curl --request POST \
--url https://openapi.imini.ai/imini/router/v1/videos/generate \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "kling/kling-v3-omni",
"prompt": "A slow pan across a misty mountain valley at sunrise, cinematic",
"resolution": "720P",
"aspect_ratio": "16:9",
"duration": 5
}
'{
"task_id": "task_2042864638838083584",
"model": "kling/kling-v3-omni",
"created_at": "2026-04-13T07:17:39.146Z",
"request_id": "291a4117-9df8-4349-aee1-bdf8ffcacb9a"
}{
"error": {
"code": "INVALID_PARAMETER",
"message": "reference_videos only supports at most 1 entry",
"status": 400,
"request_id": "req_abc123"
}
}Kling v3 Omni
Kling 3.0-Omni supports asset video references and edit_source video editing, both with up to 4 accompanying asset images.
curl --request POST \
--url https://openapi.imini.ai/imini/router/v1/videos/generate \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "kling/kling-v3-omni",
"prompt": "A slow pan across a misty mountain valley at sunrise, cinematic",
"resolution": "720P",
"aspect_ratio": "16:9",
"duration": 5
}
'{
"task_id": "task_2042864638838083584",
"model": "kling/kling-v3-omni",
"created_at": "2026-04-13T07:17:39.146Z",
"request_id": "291a4117-9df8-4349-aee1-bdf8ffcacb9a"
}{
"error": {
"code": "INVALID_PARAMETER",
"message": "reference_videos only supports at most 1 entry",
"status": 400,
"request_id": "req_abc123"
}
}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-omni.
The prompt, which may contain both positive and negative descriptions. Up to 2500 characters.
The Omni model supports referencing subjects, images, and videos in the prompt using the <<<>>> syntax, e.g. <<<element_1>>>, <<<image_1>>>, <<<video_1>>>.
Required when:
extra_params.multi_shot=false, orextra_params.multi_shot=truewithextra_params.shot_type=intelligence.When
extra_params.multi_shot=trueandextra_params.shot_type=customize, this field is ignored — per-shot prompts are provided viaextra_params.multi_prompt.
"A slow pan across a misty mountain valley at sunrise, cinematic"
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. Allowed values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
When using video editing (
reference_videos[].reference_type=edit_source), this parameter is ignored — the output duration matches the input video and is billed based on the input video duration, rounded to the nearest second.
3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 Whether to generate audio. Defaults to false.
Supports asset images, first_frame and last_frame. Up to 7 asset images without video, or 0-4 asset images with a video. This API does not expose first_frame / last_frame combined with video.
Image requirements:
- Formats:
jpg/jpeg/png; - Size ≤ 10 MB;
- Dimensions ≥ 300px, aspect ratio between
1:2.5and2.5:1.
7Show child attributes
Show child attributes
At most 1 video. asset (default) supplies a reference; edit_source edits the original video. Both modes support 0-4 accompanying images with reference_type=asset.
keep_original_sound controls the original track of this material; omission follows the model default. generate_audio has no effect when a video is supplied.
Video requirements:
- Formats:
MP4/MOV; - Size ≤ 200 MB;
- Duration ≥ 3s (upper bound depends on the model version);
- Dimensions: 720px – 2160px inclusive;
- Frame rate:
24 – 60 fps(output is always 24 fps); - Publicly accessible URL only; base64 is not supported.
1Show child attributes
Show child attributes
Kling's official extension parameters. All optional.
Show child attributes
Show child attributes
Response
Submitted successfully (asynchronous mode)
Unique task ID, used for subsequent polling
"task_2042864638838083584"
The model ID used for this task
"kling/kling-v3-omni"
Task creation time (ISO 8601)
"2026-04-13T07:17:39.146Z"
Unique request ID
"291a4117-9df8-4349-aee1-bdf8ffcacb9a"

