<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/1b54b93139ee415d959402cc0629f3f7&quot; frameborder=&quot;0&quot; width=&quot;1672&quot; height=&quot;1254&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1254</height><width>1672</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1254</thumbnail_height><thumbnail_width>1672</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/1b54b93139ee415d959402cc0629f3f7-eac80727e95a1a0b.gif</thumbnail_url><duration>120.399</duration><title>LiteLLM - Dynamic Rate Limiting Demo</title><description>In this video, I demonstrate how to use the LightElem dynamic rate limiter with priority reservations to manage traffic for different use cases. We have a model set to 100 RPM, where the production use case receives 90% of the traffic and the development use case gets 10%. I walk through the process of generating a key with priority metadata and show how to run a load test with 100 users to validate the setup. The expected outcome is that the traffic splits according to the defined priorities, with 90 successes for the higher priority key. I encourage you to implement this feature in your configurations for better traffic management.</description></oembed>