Kuaishou

Kling V3

Name: Kling V3
Brand: Kuaishou
Price: 0.084 USD
Availability: InStock

AI Video Generation Model

Video

Kuaishou's cinematic video generation model supporting text-to-video and image-to-video with multi-shot control, native audio with voice control, negative prompts, and CFG scale at 720p

Try Model

15 seconds

Max Video Duration

Supported Modes

Text to Video Image to Video

Active

Details

Model ID

kling-v3

Also known as: kling-3, kling-video-v3

Creator

Kuaishou

Family

kling

Released

December 2025

Ready to integrate?

Access kling-v3 via our unified API.

Create Account

Available at 2 providers

Starting from

$0.084 /second via fal.ai · +1 more

Prices shown are in USD

See all providers

Provider Performance

Fastest generation through fal at 89ms median latency with 100.0% success rate.

Aggregated from real API requests over the last 30 days.

Generation Time

fal

p95: 602ms

Success Rate

fal

100.0%

52 / 52 requests

Provider Rankings

#	Provider	p50 Gen Time	p95 Gen Time	Success Rate	TTFB (p50)
1	fal	89ms	602ms	100.0%	—

Data updated every 15 minutes. Based on all API requests through Lumenfall over the last 30 days.

Providers & Pricing (3)

Kling V3 is available from 3 providers, with per-video pricing starting at $0.084 through fal.ai.

fal.ai

Text to Video

fal/kling-v3

Provider Model ID: fal-ai/kling-video/v3/standard/text-to-video

Output

Second

$0.084

Second

$0.126

Second

$0.154

View official pricing • As of Mar 13, 2026

fal.ai

Image to Video

fal/kling-v3-i2v

Provider Model ID: fal-ai/kling-video/v3/standard/image-to-video

Output

Second

$0.084

Second

$0.126

Second

$0.154

View official pricing • As of Mar 13, 2026

Replicate

Text to Video Image to Video

replicate/kling-v3

Provider Model ID: kwaivgi/kling-v3-video

Output

Second

$0.168

Second

$0.252

View official pricing • As of Mar 13, 2026

kling-3 API Async video generation

Integrate Kling V3 into your applications via Lumenfall's OpenAI-compatible API to generate professional 720p video from text and image prompts with precise CFG scale and negative prompt control.

Base URL

https://api.lumenfall.ai/v1

Model

kling-v3

Code Examples

Text to Video

/v1/videos/generations

# Step 1: Submit video generation request

VIDEO_ID=$(curl -s -X POST \

  https://api.lumenfall.ai/v1/videos \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "kling-v3",

    "prompt": "",

    "size": "1024x1024"

  }' | jq -r '.id')

echo "Video ID: $VIDEO_ID"

# Step 2: Poll for completion

while true; do

  RESULT=$(curl -s \

    https://api.lumenfall.ai/v1/videos/$VIDEO_ID \

    -H "Authorization: Bearer $LUMENFALL_API_KEY")

  STATUS=$(echo $RESULT | jq -r '.status')

  echo "Status: $STATUS"

  if [ "$STATUS" = "completed" ]; then

    echo $RESULT | jq -r '.output.url'

    break

  elif [ "$STATUS" = "failed" ]; then

    echo $RESULT | jq -r '.error.message'

    break

fi

  sleep 5

done

const BASE_URL = 'https://api.lumenfall.ai/v1';

const API_KEY = 'YOUR_API_KEY';

// Step 1: Submit video generation request

const submitRes = await fetch(`${BASE_URL}/videos`, {

  method: 'POST',

  headers: {

    'Authorization': `Bearer ${API_KEY}`,

    'Content-Type': 'application/json'

},

  body: JSON.stringify({

    model: 'kling-v3',

    prompt: '',

    size: '1024x1024'

})

});

const { id: videoId } = await submitRes.json();

console.log('Video ID:', videoId);

// Step 2: Poll for completion

while (true) {

  const pollRes = await fetch(`${BASE_URL}/videos/${videoId}`, {

    headers: { 'Authorization': `Bearer ${API_KEY}` }

});

  const result = await pollRes.json();

  if (result.status === 'completed') {

    console.log('Video URL:', result.output.url);

    break;

  } else if (result.status === 'failed') {

    console.error('Error:', result.error.message);

    break;

  await new Promise(r => setTimeout(r, 5000));

import requests

import time

BASE_URL = "https://api.lumenfall.ai/v1"

API_KEY = "YOUR_API_KEY"

HEADERS = {

    "Authorization": f"Bearer {API_KEY}",

    "Content-Type": "application/json"

# Step 1: Submit video generation request

response = requests.post(

    f"{BASE_URL}/videos",

    headers=HEADERS,

    json={

        "model": "kling-v3",

        "prompt": "",

        "size": "1024x1024"

video_id = response.json()["id"]

print(f"Video ID: {video_id}")

