Vercel adds Google's Gemini Omni 1.2 Flash to AI Gateway

Vercel's changelog says Google's Gemini Omni 1.2 Flash is now available through AI Gateway, so developers can call the video model with one API key instead of a separate Google account. The model turns text prompts into clips of 3 to 15 seconds with native audio, and edits source footage of the same length using up to six reference images. Calls can extend a video by 3 to 10 seconds, to 30 seconds total, or refine an earlier result via previousInteractionId. Output comes in 360p, 720p, 1080p and 4K, in 16:9 or 9:16. Developers use the model name google/gemini-omni-1.2-flash and can receive the finished file through generateText or streamText in AI SDK. Gateway passes through provider pricing with no markup or platform fee on inference.