Skip to main content
POST
/
v1
/
predictions
curl --request POST \
  --url https://api.shuyou.ai/v1/predictions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kling-v3-video",
  "function": "video",
  "input": {
    "prompt": "A cinematic shot of a majestic lion in the savannah at golden hour",
    "aspect_ratio": "16:9",
    "resolution": "standard",
    "duration": 5,
    "generate_audio": true
  }
}
'
{
  "data": {
    "task_id": "2c4d50261173430290971a2395a3b607",
    "task_status": "processing"
  }
}

​
Overview

Kling V3 (kling-v3-video) supports:
  • Text-to-video — prompt only
  • First / last frame — first_frame_url, last_frame_url

​
Input parameters

FieldRequiredDefaultNotes
promptYes—Max 2500 characters
aspect_ratioNo16:916:9, 9:16, or 1:1
resolutionNostandardstandard or pro
durationNo53–15 (seconds)
generate_audioNotrueInclude generated audio
first_frame_urlNo—First keyframe image URL
last_frame_urlNo—Last keyframe image URL

Authorizations

​
Authorization
string
header
required

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
enum<string>
default:kling-v3-video
required

Model ID. Use kling-v3-video for this endpoint.

Available options:
kling-v3-video
Example:

"kling-v3-video"

​
function
enum<string>
required

Task type. Must be video for video generation.

Available options:
video
Example:

"video"

​
input
object
required
​
webhook
string<uri>

Optional HTTPS callback URL when the task completes, fails, or is cancelled.

Response

Async task created

​
data
object
required