Kling 3.0 Omni

Kuaishou Kling 3.0 Omni – multimodal: text, image, video and reference inputs. Tag images with @image_N in prompt. Up to 7 reference images.

Back to docs
Videokuaishou/kling-3.0-omni$0.1500–$0.1930 / sec

Base URL

https://api.zekron.tech/api/v1

Supported modes

text-to-videoimage-to-videoreference-to-videovideo-to-videomulti-shot

Parameters

Pass these inside the input object when creating a task.

promptrequired
image_urloptional
end_image_urloptional
reference_urlsoptional
durationoptional
modeoptional
aspect_ratiooptional
countoptional
native_audiooptional
multi_shotsoptional

Example request

bash
curl -X POST https://api.zekron.tech/api/v1/tasks \
  -H "Authorization: Bearer zk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kuaishou/kling-3.0-omni",
  "input": {
    "prompt": "a cinematic shot of a lighthouse at golden hour",
    "duration": 5,
    "aspect_ratio": "16:9",
    "mode": "std",
    "native_audio": true,
    "count": 1
  }
}'

Example response

json
{
  "id": "zk_task_8f3a2b1c9d",
  "model": "kuaishou/kling-3.0-omni",
  "status": "processing",
  "created_at": "2026-06-10T12:00:00Z"
}

Poll GET https://api.zekron.tech/api/v1/tasks/{id} until status is success or failed.

Pricing

This model is billed at $0.1500–$0.1930 / sec. You are only charged for successful generations — failed tasks are never billed. Generated outputs are retained for 30 days before they expire.