infery
← All models

Kling Video

kling-video-o3-4k-text-to-video

Video generationby Kling

Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling

Example

Details

Accepts
text + image

Pricing

Price
52.5 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
promptText prompt for video generation. Either prompt or multi_prompt must be provided, but not both.
durationstringenum: 3, 4, 5, 6, 7, 8Video duration in seconds (3-15s).
image_urlstringURL of the start frame image.
shot_typestringenum: customize, intelligentThe type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.
multi_promptList of prompts for multi-shot video generation.
end_image_urlURL of the end frame image (optional).
generate_audiobooleanWhether to generate native audio for the video.
elementsElements (characters/objects) to include. Reference in prompt as @Element1, @Element2.
image_urlsReference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 7 total (elements + reference images) is allowed.
aspect_ratiostringenum: 16:9, 9:16, 1:1The aspect ratio of the generated video frame.
start_image_urlImage to use as the first frame of the video.

Output

FieldTypeDescription
videoThe generated video.