Grok Imagine Video 1.5 on AI Gateway
By Steven Van ·
The xAI model turns a still image into video with synchronized audio in one pass, callable as xai/grok-imagine-video-1.5-preview via the AI SDK.
xAI's Grok Imagine Video 1.5 is now available on Vercel's AI Gateway. The model generates video from an input image with synchronized audio in a single pass, and this release improves audio quality, prompt following, and photorealism, with stronger face accuracy and character consistency across longer sequences and better lighting and physical realism.
Reference image support has also been expanded, giving more control over visual style and subject. To use the model, set model to xai/grok-imagine-video-1.5-preview in the AI SDK; an image model can be chained with it to generate a still and animate it in one flow, and it can also be tried directly in the AI Gateway Playground. It's also tracked on the AI Gateway model leaderboard.
