Kling v3
Kling 3.0 video generation model. Supports text-to-video, image-to-video, first/last-frame interpolation, and multi-reference image-to-video.
Authorizations
Pass Authorization: Bearer <YOUR_API_KEY> in the request header. Go to the API Keys management page to create and manage API Keys.
Body
Fixed value kling/kling-v3.
The prompt. Up to 2500 characters.
May be empty when
extra_params.multi_shot(multi-shot mode) is enabled; in that case, per-shot prompts are provided viaextra_params.multi_prompt.
"A cinematic shot of an orange cat stretching slowly under cherry blossoms, warm sunlight"
Output resolution. Defaults to 720P.
720P, 1080P Output aspect ratio. Defaults to 16:9.
16:9, 9:16, 1:1 Video duration in seconds. Defaults to 5; range 3 ~ 15.
3 <= x <= 15Whether to generate audio. Defaults to false.
Reference image list, up to 4 images. When empty, the task is text-to-video; otherwise the input mode is determined by the reference_type combination:
- Image-to-video: 1 image with
first_frame - First/last-frame interpolation: 1
first_frame+ 1last_frame - Multi-reference image-to-video: up to 4 images with
asset
Image constraints (each image must satisfy):
- Format:
jpg/jpeg/png - File size: ≤ 10 MB
- Dimensions: width and height each ≥ 200 px
- Aspect ratio: 1:2.5 ~ 2.5:1
4Kling's official extension parameters. All optional.
Response
Submitted successfully (asynchronous mode)
Unique task ID, used for subsequent polling
"task_2042864638838083584"
The model ID used for this task
"kling/kling-v3"
Task creation time (ISO 8601)
"2026-04-11T07:17:39.146Z"
Unique request ID
"291a4117-9df8-4349-aee1-bdf8ffcacb9a"

