Kling video models on AI Gateway
By Steven Van ·
The beta brings Kling 3.0's multishot, audio, and first/last frame video generation to Pro and Enterprise plans and paid Gateway users.
Vercel's AI Gateway now supports Kling video models, including the newest Kling 3.0, for generating video from text prompts, images, or motion references. The feature is in beta, available on the Pro and Enterprise plans, as well as for paid AI Gateway users.
- Animates still images into video clips, with coherent motion, facial expressions, and physical interactions
- Generates up to 1080p resolution in pro mode
- Kling 3.0 can produce multi-scene, multishot videos from a single narrative prompt
- Creates synchronized sound effects and ambient audio alongside the video
- Supports first and last frame control for precise scene transitions
Developers can generate videos programmatically with AI SDK 6's generateVideo function, or try models with no code in the Gateway Playground, which is embedded in each model page and lets you compare providers and download results. Details are in the announcement.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →