Providers and ModelsKling AI

Kling V3

Kling V3
Kling AI · Video Generation
POST /v1/videos/generations

Kuaishou’s Kling 3.0 video generator with text-to-video, first and last frame image-to-video, native audio, and 720p, 1080p, or 4K output.

At a glance

FieldValue
Model idkling-v3
Model release date2026-02-05
Input modalitiesText, Image
Output modalitiesVideo
Context window-
Weight precision-
Featurestext_to_video, image_to_video, audio, video_generation
Native inferenceNo
NewNo
Supported endpointsPOST /v1/videos/generations
Alternate model idskling/kling-v3

Pricing

ChargeSpecRate
Standard T2V/I2Vper second$0.168
Standard T2V/I2V Soundper second$0.252
Pro T2V/I2Vper second$0.224
Pro T2V/I2V Soundper second$0.336
4K T2V/I2Vper second$0.84

Example request

$curl https://api.empiriolabs.ai/v1/videos/generations \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "kling-v3", "prompt": "sunrise over the ocean", "duration": 6}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes-Text prompt describing the video (text-to-video) or the motion to apply to the source image (image-to-video).
model_tierenumno"standard"standard: 720p, fastest. pro: 1080p, higher fidelity. 4k: 3840x2160, highest fidelity and cost. · Allowed: standard, pro, 4k
aspect_ratioenumno"16:9"Aspect ratio for text-to-video. Image-to-video follows the source image. · Allowed: 16:9, 9:16, 1:1
durationnumberno5Video length in seconds (3 to 15). · Range: 3 – 15
soundbooleannotrueGenerate native audio with the video. Standard and pro bill a higher rate with sound on; 4k includes audio.
negative_promptstringno""What to avoid in the output.
imagestringno-Source image URL for image-to-video. One image animates from that frame; two set the first and last frame.

Notes

Model tiers: standard renders 720p, pro renders 1080p, 4k renders 3840x2160. Durations run 3 to 15 seconds. Native audio is on by default; turning Sound off bills the lower rate on standard and pro, while 4K includes audio at one flat rate. Image-to-video accepts one or two images (first and last frame) and follows the source image size.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/kling-v3.