# Step 2: Poll for completion

while True:

    result = requests.get(

        f"{BASE_URL}/videos/{video_id}",

        headers=HEADERS

    ).json()

    if result["status"] == "completed":

        print(f"Video URL: {result['output']['url']}")

        break

    elif result["status"] == "failed":

        print(f"Error: {result['error']['message']}")

        break

    time.sleep(5)

Image to Video

/v1/videos/generations

# Step 1: Submit image-to-video request

VIDEO_ID=$(curl -s -X POST \

  https://api.lumenfall.ai/v1/videos \

  -H "Authorization: Bearer $LUMENFALL_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "kling-v3",

    "prompt": "",

    "image_url": "https://example.com/start-frame.jpg",

    "duration": "10",

    "aspect_ratio": "16:9"

  }' | jq -r '.id')

echo "Video ID: $VIDEO_ID"

# Step 2: Poll for completion

while true; do

  RESULT=$(curl -s \

    https://api.lumenfall.ai/v1/videos/$VIDEO_ID \

    -H "Authorization: Bearer $LUMENFALL_API_KEY")

  STATUS=$(echo $RESULT | jq -r '.status')

  echo "Status: $STATUS"

  if [ "$STATUS" = "completed" ]; then

    echo $RESULT | jq -r '.output.url'

    break

  elif [ "$STATUS" = "failed" ]; then

    echo $RESULT | jq -r '.error.message'

    break

fi

  sleep 5

done

const BASE_URL = 'https://api.lumenfall.ai/v1';

const API_KEY = 'YOUR_API_KEY';

// Step 1: Submit image-to-video request

const submitRes = await fetch(`${BASE_URL}/videos`, {

  method: 'POST',

  headers: {

    'Authorization': `Bearer ${API_KEY}`,

    'Content-Type': 'application/json'

},

  body: JSON.stringify({

    model: 'kling-v3',

    prompt: '',

    image_url: 'https://example.com/start-frame.jpg',

    duration: '10',

    aspect_ratio: '16:9'

})

});

const { id: videoId } = await submitRes.json();

console.log('Video ID:', videoId);

// Step 2: Poll for completion

while (true) {

  const pollRes = await fetch(`${BASE_URL}/videos/${videoId}`, {

    headers: { 'Authorization': `Bearer ${API_KEY}` }

});

  const result = await pollRes.json();

  if (result.status === 'completed') {

    console.log('Video URL:', result.output.url);

    break;

  } else if (result.status === 'failed') {

    console.error('Error:', result.error.message);

    break;

  await new Promise(r => setTimeout(r, 5000));

import requests

import time

BASE_URL = "https://api.lumenfall.ai/v1"

API_KEY = "YOUR_API_KEY"

HEADERS = {

    "Authorization": f"Bearer {API_KEY}",

    "Content-Type": "application/json"

# Step 1: Submit image-to-video request

response = requests.post(

    f"{BASE_URL}/videos",

    headers=HEADERS,

    json={

        "model": "kling-v3",

        "prompt": "",

        "image_url": "https://example.com/start-frame.jpg",

        "duration": "10",

        "aspect_ratio": "16:9"

video_id = response.json()["id"]

print(f"Video ID: {video_id}")

# Step 2: Poll for completion

while True:

    result = requests.get(

        f"{BASE_URL}/videos/{video_id}",

        headers=HEADERS

    ).json()

    if result["status"] == "completed":

        print(f"Video URL: {result['output']['url']}")

        break

    elif result["status"] == "failed":

        print(f"Error: {result['error']['message']}")

        break

    time.sleep(5)

Parameter Reference

Required Supported Not available

Core Parameters

Parameter	Type	Description	Modes
`prompt`	string	Required. Text prompt for video generation	T2V I2V
`negative_prompt`	string	Negative prompt to guide generation away from undesired content	T2V I2V
`duration`	number	Video duration in seconds	T2V I2V
`mode` replicate	string	'standard' generates 720p, 'pro' generates 1080p. `pro` `standard` Default: `"pro"`	T2V I2V

Size & Layout

Parameter	Type	Description	Modes
`size`	string	Video dimensions as WxH pixels (e.g. "1920x1080") or aspect ratio (e.g. "16:9") `1365x768` `768x1365` `1024x1024` WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.	T2V I2V
`aspect_ratio`	string	Aspect ratio of the output video (e.g. "16:9", "1:1") `9:16` `1:1` `16:9` Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.	T2V I2V
`resolution`	string	Output resolution tier (e.g. "1K", "4K") `1K` Controls scale independently of shape. Higher tiers produce larger videos and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.	T2V I2V

1K 3 sizes

Output	`size`		`aspect_ratio` + `resolution`
1024 × 1024	`"1024x1024"`	or	`"1:1"` + `"1K"`
768 × 1365	`"768x1365"`	or	`"9:16"` + `"1K"`
1365 × 768	`"1365x768"`	or	`"16:9"` + `"1K"`

How these parameters work

size

Exact pixel dimensions

"1920x1080"

aspect_ratio

Shape only, default scale

"16:9"

resolution

Scale tier, preserves shape

"1K"

Priority when combined

size › aspect_ratio + resolution › aspect_ratio › resolution

size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.

