Skip to navigation
Authors and ModelsKling AI

Kling 4.0

Kling 4.0
Kling AI · Video Generation
POST /v1/videos/generations

Makes 3 to 30 second clips at 720p or 1080p with native audio from text, first, middle and last frames, reference images and videos, or a video to edit.

At a glance

FieldValue
Model idkling-4-0
Model release date2026-10-15
Input modalitiesText, Image, Video
Output modalitiesVideo
Context window-
Weight precision-
Featuresvideo_generation, text_to_video, image_to_video, audio, editing
Native inferenceNo
NewYes
Supported endpointsPOST /v1/videos/generations
Alternate model idskling-4.0, kling/kling-4-0

Pricing

ChargeSpecRate
Standard 720pper second$0.157
Standard 1080pper second$0.235
Video input 720pper second of input plus output, at least twice the output$0.094
Video input 1080pper second of input plus output, at least twice the output$0.141

Example request

curl https://api.empiriolabs.ai/v1/videos/generations \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "kling-4-0", "prompt": "sunrise over the ocean", "duration": 6}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes-Scene description, up to 26,000 English or 11,000 non-English characters. Refer to images as @image_1, @image_2 and videos as @video_1 in the order they are supplied.
resolutionenumno"1080p"Output resolution. 1080p is billed at a higher per-second rate than 720p. · Allowed: 720p, 1080p
aspect_ratioenumno"16:9"Output aspect ratio for text-to-video and reference images. A first, middle or last frame, or a video to edit, sets the aspect ratio instead. · Allowed: 16:9, 9:16, 1:1, 21:9
durationnumberno5Clip length in seconds, whole numbers only. A video edit keeps the length of the video it edits. · Range: 3 – 30
imagestringno-First frame image URL. The video starts on this image.
image_endstringno-Last frame image URL. The video ends on this image.
middle_imagesstringno-Keyframe image URLs between the first and last frame, in order, as a list or comma-separated.
reference_imagesstringno-Reference image URLs for characters, objects, scenes or style, as a list or comma-separated. Up to 10 images in total across all image inputs.
videostringno-Video URL to edit, 3 to 30 seconds. The result keeps its length and aspect ratio, and bills at the video input rate.
reference_videosstringno-Reference video URLs for motion, camera work or style, 3 to 30 seconds each, as a list or comma-separated. Up to 5 videos in total. Bills at the video input rate.

Notes

Generates 3 to 30 second clips at 24 fps in 720p or 1080p, each with a native stereo audio track.

Inputs

  • Text to video: prompt only.
  • Keyframes: a first frame (image), middle frames (middle_images) and a last frame (image_end). The video follows the first frame’s aspect ratio.
  • Reference images (reference_images): characters, objects, scenes or style to use.
  • Reference videos (reference_videos): motion, camera work or style to follow, 3 to 30 seconds each.
  • Video edit (video): a video to edit, 3 to 30 seconds. The result keeps its length and aspect ratio.
  • Up to 10 images and 5 videos per request. In the prompt, refer to images as @image_1, @image_2 (first frame, middle frames, last frame, then references) and to videos as @video_1, @video_2 (the video to edit first).

In the Playground

One attached image is the first frame, two are the first and last frames, and three or more are references. The first attached video is the one edited; any others are references.

Media limits

  • Images: JPG or PNG, at least 300 px, aspect ratio between 2:5 and 5:2, up to 30 MB.
  • Videos: MP4 or MOV, 3 to 30 seconds, 700 to 4553 px per side, up to 300 MB.

Billing

  • Without a video input: billed per second of the generated clip at the resolution you request.
  • With a video input (a video to edit or a reference video): billed at the video input rate on twice the length of the generated clip, or on the input plus the output when the input is longer.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/kling-4-0.