Skip to main content
Try it · OpenAPI specification Kling 4.0 supports text-to-video, up to ten keyframe images, and Omni generation with image and video references. Choose 720p or 1080p. Describe dialogue, music and sound effects in the prompt. Duration can be explicit or inferred from the prompt when omitted. Omni supports up to five input videos, with at most one video to edit and at most thirty seconds of total video input.

Model ID

Pass this exact public ID in the top-level model field.

Supported modes

  • text_to_video
  • image_to_video
  • omni_video

Inputs

  • Text
  • Image
  • Video

Outputs

  • Video

Capabilities

  • Text-to-video
  • Image-to-video
  • Omni video

Additional capabilities

  • Multiple keyframes
  • Reference videos
  • Video editing
  • Native audio

Technical details

Availability and final customer prices can change. Check the Dashboard model catalog before production use.
See the Kling 4.0 API guide, create task, and retrieve task references. Preview all workflows in API Explorer. See the API reference overview for authentication, request conventions, and response schemas.