Kling 4.0

Use kling-4.0 to create video output. This page contains the complete request needed for this model.

Model facts

Minimal request

curl -X POST https://api.api-stock.com/api/v1/generation/create \
  -H "Authorization: Bearer $API_STOCK_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling-4.0",
  "input": {
    "prompt": "A cinematic scene with soft natural light"
  }
}'

The create response contains a task ID:

{
  "code": 200,
  "data": {
    "taskId": "019ca881-9503-7270-a560-f00fc2b15785",
    "status": "not_started",
    "createdAt": "2026-08-22T12:00:00.000Z"
  }
}

Parameters

Parameters belong inside the top-level input object. Unknown fields are rejected.

Modes

Minimal generation

{
  "model": "kling-4.0",
  "input": {
    "prompt": "A cinematic scene with soft natural light"
  }
}

Image references

{
  "model": "kling-4.0",
  "input": {
    "prompt": "A cinematic scene with soft natural light",
    "videoMode": "elements",
    "imageUrls": [
      "https://example.com/input.jpg"
    ],
    "startImageIndex": 1
  }
}

Keyframes

{
  "model": "kling-4.0",
  "input": {
    "prompt": "A cinematic scene with soft natural light",
    "videoMode": "start_end_frame",
    "startFrameUrl": "https://example.com/start.jpg",
    "keyframeUrls": [
      "https://example.com/middle.jpg"
    ],
    "endFrameUrl": "https://example.com/end.jpg",
    "duration": 15
  }
}

Source video transform

{
  "model": "kling-4.0",
  "input": {
    "prompt": "A cinematic scene with soft natural light",
    "videoMode": "transform",
    "videoUrl": "https://example.com/source.mp4",
    "aspectRatio": "auto"
  }
}

Subject elements

{
  "model": "kling-4.0",
  "input": {
    "prompt": "A cinematic scene with soft natural light",
    "videoMode": "elements",
    "elements": [
      {
        "type": "image",
        "description": "A red toy car",
        "imageUrls": [
          "https://example.com/car.jpg"
        ]
      }
    ]
  }
}

Multiple scenes

{
  "model": "kling-4.0",
  "input": {
    "multiShots": [
      {
        "prompt": "Wide shot of a coastal city",
        "duration": 10
      },
      {
        "prompt": "Close-up of a boat",
        "duration": 5
      }
    ]
  }
}

Constraints

• videoMode: allowed: elements, start_end_frame, transform, video_reference.
• resolution: allowed: 720p, 1080p.
• duration: minimum 3; maximum 30.
• aspectRatio: allowed: auto, 16:9, 9:16, 1:1, 21:9.
• startImageIndex: minimum 1; maximum 10.
• Text-only requests omit videoMode and all media inputs. Without a source video, text-to-video requests conditioned on raw images (imageUrls) or subject/object references (elements) require elements mode. With a source video, imageUrls and elements are also accepted in transform and video_reference modes. Keyframes require start_end_frame and startFrameUrl, with at most 10 total frames. Keyframes reject elements, raw image references, source video and multiShots.
• Each element has optional description (100 characters), type (image by default, or video), and either imageUrls (1–4 URLs) or videoUrl. Raw images and elements share a cap of 15, or 14 with source video. At most 3 video elements are supported.
• multiShots replaces prompt, has 2–6 scenes and must total 3–30 seconds. Billing uses this total rather than duration. Only text-to-video and elements modes support multiShots.
• transform and video_reference require videoUrl and aspectRatio auto. The source duration is probed before charging, rounded up to whole seconds and billed at the with-video rate; requested duration is ignored. Source videos must be 3–30 seconds; transform requires a short side of at least 700px.
• Audio is included in the rate. 4K, HDR, Flash, voice references and video extension are not available. Initial client prices use the actual provider launch discount plus 50%, rounded up to the standard client increment; consult current pricing.

Invalid types, unsupported enum values, out-of-range numbers, and missing required fields return HTTP 400 with error.code: "invalid_input". Correct the request rather than retrying it unchanged.

Result

Poll the task or provide a top-level webhook URL in the create request:

curl https://api.api-stock.com/api/v1/task/status/$TASK_ID \
  -H "Authorization: Bearer $API_STOCK_KEY"

A successful media task returns one or more files:

{
  "code": 200,
  "data": {
    "taskId": "019ca881-9503-7270-a560-f00fc2b15785",
    "status": "finished",
    "files": [
      {
        "fileUrl": "https://s3.api-stock.com/result.mp4",
        "fileType": "video"
      }
    ],
    "createdTime": "2026-08-22T12:00:00.000Z"
  }
}

See Tasks and webhooks for terminal statuses, retries and webhook delivery.