KlingAI Provider

Kling 3.0 Turbo is the speed-optimized and cost-efficient model within the Kling 3.0 series. It is designed for creators who need rapid iteration, prompt exploration, or draft generation. Supporting both text-to-video and image-to-video, it produces 3 to 15-second clips at 720p or 1080p with native audio.

Kling 3.0 is the flagship video generation model in the Kling series, built on a deeply integrated unified multimodal training framework. It supports text-to-video and image-to-video generation, producing clips of up to 15 seconds

Kling 3.0 Omni is the All-in-One multimodal model of the series, representing the most powerful integration of capabilities. It breaks down the barriers between text, image, audio, and video, treating all inputs as prompts to enable native audio-visual output.

Kling-v3 is an image generation model launched by Kling AI. Cinematic narrative quality, series generation & batch optimization, and direct 1K/2K output.