<?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/0ba7a43bc1df4d44a73081f562d24d3d&quot; frameborder=&quot;0&quot; width=&quot;1720&quot; height=&quot;1290&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1290</height><width>1720</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1290</thumbnail_height><thumbnail_width>1720</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/0ba7a43bc1df4d44a73081f562d24d3d-747b45c968a5d076.gif</thumbnail_url><duration>75.87</duration><title>Add Custom Models in Warp</title><description>This Loom explains how to add custom model endpoints to a Warp. In Settings under Agents, Warp Agents, the speaker shows using the Custom Inputs section to add an external model by entering the endpoint URL, an API key, and a model name (including “ring 2.6”), with optional aliasing. They demonstrate managing custom endpoints, including adding, removing, and updating them. After adding the endpoint, the custom model appears in the conversation model picker right after the auto models, and they verify the setup by getting a “hello” response.</description></oembed>