# Request logs Once integrated GPTBoost starts saving data per each request that your app makes to the LLM. For every prompt, you can easily track its text, model, latency and cost. Moreover, you can enrich the collected data with some custom properties like user, IP, or any other attribute that matches your needs best. To obtain the complete JSON for a specific request, simply click the 'Details' button at the end of the row.

Request details are displyed with a click.

To enhance your experience further, we've added some additional options to ease your work.

* **Filtering** for period - Choose the extent of time for which requests are to be displayed. * **Ordering** By - Sort the results by Latest, Slowest or Expensive * **Smart Search** - What's an LLM-powered app analytics tool without some LLM power inside it?? Pass your own filtering criteria in simple words, and GPTBoost will display the data. Include in the prompt all the sorting options listed above or other ones. --- # Agent Instructions: 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: ``` GET https://docs.gptboost.io/features/request-logs.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.