricing-option/127390/2 "2025-08-08T14:35:40Z")
hi @umerqr Cursor does not track requests but token and model usage which depends on details reported by AI providers through API. Your screenshot shows high token consumption. This may mean - Very heavy coding usage - Large context used Recommendations - Use thinking models only when there is a clear requirement to use them as they do not have much higher quality output than non-thinking models, but consume much more tokens. - Check and avoid attaching too much context like files, rules, MCPs,… - Keep chats focused on single tasks and short. For more see following, incl. how to optimize your usage: > [@Understanding LLM Token Usage](https://forum.cursor.com/t/understanding-llm-token-usage/120673): > > 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… ---
**Author:** ![umerqr](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/umerqr/32/67160_2.png) [@umerqr](https://forum.cursor.com/u/umerqr)\ **Post date:** [August 8, 2025, 2:50pm UTC](https://forum.cursor.com/t/ran-out-sonnet-4-0-in-35-requests-any-ideas-on-how-to-to-get-back-old-pricing-option/127390/3 "2025-08-08T14:50:25Z")
Hi, I have had same usage patterns before as well, when the plan was at 500 requests, and then went on to unlimited and now to this new tier system. Is there a way to revert to 500 premium requests or is that expired? This is a big turn off as claude code can do so much more than cursor with these new changes in. at least with older format it could compete against claude code. ---
**Author:** ![condor](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/condor/32/73148_2.png) [@condor](https://forum.cursor.com/u/condor)\ **Post date:** [August 8, 2025, 2:55pm UTC](https://forum.cursor.com/t/ran-out-sonnet-4-0-in-35-requests-any-ideas-on-how-to-to-get-back-old-pricing-option/127390/4 "2025-08-08T14:55:29Z")
Please contact [hi@cursor.com](mailto:hi@cursor.com) for switching to the legacy plan.