Kling Videos

The Kling video series uses the OpenAI-compatible /v1/videos interface and supports multiple generation modes, including text-to-video, image-to-video, motion control, digital avatars, and lip sync.

OpenAI Format

Use POST /v1/videos to submit and GET /v1/videos/{task_id} to query.

Video Generation

POST /v1/videos, submit a Kling video task.

Task Status Query

GET /v1/videos/{task_id}, query task status and results.

Supported Models

Model	Description	Duration Rules
`Kling-3.0-Omni`	Kling 3.0 all-in-one edition	5-15 seconds
`Kling-2.6`	Kling 2.6 version	5-10 seconds
`Kling-2.5`	Kling 2.5 version	5-10 seconds

Scene Types

Scene Type	Description
`motion_control`	Motion control
`avatar_i2v`	Digital avatar generation
`lip_sync`	Lip sync
`template_effect`	Template effects

Parameter Description

Basic Parameters

Field	Type	Description
`model`	string	Model name
`prompt`	string	Prompt
`seconds`	string	Video duration
`size`	string	Video size
`image`	string	Reference image

metadata Parameters

Field	Type	Description
`output_config`	object	Output configuration
`scene_type`	string	Scene type
`motion_level`	string	Motion level
`offpeak`	boolean	Whether off-peak billing is enabled
`last_frame_url`	string	The last frame in a start/end frame pair
`video_url`	string	Reference video URL

output_config Parameters

Field	Type	Description
`resolution`	string	Resolution
`aspect_ratio`	string	Aspect ratio
`duration`	integer	Duration
`audio_generation`	string	Audio generation

Parameter Constraints

Field	Allowed Values	Description
`aspect_ratio`	`16:9`, `9:16`, `1:1`	Video aspect ratio
`resolution`	`720P`, `1080P`	Resolution specification
`seconds`	`5`, `10`, `15`	Video duration (seconds)
`motion_level`	`std`, `pro`	Motion level (used for billing tiers in motion control)

Featured Capabilities

Feature	Description
Motion control	`scene_type: motion_control`, precisely control video motion
Digital avatar	`scene_type: avatar_i2v`, generate digital avatar videos
Lip sync	`scene_type: lip_sync`, synchronized lip syncing with audio and video
Off-peak billing	`offpeak: true`, generate during off-peak hours for lower cost
Start/end frames	`last_frame_url`, specify the end frame to control the video ending

Overview

Text Models

Image Models

Video Models

Uploads

Tasks

Account

Kling Video Overview

Kling Videos

OpenAI Format

Video Generation

Task Status Query

Supported Models

Scene Types

Parameter Description

Basic Parameters

metadata Parameters

output_config Parameters

Parameter Constraints

Featured Capabilities

​Kling Videos

​OpenAI Format

Video Generation

Task Status Query

​Supported Models

​Scene Types

​Parameter Description

​Basic Parameters

​metadata Parameters

​output_config Parameters

​Parameter Constraints

​Featured Capabilities

​Related Pages

Kling Videos

OpenAI Format

Supported Models

Scene Types

Parameter Description

Basic Parameters

metadata Parameters

output_config Parameters

Parameter Constraints

Featured Capabilities

Related Pages