KuaishouvideoNewOperational

Kling 3.0 Omni API

Kling 3.0 with multi-image references for consistent characters

kuaishou/kling-3.0-omni/text-to-video kuaishou/kling-3.0-omni/image-to-video kuaishou/kling-3.0-omni/reference-to-video

FromUp to −12%

$0.074/s$0.084

per second of video · 720p

Open in Studio API

Try Kling 3.0 Omni

Runs on your balance at the price shown on the button. Results are saved to your account.

Open full-screen Studio

Prompt*

0/5000

Aspect ratio

Output frame shape.

Resolution

Output resolution. Higher resolutions cost more per second.

Duration

Length of the generated clip in seconds (3–15s). You pay per second.

Generate audio

Generate synchronized sound, ambience and dialogue. Clips with audio are billed at a higher per-second rate.

Estimated cost…

Create a free account with Google or email — pay only for what you generate.

Your video will appear here

Write a prompt, pick your settings and hit Run. You only pay for successful generations.

What is Kling 3.0 Omni?

Kling 3.0 Omni turns text, a first and last frame, or up to 7 reference images into 3–15 second 720p or 1080p videos with consistent characters and optional native audio.

Up to 7 references

People, products, scenes

720p / 1080p

Standard and professional

3–15 seconds

Pay per second

Native audio

Optional, at a lower rate than Kling 3.0

One model, every input

Omni is Kling's unified multimodal video model: generate from text, animate a first (and last) frame, or combine several reference images of people, products and places — then refer to them in the prompt as @Image1, @Image2…

Consistency across shots

Reference images keep faces, outfits and products on-model, making Omni the Kling choice for branded content, storyboards and recurring characters.

Kling 3.0 Omni pricing

Pay per second of video. No subscription. Failed generations are refunded automatically.

Tier	Official price	Cheaper Gen.	You save
720p silent	~~$0.084~~/s	$0.074/s	−12%
720p + audio with native audio	~~$0.112~~/s	$0.099/s	−12%
1080p silent	~~$0.112~~/s	$0.099/s	−12%
1080p + audio with native audio	~~$0.14~~/s	$0.123/s	−12%

Official price: Kling developer API list price for Kling 3.0 Omni without video input ($0.084 / s at 720p, $0.112 / s at 1080p; with native audio $0.112 / $0.14). Prices verified 2026-10-16.
Reference images are included in the price.
Native audio is billed at a higher per-second rate.

Specifications

Resolutions: 720p · 1080p
Duration: 3–15 s
Aspect ratios: 16:9 · 9:16 · 1:1
Audio: Optional (billed higher)
Inputs: Text, first/last frame, or up to 7 reference images
Released: Feb 25, 2026

Use Kling 3.0 Omni via API

One request to start a job, one to fetch the result. Same shape for every model.

Full API reference

import os, time, requests

API = "https://cheapergen.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['CHEAPERGEN_API_KEY']}"}

# 1. Submit the job
job = requests.post(f"{API}/run/kuaishou/kling-3.0-omni/text-to-video", headers=headers, json={
    "prompt": "A lone samurai walks through falling cherry blossoms at dusk, slow tracking shot, cinematic lighting",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5
}).json()

# 2. Poll until it finishes (or pass "webhook_url" and skip polling)
while job["status"] in ("queued", "running"):
    time.sleep(3)
    job = requests.get(f"{API}/generations/{job['id']}", headers=headers).json()

print(job["status"], job["output"]["video"]["url"] if job["status"] == "succeeded" else job["error"])

const API = "https://cheapergen.com/api/v1";
const headers = {
  Authorization: `Bearer ${process.env.CHEAPERGEN_API_KEY}`,
  "Content-Type": "application/json",
};

// 1. Submit the job
let job = await fetch(`${API}/run/kuaishou/kling-3.0-omni/text-to-video`, {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A lone samurai walks through falling cherry blossoms at dusk, slow tracking shot, cinematic lighting",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5
  }),
}).then((r) => r.json());

// 2. Poll until it finishes (or pass webhook_url and skip polling)
while (job.status === "queued" || job.status === "running") {
  await new Promise((r) => setTimeout(r, 3000));
  job = await fetch(`${API}/generations/${job.id}`, { headers }).then((r) => r.json());
}

console.log(job.status === "succeeded" ? job.output.video.url : job.error);

curl -X POST https://cheapergen.com/api/v1/run/kuaishou/kling-3.0-omni/text-to-video \
  -H "Authorization: Bearer $CHEAPERGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "prompt": "A lone samurai walks through falling cherry blossoms at dusk, slow tracking shot, cinematic lighting",
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "duration": 5
}'

Text to Video

kuaishou/kling-3.0-omni/text-to-video

Image to Video

kuaishou/kling-3.0-omni/image-to-video

Reference to Video

kuaishou/kling-3.0-omni/reference-to-video

Example prompts

Hit “Try it” to load a prompt into the playground above.

Reference to Video
@Image1 tries on the jacket from @Image2 in front of a mirror, then turns to camera and smiles
Try it
A paper crane unfolds into a real bird and flies out of an open window, morning light
Try it
Reference to Video
@Image1 and @Image2 share an umbrella crossing a rainy Tokyo street at night, slow dolly
Try it

Kling 3.0 Omni FAQ

Kling 3.0 Omni is billed per second of output video. 1080p costs more than 720p, and native audio is billed at a higher per-second rate — the price updates as you change the settings. Failed generations are never charged.

Yes. Requests run on Kuaishou's Kling 3.0 Omni through official API channels — the same model and output quality as the Kling developer API, at a lower price.

Attach up to 7 images in Reference to Video and mention them in the prompt as @Image1, @Image2… — for example "@Image1 wears the jacket from @Image2". Reference images don't cost extra.

Yes, subject to Kuaishou's Kling usage policy and our Terms of Service.

Related models

Kuaishou

PopularUp to −12%

Kling3.0

Text · Image → Video

from$0.074/s$0.084

Kling's flagship video model — cinematic motion, native audio, up to 15 s

Shengshu

Up to −9%

ViduQ3 Mix

Reference → Video

from$0.11/s$0.12

Vidu's premium reference-to-video: up to 7 images, consistent subjects

ByteDance

PopularUp to −20%

Seedance2.0

Text · Image · Reference → Video

from$0.057/s$0.07

Cinematic multi-shot video with native audio, up to 4K

Kling 3.0 Omni is developed by Kuaishou. Cheaper Gen. provides API access through official upstream endpoints and does not own the model. Trademarks belong to their respective owners. · Markdown · OpenAPI