Kling 4.0 Flash - Unifically

Generate 720p AI videos with Kling 4.0 Flash, the faster, lower-cost model in Kuaishou’s Kling 4.0 lineup. It takes the same request as Kling 4.0: text-to-video, up to 10 raw reference images, persistent subject/object elements, a start frame, video reference, and multi-shot generation. Videos run 3–20 seconds at 720p with native stereo audio on by default, in five aspect ratios including 21:9. More on this model: Kling 4.0 Flash API page.

Model

kuaishou/kling-4.0-flash-video

Parameters

Parameter	Type	Required	Default	Description
`video_mode`	string	No	-	Input mode. Allowed: `"elements"`, `"start_end_frame"`, `"transform"`, `"video_reference"`. Omit for text-to-video
`prompt`	string	Conditional	-	Text prompt. Use `@Image1`, `@Element1` to reference inputs. Mutually exclusive with `multi_shots`
`mode`	string	No	`"std"`	`"std"` (720p) only. `"pro"` and `"4k"` are rejected
`duration`	integer	No	`3`	Video length in seconds (3–20). Ignored when `video_url` is set (the source video’s length is used)
`aspect_ratio`	string	No	-	`"auto"`, `"1:1"`, `"9:16"`, `"16:9"`, or `"21:9"`. Must be `"auto"` when `video_url` is set. Omit to let the server choose (`"auto"` if `video_url` or `start_end_frame`, else `"16:9"`)
`native_audio`	boolean	No	`true`	Generate AI audio (two-channel stereo). On by default
`keep_audio`	boolean	No	`true`	Preserve original audio from the source video (`transform` / `video_reference` modes)
`image_urls`	string[]	No	-	Raw reference image URLs uploaded per request (max 10). Use `@Image1`, `@Image2` in `prompt`
`start_image_index`	integer	No	-	1-based index into `image_urls` marking which reference image anchors the first frame
`elements`	ElementInput30[]	No	-	Persistent subject/object assets (max 7, of which at most 3 `type: "video"`). Auto-created on Kling and auto-deleted if submit fails. Use `@Element1`, `@Element2` in `prompt`
`start_frame_url`	string	No	-	First frame image URL (`start_end_frame` mode)
`video_url`	string	No	-	Source video URL (`transform` / `video_reference` modes). Billed per second of the source video at the with-video rate
`multi_shots`	array	No	-	Multi-shot sequence (2–6 shots, each with `prompt` and `duration`, total 3–20 s). Mutually exclusive with `prompt`. Not available in `start_end_frame` mode
`nsfw_check`	boolean	No	`false`	Check the prompt and input images for NSFW content before generating. Off unless set to `true`

Modes

Mode	Required inputs	Optional inputs	Notes
omitted (text-to-video)	`prompt` or `multi_shots`	—	Rejects every input field including `elements`, `image_urls`, `start_frame_url`, `video_url`
`elements`	At least one of `image_urls`, `elements`	—	Combined `image_urls` + `elements` cap of 15 (`image_urls` ≤ 10, `elements` ≤ 7). `video_url` rejected
`start_end_frame`	`start_frame_url`	—	Image-to-video from a first frame. `end_frame_url` and `keyframe_urls` are rejected: last and middle frames are on Kling 4.0 only. `aspect_ratio` is ignored (the frames set it). `elements` and `multi_shots` rejected
`transform`	`video_url`	`image_urls`, `elements`	Combined `image_urls` + `elements` cap of 14 (the source video is the 15th reference). `aspect_ratio` must be `"auto"`
`video_reference`	`video_url`	`image_urls`, `elements`	Combined `image_urls` + `elements` cap of 14. `aspect_ratio` must be `"auto"`

Kling 4.0 Flash vs Kling 4.0 — Flash outputs 720p only and runs up to 20 seconds. For 1080p, videos up to 30 seconds, or last and middle keyframes, use Kling 4.0.

Pricing

Billed per second of output video. With a source video (transform / video_reference modes) or a video-type element, the with-video rate applies; with a source video it is billed per second of the input video.

Mode	Resolution	Per second	With source video
`std`	720p	$0.0756	$0.1008

Example - Text-to-Video

curl -X POST https://api.unifically.com/v1/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "kuaishou/kling-4.0-flash-video",
    "input": {
      "prompt": "A street food vendor flips noodles in a flaming wok at night, sizzling oil and crowd chatter",
      "duration": 5,
      "aspect_ratio": "16:9"
    }
  }'

Example - Reference Images

curl -X POST https://api.unifically.com/v1/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "kuaishou/kling-4.0-flash-video",
    "input": {
      "video_mode": "elements",
      "prompt": "@Image1 and @Image2 meet on the cliff edge in @Image3, laughing",
      "image_urls": [
        "https://example.com/man.jpg",
        "https://example.com/woman.jpg",
        "https://example.com/cliff.jpg"
      ],
      "duration": 10
    }
  }'

Example - Image-to-Video

curl -X POST https://api.unifically.com/v1/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "kuaishou/kling-4.0-flash-video",
    "input": {
      "video_mode": "start_end_frame",
      "prompt": "The camera slowly pushes in as the lights come on",
      "start_frame_url": "https://example.com/street.jpg",
      "duration": 5
    }
  }'

Example - Video Reference

curl -X POST https://api.unifically.com/v1/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "kuaishou/kling-4.0-flash-video",
    "input": {
      "video_mode": "video_reference",
      "prompt": "Same camera move, but in a snowy forest",
      "video_url": "https://example.com/source.mp4"
    }
  }'

Response

{
  "code": 200,
  "success": true,
  "data": {
    "task_id": "abc123def456",
    "status": "processing"
  }
}

Volume discounts are available for almost all models. Reach out at contact@unifically.com to discuss custom pricing.

​Model

​Parameters

​Modes

​Pricing

​Example - Text-to-Video

​Example - Reference Images

​Example - Image-to-Video

​Example - Video Reference

​Response

Model

Parameters

Modes

Pricing

Example - Text-to-Video

Example - Reference Images

Example - Image-to-Video

Example - Video Reference

Response