Docs/Kling Video API

Kling Video API

AI video generation supporting text-to-video, image-to-video, audio generation and voice customization.

Quick Start

Get your API key from the Console

Choose a Kling video model (kling-v2-6 or kling-v3)

Send POST request to create task

Poll GET request for video result

Authentication

Add Authorization header with Bearer token to all requests:

Authorization: Bearer YOUR_API_KEY

Available Models

Model	API Name	Features	Price (85% off)
Kling V2.6	`kling-v2-6`	5s/10s, Text/Image-to-Video, Audio+Voice	From $0.0159
Kling V3	`kling-v3`	3-15s, Text/Image-to-Video, Audio, Per-Second	From $0.0064/s
Kling Motion Control	`kling-motion-control`	Motion Control, 720p/1080p, Up to 30s	From $0.06/s

Detailed Pricing (85% off)

Kling V2.6

Mode	Duration	Audio	Voice	$
std	5s	-	-	$0.0159
std	10s	-	-	$0.0320
pro	5s	-	-	$0.0267
pro	10s	-	-	$0.0531
pro	5s	on	-	$0.0531
pro	10s	on	-	$0.1064
pro	5s	on	on	$0.0639
pro	10s	on	on	$0.1275

Kling V3

Mode	Duration	Audio	$/s
std	3-15s	-	$0.0633
std	3-15s	on	$0.0956
pro	3-15s	-	$0.0853
pro	3-15s	on	$0.1280

Kling Motion Control (30% off)

Resolution	Duration	$
Kling 2.6 · 720p	Up to 30s	$0.06/s
Kling 2.6 · 1080p	Up to 30s	$0.10/s
Kling 3.0 · 720p	Up to 30s	$0.12/s
Kling 3.0 · 1080p	Up to 30s	$0.15/s

Endpoints

POST/api/v1/video/generations

Create a Kling video generation task. Automatically routes to text-to-video or image-to-video based on whether image parameter is provided.

GET/api/v1/video/generations?task_id=xxx

Query task status and get video URL

Request Parameters

Common Parameters

modelrequiredstring

"kling-v2-6", "kling-v3", or "kling-motion-control"

promptstring

Text prompt (max 2500 chars). Required for text-to-video.

imagestring

Reference image (base64 or URL). If provided, uses image-to-video mode.

modestring

"std" (standard) or "pro" (high quality). Default: "std"

durationstring

V2.6: "5" or "10". V3: "3" to "15". Default: "5"

soundstring

"on" or "off". Enable audio generation. Default: "off"

negative_promptstring

Negative text prompt (max 2500 chars)

aspect_ratiostring

Video aspect ratio (width:height)

cfg_scalenumber

Creativity control. Higher = closer to prompt.

callback_urlstring

Webhook URL for completion notification

Advanced Parameters

image_tailstring

Tail frame reference image (image-to-video only)

voice_listarray

Voice IDs for voice customization (V2.6+ only, max 2)

camera_controlobject

Camera movement control (type + config)

multi_shotboolean

Enable multi-shot video generation

watermark_infoobject

{ enabled: true/false } - Generate watermarked version

motion_videostring

Motion reference video URL (kling-motion-control only). Provide the motion source video to drive character animation.

Kling Motion Control

When using model "kling-motion-control", provide image (character reference image) and motion_video (motion source video) to generate a video of the character performing the motion. Supports up to 30s, 720p/1080p.

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-v2-6",
    "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-v2-6"
  }
}

Success Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "clxxx...",
    "state": "completed",
    "model": "kling-video/kling-v2-6",
    "resultUrls": ["https://...video.mp4"],
    "createTime": 1705123450000,
    "completeTime": 1705123500000
  }
}

Failed Response

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "clxxx...",
    "state": "failed",
    "model": "kling-video/kling-v2-6",
    "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-v2-6",
    "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
  "thumbnailUrl":  "https://...jpg",   // optional
  "videoSize":     "1280x720",         // optional
  "videoModel":    "kling-v2-6"        // optional
}

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

Node.js receiver example

app.post('/webhook/kling-video', 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.
-Kling 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

pendingTask queued, waiting to process

processingVideo is being generated

completedVideo generation successful

failedVideo generation failed

Error Codes

400Bad Request - Missing or invalid parameters

401Unauthorized - Invalid API key

402Payment Required - Insufficient credits

404Not Found - Task ID not found

500Internal Server Error

Important Notes

*Video files are stored for 7 days, download promptly
*If image parameter is provided, image-to-video mode is used automatically
*V3 supports flexible 3-15s duration with per-second pricing
*Audio generation is available for V2.6 and V3 (set sound: "on")
*Voice customization requires V2.6+ with sound: "on" and voice_list
*Poll every 5-10 seconds to check status
*Kling Motion Control requires both image (character reference) and motion_video (motion source) parameters

Try in Playground Get API Key