<?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/35539129dd104313aff40eb1cd255778&quot; frameborder=&quot;0&quot; width=&quot;1230&quot; height=&quot;922&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>922</height><width>1230</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>922</thumbnail_height><thumbnail_width>1230</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/35539129dd104313aff40eb1cd255778-d69fd452832acaec.gif</thumbnail_url><duration>119.659</duration><title>Setting Up Fallbacks and Model Groups for Key Management 🔑</title><description>In this video, I walk through the process of setting up a new key with specific Fallbacks for a model that I anticipate will fail when I send a request to it. I’ve configured the primary mode to cloud and organized multiple groups of models for better management. After creating the key, I demonstrate how to test it by making a request with the failing model, which should now work correctly. Please check the logs to confirm the successful setup. Let me know if you have any questions or need further assistance!</description></oembed>