xAI's Grok Imagine Video 1.5 is now available on Vercel's AI Gateway, generating video from a single input image with synchronized audio in one pass.
Version 1.5 ships with measurable improvements to face accuracy, character consistency across longer sequences, lighting realism, and prompt adherence. Reference image support is expanded, giving developers tighter control over visual style and subject. The model is callable via the AI SDK using the identifier xai/grok-imagine-video-1.5-preview, and can be chained directly with an image model to generate a still and animate it in a single flow. The full changelog details how that pipeline is structured, which is worth reading if you are evaluating this for production use.
AI Gateway routes all of this through a unified API with built-in failover, retry logic, dynamic provider sorting by latency and cost, Zero Data Retention support, and custom reporting. It reflects provider pricing with no markup and charges no platform fee, including on Bring Your Own Key requests. The AI Gateway model leaderboard is live if you need cost and throughput comparisons before committing.
[READ ORIGINAL →]