Kling V1.6 - Multi Image to Video
kling-v1-6-multi-i2v
A video generation model that creates videos from multiple reference images combined with text prompts.
Endpoints
Section titled “Endpoints”POST /v1/queue/kling-v1-6-multi-i2v # Create taskGET /v1/queue/kling-v1-6-multi-i2v/requests/{request_id}/status # Check statusGET /v1/queue/kling-v1-6-multi-i2v/requests/{request_id}/response # Get resultPUT /v1/queue/kling-v1-6-multi-i2v/requests/{request_id}/cancel # Cancel taskRequest parameters
Section titled “Request parameters”curl --request 'POST' 'https://odirouter.ai/model/v1/queue/kling-v1-6-multi-i2v' \ --header 'Authorization: Bearer YOUR_API_KEY' \ --header 'Content-Type: application/json' \ --location \ --data-raw '{ "image_list": [ { "image": "https://www.gstatic.com/webp/gallery/1.jpg" }, { "image": "https://www.gstatic.com/webp/gallery/1.jpg" } ], "prompt": "Two characters meet and greet each other warmly in a sunlit park", "negative_prompt": "blurry, low quality, distorted", "mode": "std", "duration": "5", "aspect_ratio": "16:9"}'Reference image list. Supports up to 4 images, each carrying its URL or Base64 string via the image key:
"image_list": [
{ "image": "image_url_or_base64" },
{ "image": "image_url_or_base64" }
]
No cropping is applied on the API side — upload images with the subject already framed as intended
Supports Base64 encoded images or image URLs (must be publicly accessible)
Note: When using Base64, do not add any prefix (e.g. data:image/png;base64,) — pass the raw Base64-encoded string directly
Supported formats: .jpg / .jpeg / .png
File size must not exceed 10MB; image width and height must be at least 300px; aspect ratio between 1:2.5 and 2.5:1
Image URL or Base64 encoded string
Positive text prompt
Must not exceed 2500 characters
Negative text prompt
Must not exceed 2500 characters
Video generation mode
Default: std
Options: std, pro
std: Standard mode — basic mode with high cost-efficiency
pro: Pro mode (high quality) — high-performance mode with better video quality
Generated video duration in seconds
Default: 5
Options: 5, 10
Aspect ratio of the generated video (width:height)
Default: 16:9
Options: 16:9, 9:16, 1:1
Whether to generate a watermarked version of the result. Custom watermarks are not supported.
true: Generate a watermarked version
false: Do not generate a watermarked version
Callback notification address for this task. If configured, the server will actively notify when the task status changes.
Custom task ID
A user-defined task ID. It does not override the system-generated task ID but can be used to query the task.
Note: Must be unique per user.
Response parameters
Section titled “Response parameters”{ "request_id": "task_01hxyz...", "response_url": "https://odirouter.ai/model/v1/queue/kling-v1-6-multi-i2v/requests/task_01hxyz.../response", "status_url": "https://odirouter.ai/model/v1/queue/kling-v1-6-multi-i2v/requests/task_01hxyz.../status", "cancel_url": "https://odirouter.ai/model/v1/queue/kling-v1-6-multi-i2v/requests/task_01hxyz.../cancel", "queue_position": 0}| Field | Type | Description |
|---|---|---|
request_id | string | Task ID used for all follow-up operations. |
response_url | string | URL to fetch the final result. |
status_url | string | URL to query task status. |
cancel_url | string | URL to cancel the task. |
queue_position | int | Current queue position. |