Kling 3.0 API

Use EvoLink's unified API to access Kling 3.0 text-to-video and image-to-video. Generate 3-15 second videos with per-second billing, one integration path, and production-ready async delivery.

Model Type:

Kling 3.0 Text to Video Kling 3.0 Image to Video ✓Custom Element

Price: $0.014(~ 1 credits) per request

Highest stability with guaranteed 99.9% uptime. Recommended for production environments.

Use the same API endpoint for all versions. Only the model parameter differs.

Reference Type*

Choose whether to create element from images or video

Frontal Image *

Frontal view of the subject — must contain a visible human face (1 image)

Click to upload or drag and drop

Supported formats: JPG, JPEG, PNG
Maximum file size: 10MB; Maximum files: 1

Reference Angles *

Other angle reference images — must contain a visible human face (optional, 1-3)

Click to upload or drag and drop

Supported formats: JPG, JPEG, PNG
Maximum file size: 10MB; Maximum files: 3

Element Name*

Name of the subject element (max 20 characters)

Element Description*

Description of the subject element (max 100 characters)

No video URL found in response

Check console for details

History

Max 20 items

0 running · 0 completed

Your generation history will appear here

Billing Rules

•Fixed price: 1 Credit per element creation
•Full refund on failure
•Estimated processing time: ~10 minutes

Pricing

Model	Mode	Type	Price
Kling Custom Element	Element Creation	Element Creation	$0.014/ request(1 Credits)

Kling Custom Element

Element Creation

Type:Element Creation

Price:

$0.014/ request

(1 Credits)

If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.

Kling 3.0 API Pricing, Playground, and Integration

Access Kling 3.0 through EvoLink's unified API. Use text-to-video and image-to-video routes with async delivery, per-second pricing, and one integration path for production workflows.

Kling 3.0 pricing starts at $0.075 per second on EvoLink, compared to $0.084 on the official Kling API. Generate 3-15 second videos from text or images with free credits to start, no deposit required.

Hero showcase of Kling 3.0 video capabilities

Kling 3.0 overview and version history

Kling 3.0 is the standard video generation model in the Kling AI family by Kuaishou. Two modes — text-to-video and image-to-video — produce 3-15 second clips at 720p or 1080p with per-second billing.

Compared to Kling 2.1 and 1.6, version 3.0 improved motion quality, scene coherence, and prompt adherence. It also added multi-shot support, AI sound effects, and subject control for consistent characters across clips. Access Kling 3.0 on EvoLink with free credits, a built-in playground, and pricing lower than the official rate.

Kling 3.0 API video modes and workflow features

Kling 3.0 Text-to-Video API

Generate videos directly from text prompts with Kling 3.0. Describe scenes, actions, and styles in natural language and let the model produce 3-15 second clips ready for marketing, social media, or creative projects.

Kling 3.0 Image-to-Video API

Use images to guide video generation. Kling 3.0 supports image-to-video mode, giving teams precise control over visual style, character consistency, and scene composition.

Kling 3.0 Multi-Shot and Sound Effects

Create complex multi-shot videos with scene transitions and add AI-generated sound effects. Kling 3.0 supports customizable shot sequences and audio generation for professional-quality output.

Why teams use Kling 3.0 through EvoLink

Kling 3.0 gives teams text-to-video and image-to-video access through one gateway, making pricing, routing, and production integration easier to manage.

One API for two core Kling 3.0 modes

Use the same integration path for text-to-video and image-to-video, instead of splitting implementation across separate vendor setups.

Cleaner production integration

Async task handling, one API key, and unified billing make it easier to run Kling 3.0 inside internal tools, creator products, and automation workflows.

Predictable per-second pricing

3-15 second output windows and visible quality options help teams estimate cost before sending production traffic.

How to integrate the Kling 3.0 API

From input to production-ready video in three steps.

Choose your mode

Select text-to-video or image-to-video based on your workflow needs.

Submit a generation task

Send your request with prompts or images. Track the async task until results are ready.

Review and iterate

Download results, compare variations, and reuse the same structure for fast iteration across campaigns.

View API Docs

Kling 3.0 API capabilities

Text-to-video and image-to-video access through one production-ready gateway

Text

Text-to-video generation

Generate videos purely from text descriptions. Kling 3.0 interprets natural language prompts to produce dynamic video content without requiring any visual input.

Image

Image-to-video transformation

Transform static images into dynamic videos. Provide reference images and let Kling 3.0 animate them with natural motion and scene dynamics.

Multi-Shot

Multi-shot support

Create complex multi-shot videos with customizable scene transitions, per-shot prompts, and duration control for professional video production.

Sound

Sound effects

Add AI-generated sound effects to your videos. Toggle sound on or off based on your needs, with transparent pricing for audio generation.

Billing

Per-second billing

Pay only for what you generate with per-second billing. Videos range from 3 to 15 seconds, giving teams precise cost control for every project.

Quality

720p & 1080p quality

Choose between standard 720p and high-quality 1080p output resolution to balance quality and cost for your specific use case.

Kling 3.0 API FAQ

Everything you need to know about the product and billing.

The Kling 3.0 API provides access to Kling's 3.0 video model through EvoLink. It supports two modes: text-to-video and image-to-video. Each mode generates 3-15 second videos with per-second billing. Use your EvoLink dashboard for current pricing and availability.

Kling 3.0 offers two modes: text-to-video for generating from prompts, and image-to-video for animating images. Each mode is optimized for different production workflows.

Kling 3.0 generates videos between 3 and 15 seconds. Billing is per-second within this range. Videos shorter than 3 seconds are billed at the 3-second minimum. This range is suitable for social media clips, ads, and short-form content.

Kling 3.0 uses per-second billing at 5.4 credits per second base rate. The price varies by quality and sound: 720p+off = 1.0x, 720p+on = 1.5x, 1080p+off = 1.333x, 1080p+on = 2.0x. Check your EvoLink dashboard for your group's specific pricing.

Kling O3 (V3 Omni) supports four modes including reference-to-video and video editing, while Kling 3.0 focuses on text-to-video and image-to-video. 3.0 has slightly different pricing factors compared to O3.

Start with a clear subject and describe the action, mood, and setting in simple terms. For image-to-video, provide high-quality reference images. Consistency improves when your prompt structure stays stable across runs.

Limits, pricing, and available modes are determined by your provider and region. Use your EvoLink dashboard and API responses as the source of truth. Check the API documentation for the most current constraints and parameters.

All Kling AI Models

EvoLink provides unified API access to the full Kling model family: All models share the same API key. Switch models with one parameter.

Explore Kling family View Kling O1 View Kling O3 View Motion Control

API Reference

Select endpoint

Authentication

All APIs require Bearer Token authentication.

Header

Authorization: 
Bearer YOUR_API_KEY

Get API Key

POST

/v1/videos/generations

Create Element

Kling Custom Element (kling-custom-element) creates reusable subjects (elements) from reference images or videos. Created elements can be referenced in Kling V3 Image-to-Video, Kling O3 series, and Kling V3 Motion Control video generation via element_list for consistent character appearance.

Asynchronous processing mode, use the returned task ID to query status.

Upon completion, result_data will contain the element_id for use in video generation.

Important Notes

This model creates reusable elements (subjects), not videos. No prompt/duration/quality/aspect_ratio parameters needed.
The reference image or video must contain a clearly visible human face.
Fixed pricing: 1 Credit per element creation. Full refund on failure.
Estimated processing time: approximately 10 minutes.
After successful creation, use the returned element_id in Kling V3 Image-to-Video, Kling O3 series, and Kling V3 Motion Control video generation via element_list.

Request Parameters

modelstringRequiredDefault: kling-custom-element

Model name for custom element creation.

Examplekling-custom-element

model_params.element_namestringRequired

Name for the element (subject) being created.

Notes

Max 20 characters

ExampleMyCharacter

model_params.element_descriptionstringRequired

Description of the element, used to help the model understand the subject characteristics.

Notes

Max 100 characters

ExampleA young male character with short hair, wearing a white T-shirt

model_params.reference_typestringRequired

Type of reference material used to create the element.

Value	Description
image_refer	Use reference images to create element
video_refer	Use reference video to create element

Exampleimage_refer

model_params.element_image_listobjectOptional

Reference image list for element creation. Required when reference_type is image_refer.

Notes

Conditionally required: must be provided when reference_type = image_refer
frontal_image (string): URL of the frontal reference image (recommended)
refer_images (array): Additional reference images, each with an image_url field
Use clear, well-lit images with the subject clearly visible for best results
The reference images must contain a clearly visible human face

Example{"frontal_image": "https://example.com/front.jpg", "refer_images": [{"image_url": "https://example.com/side.jpg"}]}

model_params.element_video_listobjectOptional

Reference video for element creation. Required when reference_type is video_refer.

Notes

Conditionally required: must be provided when reference_type = video_refer
video_url (string): URL of the reference video
The reference video must contain a clearly visible human face

Example{"video_url": "https://example.com/reference.mp4"}

model_params.element_voice_idstringOptional

Voice ID to assign to the element. The voice will be used when the element speaks in generated videos.

Notes

Optional parameter — only supported when reference_type = video_refer
Not available for image_refer (image-based element creation does not support voice assignment)
See the Voice ID Reference section below for all available voice IDs

Example829824295735410756

callback_urlstringOptional

HTTPS callback address after task completion.

Notes

Triggered on completion, failure, or cancellation
HTTPS only, no internal IPs
Max length: 2048 chars
Timeout: 10s, Max 3 retries

Examplehttps://your-domain.com/webhooks/element-task-completed

Request Example (Image Reference)

{
  "model": "kling-custom-element",
  "model_params": {
    "element_name": "MyCharacter",
    "element_description": "A young male character with short hair, wearing a white T-shirt",
    "reference_type": "image_refer",
    "element_image_list": {
      "frontal_image": "https://example.com/front.jpg",
      "refer_images": [
        {"image_url": "https://example.com/side.jpg"},
        {"image_url": "https://example.com/back.jpg"}
      ]
    }
  }
}

Request Example (Video Reference)

{
  "model": "kling-custom-element",
  "model_params": {
    "element_name": "CharacterA",
    "element_description": "Middle-aged female with long hair, wearing a red dress",
    "reference_type": "video_refer",
    "element_video_list": {
      "video_url": "https://example.com/reference.mp4"
    },
    "element_voice_id": "829826751244537879"
  }
}

Response Example

{
  "created": 1739500000,
  "id": "task-video-xxxxxxxx",
  "model": "kling-custom-element",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "estimated_time": 600,
    "can_cancel": true
  },
  "usage": {
    "credits_reserved": 1,
    "billing_rule": "per_call"
  }
}