How matching works

Shape matching – we pick the closest supported ratio. Ask for 7:1 on a model with 4:1 and 8:1, you get 8:1.

Scale matching – providers use different tier formats: K tiers (0.5K 1K 2K 4K) or megapixel tiers (0.25 1). If the exact tier isn't available, you get the nearest one.

Dimension clamping – if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.

Character Elements

Parameter	Type	Description	Modes
`elements` fal	array	Elements (characters/objects) to include in the video. Each example can either be an image set (frontal + reference images) or a video. Reference in prompt as @Element1, @Element2, etc.	T2V I2V

Multi-Shot Control

Parameter	Type	Description	Modes
`multi_prompt`	array	List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations.	T2V I2V
`shot_type` fal	string	The type of multi-shot video generation `customize` `intelligent` Default: `"customize"`	T2V I2V

Audio

Parameter	Type	Description	Modes
`generate_audio`	boolean	Whether to generate audio alongside video	T2V I2V

Output & Format

Parameter	Type	Description	Modes
`n`	integer	Number of videos to generate Default: `1` Gateway generates multiple videos in parallel even if provider only supports 1.	T2V I2V

Additional Parameters

Parameter	Type	Description	Modes
`input_reference`	array	Input image(s) to animate into video	T2V I2V
`cfg_scale`	number	Classifier-free guidance scale	T2V I2V
`end_image`	string	End frame image URL for video interpolation	T2V I2V

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior	What happens	Example
`passthrough`	Sent as-is to the provider	style, quality
`renamed`	Same value, mapped to the field name the provider expects	prompt
`converted`	Transformed to the provider's native format	size
`emulated`	Works even if the provider has no concept of it	n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.

Full API Reference Authentication, endpoints, and more

Kling V3 FAQ

How much does Kling V3 cost?

Kling V3 starts at $0.084 per video through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

How do I use Kling V3 via API?

You can use Kling V3 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "kling-v3". Code examples are available in Python, JavaScript, and cURL.

Which providers offer Kling V3?

Kling V3 is available through fal.ai and Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.

Overview

Kling V3 is a cinematic video generation model developed by Kuaishou, designed to produce high-fidelity video sequences from either text prompts or static images. It represents a significant iteration in the Kling family, introducing native audio generation and precise control over cinematic parameters like multi-shot coordination and voice-synchronized output. The model is distinctive for its ability to output video at 720p resolution while maintaining temporal consistency across complex motions.

Strengths

Integrated Audio Synthesis: Unlike models that require post-production dubbing, Kling V3 generates native audio with direct voice control, ensuring sound effects and speech are synchronized with the visual action.
Multi-Shot Control: The model excels at maintaining character and environmental consistency across multiple shots within a single generation, reducing the visual “drift” common in long-form AI video.
Fine-Grained Steering: Developers can utilize negative prompts and adjustable Classifier-Free Guidance (CFG) scales to tightly constrain the output, allowing for better adherence to specific brand guidelines or aesthetic requirements.
Dynamic Motion Handling: It demonstrates high proficiency in rendering complex human movements and fluid physics, making it suitable for realistic storytelling rather than just static “living portraits.”

Limitations

Resolution Constraints: While the model produces high-quality cinematic content, it is currently capped at 720p native resolution, which may require upscaling for 4K professional broadcast workflows.
Inference Latency: Due to the complexity of simultaneous video and audio synthesis, generation times may be higher compared to models that focus exclusively on visual frames.
Niche Stylization: While excellent for realistic and cinematic styles, it may struggle with highly abstract or non-Euclidean artistic prompts where spatial logic is intentionally broken.

Technical Background

Kling V3 is built on a sophisticated diffusion transformer architecture optimized for spatio-temporal modeling. It utilizes a joint training approach where video and audio data are processed in the same latent space, allowing the model to learn the fundamental relationships between visual motion and acoustic signals. This version places a heavy emphasis on CFG scaling and negative prompt integration to improve prompt adherence over its predecessors.

Best For

Kling V3 is ideal for creators developing marketing assets, cinematic trailers, and social media content that requires “one-shot” generation of both visuals and sound. It is particularly effective for character-driven narratives where lip-syncing or specific voice parameters are necessary. You can experiment with Kling V3’s Text-to-Video and Image-to-Video modes through Lumenfall’s unified API and interactive playground to integrate high-end video synthesis into your existing applications.

Try Kling V3 in Playground

Generate images with custom prompts — no API key needed.

Open Playground