Skip to main content

Kling v3 Omni

Kling v3 Omni is Kuaishou’s Kling VIDEO 3.0 Omni model. On top of the Kling v3 modes, kling-v3-omni adds reference-to-video: combine up to 7 images of subjects, scenes, or styles in one video.
  • text-to-video: omit image_urls.
  • image-to-video: 1 image sets the first frame; 2 images set the first and last frame.
  • reference-to-video: 1–7 reference images. Cite them in the prompt as <<<image_1>>> … <<<image_N>>>, numbered in image_urls order. If the prompt cites none, <<<image_1>>> is prepended automatically.

Request parameters

Each request produces one video without a watermark. Reference videos, 4K, multi-shot storyboards, and element references are not offered.
Submit to POST /api/v1/task/submit/kling-v3-omni. Save the returned data.task_id and poll /api/v1/task/status.

Pricing

Kling v3 Omni is billed per second by resolution and audio. Reference images are not billed.
Example: a 5-second 1080p video with audio costs 216 × 5 = 1,080 credits. /pricing remains the current source of truth.
See the Kling v3 Omni API reference for the machine-readable Schema.