<?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/d5dadd811ae64c70b29a16ecd558d4ba&quot; frameborder=&quot;0&quot; width=&quot;1670&quot; height=&quot;1252&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1252</height><width>1670</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1252</thumbnail_height><thumbnail_width>1670</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/d5dadd811ae64c70b29a16ecd558d4ba-6f848c0201b7e100.gif</thumbnail_url><duration>60.846</duration><title>LiteLLM x gemini-cli demo</title><description>In this video, I explain how to use Gemini CLI with Anthropic Cloud Models by connecting it to LightLM&apos;s proxy. By setting two environment variables—our base URL and API key—we can easily route requests to LightLM and receive responses from Anthropic&apos;s models. I demonstrate this by sending a simple query, &quot;hi, who is this?&quot; to show the process in action. I encourage you to follow these steps to leverage any model you want with Gemini CLI. Let’s get started!</description></oembed>