Kling v3

Video generationNewAvailable
by Kuaishou (Kling)Model ID: kling-v3

Cinematic video up to 15s with multi-shot and native audio

Price
$0.2688/s
Aspect ratios
16:9, 9:16, 1:1
Duration
3, 5, 10, or 15 s
Input โ†’ output
Text + Image โ†’ Video
Developer
Kuaishou (Kling)
Updated
September 23, 2026
01

Playground

Try Kling v3

Input & output

$0.2688/s
Try Kling v3
Output
Your video appears here.

This run

$1.344 ยท 134.4 credits

Billed: 5 s

For accounts without a purchase: runs above 2 credits need a top-up.

New here?

10 free credits ($0.10) when you sign up with Google

Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits.

02

Examples

Real outputs from the public examples of this model on Replicate, with the prompt and settings that produced them. They were not generated live on this page.
  • Prompt

    First-person POV of a roller coaster plunging into the mouth of an erupting volcano. The track spirals down through rivers of glowing orange lava, sparks and embers flying past the camera. The coaster banks hard around a pillar of molten rock, then launches upward through a vent, bursting out of the volcano's crater into a dazzling sunset sky above the clouds. Wind roaring, riders screaming with excitement, the deep rumble of the volcano.

    Length: 0:08

    Settings

    aspect_ratio
    16:9
    duration
    15
    mode
    pro
  • Prompt

    Bamse, the world's strongest bear, a cartoon brown bear wearing blue overalls and a blue knit cap, lifts an enormous boulder over his head and hurls it across a sunny Swedish meadow. Wildflowers scatter in the wind. His friends, a small rabbit and a turtle with a shell full of gadgets, cheer from behind a wooden fence. Bright, colorful 2D animation style with thick outlines. Cheerful music, a triumphant fanfare, birds chirping.

    Length: 0:08

    Settings

    aspect_ratio
    16:9
    duration
    10
    mode
    pro
  • Prompt

    Cinematic drone footage of a dragon made of living fire soaring over a frozen Nordic fjord at twilight. Its wings trail streams of flame that melt the ice below, creating swirling clouds of steam. The dragon banks sharply and breathes a column of fire across the mountainside, igniting the snow in brilliant orange and gold. Northern lights shimmer green and purple in the sky above. Thunderous wingbeats, crackling fire, hissing steam, a deep otherworldly growl.

    Length: 0:08

    Settings

    aspect_ratio
    16:9
    duration
    15
    mode
    pro

Example prompts

Examples from the Railwail catalog. They were not generated live on this page.

  • Action

    Length: 0:10

    Parkour athlete on rooftops at sunset
03

About Kling v3

TL;DRAs of September 23, 2026

Kling v3 is a model by Kuaishou (Kling) in the Video generation category. On Railwail, Kling v3 costs $0.2688 per second of video. Depending on the settings, the price ranges from $0.2016/s to $0.504/s. A default run of 5 seconds costs $1.344. Supported aspect ratios: 16:9, 9:16, and 1:1. Possible lengths: 3, 5, 10, or 15 s.

Background

About Kuaishou Technology

Founded 2011 ยท Beijing, China

Kuaishou Technology, founded in 2011 by Su Hua and Cheng Yixiao, is one of China's two dominant short-video platforms, with ~700M monthly active users in 2025. Its KLING AI team shipped Kling 1.0 in June 2024, Kling 1.5 and 1.6 (late 2024), Kling 2.0 (Q1 2025) and Kling v3 (mid-2025). Kling v3 introduced native synchronized audio (sound effects and dialogue), 1080p+ at 30 fps, much improved motion physics, and the Omni multimodal-conditioning variant. The model is exposed via klingai.com, the Kling mobile app and a commercial API and is widely used by Chinese ad agencies, music labels and social-media creators.

Visit Kuaishou Technology

Architecture

Diffusion Transformer (DiT) with 3D spatio-temporal VAE and joint audio-video diffusion

Kling v3 is a closed-source video diffusion model built on Kuaishou's third-generation Diffusion Transformer architecture. The denoiser operates on a 3D spatio-temporal latent produced by a high-compression VAE and uses full 3D spatio-temporal attention rather than factorised attention. v3's headline change is a joint audio-video diffusion module that generates synchronized soundtrack (ambient sound, footsteps, music swells and short dialogue) aligned to the visual track. Text conditioning uses a bilingual LLM encoder with extended context for very long prompts; image conditioning supports first-frame, end-frame and subject-reference modes. Training uses a curated multi-billion-clip corpus (including platform data) with synthetic dense audio-visual captions; post-training combines reward-model alignment for visual aesthetics, prompt fidelity and audio-video sync.

