Kling V3

Kling V3 is a general video model supporting text, images, first-and-last frames, motion control, digital humans, and generated audio, with additional image generation and editing capabilities. It is suited to creative prototyping, advertising assets, social media production, and automated video workflows that need repeatable API access. Use the playground below to test representative prompts, input media, duration, resolution, aspect ratio, and other controls that are available for this model. Before production rollout, compare motion quality, subject consistency, processing time, failure handling, and estimated cost with your actual workload. The controls shown on this page describe the currently supported integration options.

A stunt performer in red tracked by a motion-control camera on a film stage

Model ID: kling-v3
Provider: Kling
API endpoint: /v1/videos
Pricing: 0.117647058824
Last updated: 2026-08-13

Capabilities

Video generation through the current public task endpoint
Image, reference, duration, or resolution controls when exposed by the live schema
Current parameters including prompt, operation, resolution

Limitations

Capabilities and parameter ranges can change; pin and validate the parameter set used in production
Do not assume support for parameters absent from the live request schema
Asynchronous jobs require explicit polling, failure, timeout, and safety-status handling

Use cases

Product prototypes and automated content workflows
Batch media generation and programmatic creative tooling
Multi-model applications that need unified authentication, billing, and usage records

Pricing and billing examples

PRO digital human by audio duration | 0.117647058824 | input_audio_seconds | {"input_audio_seconds":{"gt":0},"operation":"video.avatar","resolution_tier":"pro"}
PRO digital human voice estimate (5 seconds) | 0.588235294118 | output_videos | {"input_audio_seconds":0,"operation":"video.avatar","resolution_tier":"pro"}
STD digital human by audio duration | 0.058823529412 | input_audio_seconds | {"input_audio_seconds":{"gt":0},"operation":"video.avatar","resolution_tier":"std"}
STD digital human voice estimate (5 seconds) | 0.294117647059 | output_videos | {"input_audio_seconds":0,"operation":"video.avatar","resolution_tier":"std"}
Subject image completion | 0.073529411765 | output_images | {"operation":"image.complete_subject"}
Image generation, editing, or outpainting | 0.029411764706 | output_images | {"operation":["image.generate","image.edit","image.outpaint"]}
PRO motion control | 0.176470588235 | input_video_seconds | {"operation":"video.motion_control","resolution_tier":"pro"}
STD motion control | 0.132352941176 | input_video_seconds | {"operation":"video.motion_control","resolution_tier":"std"}
PRO video output with audio | 0.176470588235 | output_video_seconds | {"generated_audio":true,"operation":["video.generate","video.image_to_video","video.reference_to_video"],"resolution_tier":"pro"}
PRO silent video output | 0.117647058824 | output_video_seconds | {"generated_audio":false,"operation":["video.generate","video.image_to_video","video.reference_to_video"],"resolution_tier":"pro"}
STD video output with audio | 0.132352941176 | output_video_seconds | {"generated_audio":true,"operation":["video.generate","video.image_to_video","video.reference_to_video"],"resolution_tier":"std"}
STD silent video output | 0.088235294118 | output_video_seconds | {"generated_audio":false,"operation":["video.generate","video.image_to_video","video.reference_to_video"],"resolution_tier":"std"}

Request parameters

Parameter	Type	Required	Default	Options
model	string	Yes
prompt	textarea	Yes
operation	select	Yes	text_to_video	text_to_video, image_to_video, first_last_frame, motion_control, avatar
resolution	select	Yes	std	std, pro
duration	integer	No	5
aspect_ratio	select	No	16:9	16:9, 9:16, 1:1
sound	select	No	off	off, on
image	asset_list	No
last_image	asset_list	No
watermark	boolean	No	false

API examples

cURL

curl -X POST 'https://api.uniall.ai/v1/videos' \
  -H 'Authorization: Bearer $UNIALL_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"aspect_ratio":"16:9","duration":5,"model":"kling-v3","operation":"text_to_video","prompt":"Describe the output you want","resolution":"std","sound":"off","watermark":false}'

Python

import json
import requests

payload = json.loads(r'''{"aspect_ratio":"16:9","duration":5,"model":"kling-v3","operation":"text_to_video","prompt":"Describe the output you want","resolution":"std","sound":"off","watermark":false}''')
response = requests.post(
    "https://api.uniall.ai/v1/videos",
    headers={"Authorization": "Bearer " + UNIALL_API_KEY},
    json=payload,
)
response.raise_for_status()
result = response.json()

JavaScript

const response = await fetch("https://api.uniall.ai/v1/videos", {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.UNIALL_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({"aspect_ratio":"16:9","duration":5,"model":"kling-v3","operation":"text_to_video","prompt":"Describe the output you want","resolution":"std","sound":"off","watermark":false}),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
const result = await response.json();

Frequently asked questions

What API endpoint does kling-v3 use?

The endpoint is resolved from the current model capabilities and request schema and shown on this page.

How is kling-v3 priced?

The pricing section reads the current structured billing configuration, so editorial text does not need a rewrite after a price change.

Can I use Python?

Yes. The example uses the current endpoint and exact model identifier.

Are JavaScript and cURL examples included?

Yes. All examples share the same live request structure.

Which resolution, duration, or reference-image controls are supported?

Supported controls come from the current request schema. Do not assume fields that are not listed.

What should I validate before production use?

Validate parameters, timeouts, error handling, and asynchronous video task status behavior after model updates.