Kling v4 Flash Video Generation | ToAPIs Documentation

POST

/v1/videos/generations

All three input modes use kling-4.0-flash. The API selects the generation path from the supplied media. Generation is asynchronous; query the platform task ID returned by submission.

Use a platform API key. Mainland China users can replace https://toapis.com with https://toapis.cn. Availability depends on the deployed channel configuration and account access.

Input modes

Mode	Request content
Text-to-video	Send a prompt and output specifications without media.
Reference media	Use `image_urls` / `video_urls`, or media with reference roles. Images and videos can be combined.
First frame	Set a single `first_frame` image in `image_with_roles`. Do not include reference images or videos; middle and last frames are unsupported.

Request parameters

Authorizationstringheaderrequired

Authenticate with Bearer YOUR_API_KEY.

modelstringbodyrequired

Always kling-4.0-flash. Do not change the model ID between modes.

promptstringbodyrequired

Required, nonblank, at most 8000 Unicode characters. Describe the subject, action, camera and relationships between media.

durationintegerbodydefault: 5

Integer from 3 to 20 seconds. Defaults to 5.

resolutionstringbodydefault: 720p

Only 720p. Defaults to 720p.

aspect_ratiostringbody

auto, 16:9, 9:16, 1:1 or 21:9. Omission leaves the upstream default unchanged; send auto explicitly for automatic aspect ratio.

image_urlsstring[]body

Reference image URL array, at most 10 images. Positions do not imply a first frame. Counts combine with reference image roles; use one representation per media item.

video_urlsstring[]body

Reference video URL array, at most 5 videos combined with video_with_roles.

image_with_rolesobject[]body

Each object has url and role. reference / reference_image means reference image; first_frame means the first frame. keyframe and last_frame are unsupported.

video_with_rolesobject[]body

Each object has url and role. Supported roles: reference / reference_video.

metadataobjectbody

Boolean keep_original_sound preserves reference video audio, for example {"keep_original_sound": true}. Use for reference videos only. First-frame mode rejects this key even when false.

client_business_idstringbody

Optional client business ID, stored with the task and accepted by the same query endpoint.

Media rules and validation

Use publicly accessible HTTP(S) media URLs without usernames or passwords. Upload local files with image upload or video upload. Do not send local paths or base64.
Reference mode allows up to 10 images and 5 videos. Plain arrays and explicit reference roles are combined; do not send the same media twice.
First-frame mode accepts exactly one first_frame image; keyframe and last_frame roles are rejected. The first frame is selected by role, not by plain image array positions.
First frame and reference media are mutually exclusive. Do not use legacy Kling mode, audio, video_list or Omni reference structures. audio_with_roles, metadata.elements and metadata.voices are unsupported.
Invalid specifications, roles, URLs, counts or mode combinations are rejected. Correct the returned error before retrying. This page does not promise file size, codec or input video duration limits; media must also satisfy upload service and upstream requirements.

Request examples

Text-to-video

{
  "model": "kling-4.0-flash",
  "prompt": "Waves on the shore, a slow camera push, sunset lighting",
  "duration": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9"
}

Reference media

{
  "model": "kling-4.0-flash",
  "prompt": "Keep the character from the reference image and the camera motion from the reference video",
  "duration": 10,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "image_urls": [
    "https://example.com/character.png"
  ],
  "video_urls": [
    "https://example.com/motion.mp4"
  ],
  "metadata": {
    "keep_original_sound": true
  }
}

First frame

{
  "model": "kling-4.0-flash",
  "prompt": "Starting from the first frame, the character slowly turns toward the window",
  "duration": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "image_with_roles": [
    {
      "url": "https://example.com/first.png",
      "role": "first_frame"
    }
  ]
}

Submit a task

requestExample

curl --request POST \
  --url https://toapis.com/v1/videos/generations \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "kling-4.0-flash",
  "prompt": "Waves on the shore, a slow camera push, sunset lighting",
  "duration": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9"
}'

responseExample

{
  "id": "task_example",
  "object": "generation.task",
  "model": "kling-4.0-flash",
  "status": "queued",
  "created_at": 1792713600
}

Task queries and billing

The response id is the platform task ID. Query it below instead of using the provider task_id. States include queued, in_progress, completed and failed. See video task status for the result schema and task webhooks for callbacks.

curl --request GET \
  --url https://toapis.com/v1/videos/generations/YOUR_TASK_ID \
  --header 'Authorization: Bearer YOUR_API_KEY'

Defaults are 5 seconds / 720p. Set these explicitly to control output specifications. This page does not quote fixed prices or equate original audio preservation with legacy Sound billing. Account quotes and task usage / billing determine the actual charges.