Kling Video O3 Pro

POST/v1/run

Kling Video O3 Pro by KwaiVGI - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to kwaivgi/kling-video/o3/pro/video-to-video.

Default: kwaivgi/kling-video/o3/pro/video-to-video

stringpromptrequired

Text prompt for video generation. Reference video as @Video1.

Optional<array<string>>images

Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.

Optional<string>video

Reference video URL. Only .mp4/.mov formats, 3-10s duration, 720-2160px resolution, max 200MB.

Optional<integer>duration

Video duration in seconds (3-15s for reference video).

Allowed values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15

Optional<boolean>keep_audio

Whether to keep the original audio from the reference video.

Default: true

Optional<string>shot_type

The type of multi-shot video generation.

Default: customize

Optional<string>aspect_ratio

The aspect ratio of the generated image.

Allowed values: 16:9, 9:16, 1:1

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: video-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kwaivgi/kling-video/o3/pro/video-to-video",
  "prompt": "Integrate @Element1 in the scene. Style video should be following watercolor style of @Image1",
  "video": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/video_reference.mp4",
  "duration": "5",
  "aspect_ratio": "16:9"
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/run_abc123 \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "run_abc123",
  "model": "kwaivgi/kling-video/o3/pro/video-to-video",
  "status": "running",
  "outputs": []
}