Parameters
Undisclosed

Capabilities

  • Text-to-video, image-to-video and subject-reference modes
  • 1080p / 30 fps clips up to 10 seconds natively, extendable beyond 1 minute
  • Synchronized native audio (ambient sound, simple dialogue, music swells)
  • Director-style camera control (lenses, rigs, moves)
  • Strong physics on water, fabric, hair and crowd dynamics
  • Bilingual Chinese/English prompts with extended context
  • Lip-sync and motion-brush in Kling editor
  • Commercial API and Kling editor integration
  • Best for: cinematic shorts, ads with audio, music videos, character-driven content.

Training & license

Closed multi-billion-clip corpus combining licensed video, web video and Kuaishou platform data, with dense audio-visual captions; exact size undisclosed.

License: Proprietary commercial licence via Kling AI / Kuaishou terms; commercial use on paid plans.

Safety testing: NSFW, CSAM, public-figure, copyright and politically sensitive content filters in line with CAC rules; stricter moderation on Chinese surfaces; audio module includes anti-impersonation checks.

Known limitations

  • 10-second native clip limit
  • Audio quality is short-form (limited length and music sophistication)
  • Heavy political and public-figure moderation
  • Closed model with no public technical paper
  • Output queues during peak hours
04

Pricing

Prices in US dollars. Usage is charged from prepaid credits.
mode: standard ยท generate_audio: false$0.2016 per second of video
mode: standard ยท generate_audio: true$0.3024 per second of video
mode: pro ยท generate_audio: falseDefault$0.2688 per second of video
mode: pro ยท generate_audio: true$0.4032 per second of video
mode: 4k ยท generate_audio: false$0.504 per second of video
mode: 4k ยท generate_audio: true$0.504 per second of video
Default run (5 s)$1.344 per run
  • 1 credit = $0.01

Cost calculator

Price calculator

Variant
s

Total

$134.40

13,440 credits

Per run

$1.344 ยท 134.4 credits

billed as 5 s

Fixed price per run, known before the run starts.

05

API

Call Kling v3 with your Railwail API key. Use this model ID in the request:
curl https://railwail.com/api/v1/videos/generations \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-v3",
    "prompt": "A slow drone shot over a misty pine forest at sunrise"
  }'

# Response: {"job_id": "...", "status": "queued", ...}
# Poll until status is completed, failed or cancelled:
curl https://railwail.com/api/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAILWAIL_API_KEY"
Set your key as RAILWAIL_API_KEYCreate API key

Videos run asynchronously: the first call returns a job_id; query /api/v1/jobs/JOB_ID until the status is completed.

06

Specifications

Model ID
kling-v3
Input
Text, Image
Output
Video
Output formats
MP4
Aspect ratios
16:9, 9:16, 1:1
Duration
3, 5, 10, or 15 s
Billing
Fixed price, known before the run
Model size
Undisclosed
License
Proprietary commercial licence via Kling AI / Kuaishou terms; commercial use on paid plans.
Catalog entry updated
September 23, 2026

Input parameters

Inputs and settings from the model's input schema. The example in the API section shows which of them the API accepts.

  • promptrequired
    Type: Text
    Default: โ€“
    Allowed values: โ€“
  • duration
    Type: Choice
    Default: 5
    Allowed values: 3, 5, 10, or 15
  • end_image
    Type: Image
    Default: โ€“
    Allowed values: โ€“
  • start_image
    Type: Image
    Default: โ€“
    Allowed values: โ€“
  • aspect_ratio
    Type: Choice
    Default: โ€“
    Allowed values: 16:9, 9:16, or 1:1

Tags

  • popular
  • audio
  • i2v
07

Use cases

What it is used for

  • Cinematic shorts with sound design
  • Ad creative
  • Music-video animatics
  • Character-driven shorts
  • Stylised product video
  • Storyboards with audio
08

Frequently asked questions

What is Kling v3?

Kling v3 is a model by Kuaishou (Kling) in the Video generation category. On Railwail you can call it with an API key through the Railwail API.

How much does Kling v3 cost on Railwail?

On Railwail, Kling v3 costs $0.2688 per second of video. Depending on the settings, the price ranges from $0.2016/s to $0.504/s. A default run of 5 seconds costs $1.344. The price is known before the run starts. Usage is paid from prepaid credits; 1 credit equals $0.01.

Which settings does Kling v3 support?

According to its input schema, Kling v3 knows these parameters: prompt, duration (3, 5, 10, or 15), end_image, start_image, and aspect_ratio (16:9, 9:16, or 1:1).

How fast is Kling v3?

There are not enough measured runs of Kling v3 on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.

Is Kling v3 better than Google Veo 3.1?

That depends on the task. Kling v3 (Kuaishou (Kling)) and Google Veo 3.1 (Google DeepMind) are both models in the Video generation category. The comparison page shows their prices and specifications side by side.

Compare Kling v3 and Google Veo 3.1

Can Kling v3 use an image as input?

Yes. Send the image in the end_image parameter.

How do I use Kling v3 through the API?

Create a Railwail API key and send your request with the model ID kling-v3. Code examples for curl, Python and JavaScript are in the API section of this page.

09

Comparable models

All in this category

Use Kling v3 via the API

One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = $0.01.