> For the complete documentation index, see [llms.txt](https://studio-docs.sandbox.game/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://studio-docs.sandbox.game/working-efficiently-with-ai/monitoring-and-managing-your-credit-usage.md). # Monitoring and managing your credit usage You will not run out of credits at a convenient moment. Checking usage regularly - not just when something feels wrong - is the habit that keeps you in control. ## The Core Explanation ### Where to check in Cursor Your usage is visible in two places. Inside the IDE, open Settings and navigate to your account. This shows your current plan, your remaining premium requests for the billing cycle, and whether you are on a standard or overage rate. For a fuller breakdown, log in to your Cursor account at [cursor.com](http://cursor.com/) - the dashboard there shows total usage, spend per period, and where you are in the billing cycle. The model selector at the top of the chat panel shows which model is active right now. This is your real-time cost indicator. Before sending any significant request, glance at it. If the model is set higher than the task requires, change it before you send — not after. For which tier to use, see [Choosing the right model for the task](/working-efficiently-with-ai/choosing-the-right-model-for-the-task.md). ### What to look for Remaining included usage. Cursor splits usage into pools. Premium-tier models (see [Choosing the right model for the task](/working-efficiently-with-ai/choosing-the-right-model-for-the-task.md)) consume included usage faster than the fast tier. Tab completions draw from a cheaper pool. Watch remaining usage in Settings and on the dashboard — when it drops, on-demand billing or plan limits apply depending on your plan. Session length as a cost signal. There is no single counter in Cursor that shows you how large your current context is, but session length is a reliable proxy. A conversation that has been running for an hour with multiple file reads is costing more per message than it did when it started. This is the signal to consider a fresh chat -not just for quality but for cost. The model indicator mid-session. Cursor sometimes adjusts the active model automatically depending on the request type. Check the model selector periodically during a long session, not just at the start. If it has shifted to a higher tier than you intended, correct it. ### What to do when usage is running high If you check the dashboard and find you are burning through credits faster than expected, the cause is almost always visible in your recent session behaviour. Check which model has been active, how long your sessions have been running, and whether any large files were pulled into context. Adjust from there - drop the model tier for implementation work, start fresh chats more frequently, and tighten what gets loaded into context. {% hint style="info" %} *NOTE: Cursor's billing resets on a calendar cycle. If you are close to the limit mid-cycle, lighter models and shorter sessions will stretch what remains. If you are consistently hitting the limit early, the pattern is the problem - not the plan tier.* {% endhint %} ## Practical Guidance * Check the account dashboard at the start of each working session, not just when something feels wrong. * Glance at the model selector before every significant prompt and adjust if it is set higher than the task requires. * Check the model selector periodically during long sessions — it can shift automatically and cost more than you intended. * Treat session length as a cost proxy - longer sessions cost more per message; fresh chats reset that. * If credits are running low mid-cycle, switch to lighter models and shorter sessions to make what remains last. Two checks cover most of it: the dashboard for where you stand in the cycle, and the model selector for what you are spending right now. Neither takes more than a few seconds and both tell you something the other does not. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://studio-docs.sandbox.game/working-efficiently-with-ai/monitoring-and-managing-your-credit-usage.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.