Kling Omni-Video API

Quick Start

Authentication

Add Authorization header with Bearer token to all requests:

Authorization: Bearer YOUR_API_KEY

Available Models

Detailed Pricing (85% off)

Kling Video O1

Kling V3 Omni

Endpoints

Request Parameters

Common Parameters

Advanced Parameters

Code Examples

curl -X POST https://apimodels.app/api/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-video-o1",
    "prompt": "A girl dancing on the beach at sunset, cinematic lighting",
    "mode": "std",
    "duration": "5",
    "aspect_ratio": "16:9"
  }'

Response Format

Create Task Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "clxxx...",
    "state": "pending",
    "model": "kling-video/kling-video-o1"
  }
}

Success Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "clxxx...",
    "state": "completed",
    "model": "kling-video/kling-video-o1",
    "resultUrls": ["https://...video.mp4"],
    "createTime": 1705123450000,
    "completeTime": 1705123500000
  }
}

Failed Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "clxxx...",
    "state": "failed",
    "model": "kling-video/kling-video-o1",
    "failMsg": "Content policy violation"
  }
}

Webhook Callback (callback_url)

Pass callback_url in the create request. When the task reaches the completed or failed terminal state, our server sends a single HTTP POST to that URL with Content-Type: application/json (no signing header). Delivery is retried up to 3 times (exponential backoff 1s/2s/4s, 10s per attempt); if still unsuccessful, a background job keeps retrying for up to 30 minutes until your endpoint returns 2xx.

Payload Structure

POST {your callback_url}
Content-Type: application/json

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "clxxx...",
    "model": "kling-video/kling-video-o1",
    "state": "completed" | "failed",
    "param": "<JSON string>",            // request params, JSON.parse once
    "resultJson": "<JSON string> | null", // result object, JSON.parse once
    "failCode": null | "string",
    "failMsg": null | "string",
    "costTime": 12345,                    // duration in ms
    "completeTime": 1705123500000,        // ms epoch
    "createTime": 1705123450000           // ms epoch
  }
}

Note: data.param and data.resultJson are both JSON strings — call JSON.parse once on each.

Video task: shape after JSON.parse(data.resultJson)

{
  "resultUrls":    ["https://r2.apimodels.app/videos/xxx.mp4"],
  "videoDuration": 5                   // optional, seconds
}

resultUrls is always present (length 1 in success, [] on failure). Other fields are optional. When state=failed, resultJson is typically null or {"resultUrls":[]}.

Node.js receiver example

app.post('/webhook/kling-omni', express.json(), (req, res) => {
  const { taskId, state, resultJson, failMsg } = req.body.data
  if (state === 'completed') {
    const r = JSON.parse(resultJson)
    console.log('video ready', taskId, r.resultUrls[0], r.videoDuration)
  } else {
    console.warn('video failed', taskId, failMsg)
  }
  res.status(200).end()                 // must be 2xx, otherwise we retry
})

Notes

• -A task stops retrying only after a 2xx response — once delivered it is never pushed again.
• -Callbacks are not signed today. Embed a random token in your callback_url path and verify it on receipt.
• -Omni video jobs typically take 30s to several minutes — strongly prefer callback_url over polling.
• -Use a public HTTPS endpoint that responds within 10 seconds (per-attempt timeout).

Task States

Error Codes

Important Notes

• *Video files are stored for 7 days, download promptly
• *Omni-Video uses a single unified endpoint -- no need to choose between text-to-video and image-to-video
• *At least one of prompt, image_list, or video_list must be provided
• *O1 supports 3-10s duration, V3 Omni supports 3-15s duration, both priced per second
• *Audio generation is available for both models (set sound: "on")
• *Use video_list with refer_type: "base" for video editing/re-creation
• *Poll every 5-10 seconds to check status