xAI: Grok Imagine Video API

Grok Imagine Video is xAI's first native audio-video model, covering generation, editing and extension in one model: text-to-video, image-to-video (first frame), reference-to-video (up to 7 images), prompt-based edits of an existing video, and continuing a video from its last frame. Up to 720p and 15 seconds per clip, with audio.