Skip to content
Docs menu

Video models

Kling 3.0

On this page

Cinematic text & image to video with native sound and multi-shot support.

modelIdkling-3-0
Modalityvideo
PricingSee this model on the Pricing page for the current per-call price (with your markup).

Operations

OperationEndpointDescription
Text to videoPOST /api/v1/generateBase generation from a text prompt.
Image to videoPOST /api/v1/generateCondition on a reference image — upload it via /api/v1/files/upload and pass the URL.
Poll taskGET /api/v1/task/{id}?model=kling-3-0Retrieve state and result URLs.

Input parameters

FieldTypeRequiredValues / example
image_urlsimageoptional
multi_shotsselectrequiredfalse, true
soundselectoptionalfalse, true
prompttextarearequiredEnter prompt (max 2500 characters)
durationnumberrequired
kling_elementselementsoptional
aspect_ratioselectoptional1:1, 9:16, 16:9
modeselectoptionalstd, pro, 4K

Example request

bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"kling-3-0","input":{"multi_shots":"false","sound":"true","prompt":"A barista pours latte art in slow motion at a cozy window counter, morning light, steam curling.","duration":5,"kling_elements":"…","aspect_ratio":"1:1","mode":"std"}}'