Kling-O3

Kling-O3

Provider: Kling AI
Category: Video Generation
Endpoint: POST /v1/videos/generations
Context window:
Served from:

Video model in Standard or Pro modes with Text-to-Video, Image-to-Video, Reference-to-Video, editing, native sound, and multi-scene transitions.

At a glance

FieldValue
Model idkling-o3
Input modalitiestext
Output modalitiesvideo
Context window
Region
Featuresaudio, editing
NewNo
Native inferenceNo

Pricing

ChargeSpecRate
Standard T2V/I2Vper second$0.17
Standard T2V/I2V + Soundper second$0.22
Standard Video Inputper second$0.25
Pro T2V/I2Vper second$0.22
Pro T2V/I2V + Soundper second$0.28
Pro Video Inputper second$0.34

Example request

$curl https://api.empiriolabs.ai/v1/videos/generations \
> -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
> -H 'Content-Type: application/json' \
> -d '{"model": "kling-o3", "prompt": "sunrise over the ocean", "duration": 6}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyesMulti-scene: pipe (|) or newline-separated prompts, optionally prefixed with duration like ‘5s: scene text’. Up to 6 scenes.
model_tierenumno"pro"standard: cheapest. pro: balanced quality. 4k: highest fidelity, longest render. · Allowed: standard, pro, 4k
workflowenumno"auto"auto: detect from inputs. t2v: text-to-video. i2v: image-to-video. video_edit: edit attached video. reference: use reference_images. · Allowed: auto, t2v, i2v, video_edit, reference
aspect_ratioenumno"16:9"Kling O3 supports landscape, square, and portrait only. · Allowed: 16:9, 1:1, 9:16
durationnumberno5Per-scene duration in seconds. · Range: 3 – 15
soundbooleannotrueGenerate native audio with the video.
keep_original_soundbooleannotruevideo_edit only. Keep audio from the source video.
imagestringnoReference image URL for i2v.
videostringnoSource video URL for video_edit.
reference_imagesstringnoComma-separated image URLs for reference workflow.
seednumbernoReproducibility seed.

Live machine-readable schema is also available at GET https://api.empiriolabs.ai/v1/models/kling-o3.