Kling 4.0 Flash API for Fast 720p Video with Sound

Kling 4.0 Flash is the faster, lower-cost version of Kling 4.0. Send a prompt to POST /api/v1/videos/generations with model: kling-4-0-flash, optionally with a first frame in image_url, and get a 720p single take of 3 to 20 seconds with a native audio track. Track the job with the returned img_uuid.
Get API Key
Motorbike rider on a coastal road with a camera car tracking alongside

Kling 4.0 Speed at a Lower Price

Single takes up to 20 seconds

duration takes any integer from 3 to 20 (default 5), so one request can cover a full shot.
Stopwatch beside a clapperboard on a director's chair

Start from a first frame

Pass image_url to animate your image; the aspect ratio follows it. Images up to 10MB, at least 300px wide and tall, between 2:5 and 5:2.
Printed photo of a lighthouse being placed under a camera on a copy stand

Audio included in every clip

Each video comes with a native audio track. There is no switch, so sound / generate_audio are rejected.
Headphones and a field recorder on a rock by a waterfall
A prompt is required; a first frame switches to image-to-video.

Kling 4.0 Flash Request Fields and Limits

model

Always kling-4-0-flash.

prompt (required)

Scene, motion and camera, up to 2500 characters.

image_url

Optional first frame. Up to 10MB, width and height at least 300px, aspect ratio between 2:5 and 5:2; smaller images are upscaled automatically.

duration, resolution and ratio

duration: integer 3-20, default 5. resolution: 720p only. ratio: 16:9 (default), 9:16, 1:1 or 21:9, text-to-video only.

Rejected fields

image_end_url and keyframes (use Kling 4.0), reference images or videos (use Kling 4.0 Flash Reference to Video), sound / generate_audio, negative_prompt, seed, model_params.multi_shot and 1080p / 4K are rejected before any tokens are charged.

custom_callback_url

Optional public HTTPS URL. GoEnhance POSTs the same body as GET /api/v1/jobs/detail when the task status changes, with up to 3 retries.
Billed per second of generated video; text-to-video and image-to-video cost the same.

Kling 4.0 Flash API Pricing

720p: 5.5715 tokens ($0.11143) per second

The only resolution for this model.

5-second clip

27.86 tokens ($0.5572).

20-second clip

111.43 tokens ($2.2286).

Integrate the Kling 4.0 Flash API

1

1. Create an API key

Generate a key at /keys and send it as Authorization: Bearer <key>.
2

2. Prepare the request

POST model, prompt and an optional image_url to /api/v1/videos/generations.
3

3. Store img_uuid

Keep the returned img_uuid and poll GET /api/v1/jobs/detail, or pass custom_callback_url.
4

4. Save the video

When the status is success, download the video and store it on your side.
Create an API Key
High-volume clips where 720p is enough.

What Developers Build with Kling 4.0 Flash

Social clip generators

Turn a prompt into a vertical 9:16 clip with sound for short-video apps.

Photo animation

Animate a user's photo from image_url into a 3-20 second shot.

Draft before a final render

Iterate on prompts with Flash, then send the chosen version to Kling 4.0 for 1080p or last-frame control.

Cinematic widescreen shots

Use 21:9 for banner and trailer-style shots from text.
Common questions about requests and billing.

Kling 4.0 Flash API FAQ

How is Kling 4.0 Flash different from Kling 4.0?

Flash is faster and costs less, but outputs 720p only, up to 20 seconds, and takes a first frame only: no last frame or middle keyframes.

Can I turn the audio off?

No. Every clip includes native audio and sound / generate_audio are rejected.

Can I set the aspect ratio for image-to-video?

No. With image_url the output follows your image and ratio is ignored.

Can I use reference images or videos?

Use the kling-4-0-flash-refs model for references, and kling-4-0-flash-edit to edit a video.

What happens if I send 1080p?

The request is rejected before any tokens are charged; only 720p is supported.

Start Building with the Kling 4.0 Flash API

Kling 4.0 Flash API: Pricing & Integration | GoEnhance