kling-3.0-omni API

Use the exact model ID kling-3.0-omni. The model field must match this page exactly.

Sample outputkling-3.0-omniPOST /v1/videos5.0s

Parameters: duration=5resolution=1080pratio=16:9

Prompt: One continuous take, no cuts. A concrete rooftop at golden hour, the city low and hazy behind. A model in a chrome moulded dress stands still with arms down while loose fabric panels fly in from off frame, hundreds of them in coral, ultraviolet and bronze, and assemble around her into a vast sculpted train that keeps growing past the roof edge. The camera orbits her a full half turn at chest height and rises as the train forms. One hard low sun from the left, deep cool shadow on the right. Real weight and inertia, cloth snapping in the wind, no text.

Request that produced this sample

{
  "model": "kling-3.0-omni",
  "prompt": "One continuous take, no cuts. A concrete rooftop at golden hour, the city low and hazy behind. A model in a chrome moulded dress stands still with arms down while loose fabric panels fly in from off frame, hundreds of them in coral, ultraviolet and bronze, and assemble around her into a vast sculpted train that keeps growing past the roof edge. The camera orbits her a full half turn at chest height and rises as the train forms. One hard low sun from the left, deep cool shadow on the right. Real weight and inertia, cloth snapping in the wind, no text.",
  "seconds": "5",
  "duration": 5,
  "resolution": "1080p",
  "ratio": "16:9",
  "aspect_ratio": "16:9"
}

Authentication and endpoint

Use a Modelflare API key with https://modelflare.dev/v1. The gateway entry point is POST /v1/videos.

HTTP

Authorization: Bearer YOUR_MODELFLARE_API_KEY

Create a task

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "kling-3.0-omni",
    "prompt": "A white cat runs through a neon-lit street in the rain, cinematic tracking shot",
    "duration": "5", "mode": "std"
  }'

Poll and download

Save the task ID. Poll GET /v1/videos/{task_id} and download with GET /v1/videos/{task_id}/content. Result URLs may expire, so transfer the file promptly.

bash

curl https://modelflare.dev/v1/videos/TASK_ID \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY"

Request notes

Kling uses family-specific model_name, prompt, mode, duration, image_list, or contents / settings fields; native JSON is preserved and forwarded.

Request parameters

Kling Omni/O1 uses model_name, prompt, and media lists. Follow each model’s official constraints when combining image_list, video_list, element_list, multi_shot, and sound.

Field	Required	Notes
model_name	Yes	kling-3.0-omni
prompt	Conditional	Required when multi-shot is disabled
mode	No	std / pro
aspect_ratio	Conditional	16:9 / 9:16 / 1:1
duration	No	3–15 seconds (string)
image_list	No	First/end-frame, scene, or style references; Omni/O1 allow multiple items within model limits
video_list	No	Video editing or style references
element_list	No	Kling element IDs; this integration does not provide element management
multi_shot	No	Enable multi-shot storyboarding
sound	No	Whether to generate synchronized sound

Input and output limits

Omni supports 720p/1080p/4k, 3–15 seconds, image/video/element references, and up to six storyboard shots. Set sound off when a reference video is present.

Documented workflow examples

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "kling-3.0-omni",
    "prompt": "让图 1 中的人物在雨中向镜头挥手",
    "image_list": [{"image_url": "https://example.com/character.png"}],
    "duration": "5", "mode": "pro", "aspect_ratio": "16:9", "sound": "off"
  }'

Reference videos, elements, and multi-shot combinations must follow this page’s limits; turn sound off when a reference video is present.

Errors and failed tasks

Invalid model parameters return a 4xx with a request ID. An asynchronous task can also enter failed after creation succeeds; use error_code and error_message from the poll response as the final task reason. Do not retry the same request with a different JSON shape.

Supported scope

This page covers Modelflare model generation and editing calls. Search or map enrichment, voice management, and element-library management are resource APIs outside this public model-call surface and are not required request fields.

Pricing and billing

This model uses per-second video billing. See the model pricing page for the current customer price, reference list price, and complete specification.

Note

This page documents Modelflare’s public interface; the fields and limits shown here are the current contract.