MODEL IDklingai:kling-video@o3-standard

live

Kling VIDEO 3.0 Omni Standard

by Kling AIFebruary 5, 2026

Kling VIDEO 3.0 Omni Standard is a cost-efficient version of the 3.0 Omni generation that produces HD video from text or images with native audio. It balances quality with speed and price, and it supports reference-based generation plus prompt-based video edits that preserve temporal stability across the clip.

API Options

Platform-level options for task execution and delivery.

taskType stringrequiredvalue: videoInference: Identifier for the type of task being performed

taskUUID stringrequiredUUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType stringdefault: URL: Video output type.
Allowed values1 value

outputFormat stringdefault: MP4

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

`MP4`: Widely supported video container (H.264), recommended for general use.
`WEBM`: Optimized for web delivery.
`MOV`: QuickTime format, common in professional workflows (Apple ecosystem).

Allowed values3 values

outputQuality integermin: 20max: 99default: 95: Compression quality of the output. Higher values preserve quality but increase file size.

webhookURL stringURI

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Learn more1 resource

Webhooks
PLATFORM

deliveryMethod stringdefault: async

Determines how the API delivers task results.

Allowed values1 value

: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. Required for long-running tasks like video generation.

Learn more1 resource

Task Polling
PLATFORM

uploadEndpoint stringURI

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

Common use cases:

Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
CDN integration: Upload to content delivery networks for immediate distribution.

// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg

The content data will be sent as the request body to the specified URL when generation is complete.

safety object

Content safety checking configuration for video generation.

Properties2 properties

safety » checkContent checkContent booleandefault: false: Enable or disable content safety checking.

safety » mode mode stringdefault: none

Safety checking mode for video generation.

Allowed values3 values

: Disables checking.
: Checks key frames.
: Checks all frames.

ttl integermin: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost booleandefault: false: Include task cost in the response.

Inputs

Input resources for the task (images, audio, etc). These must be nested inside the inputs object.

inputs » referenceImages referenceImages array of stringsmin items: 1max items: 7: List of reference images (UUID, URL, Data URI, or Base64).

inputs » frameImages frameImages array of strings or objectsmin items: 1max items: 2

List of frame-specific image inputs. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object with an image and a target position in the video.

Format 1: string[]

string: Image input (UUID, URL, Data URI, or Base64).

Format 2: object[]2 properties

inputs » frameImages » image image stringrequired: Image input (UUID, URL, Data URI, or Base64).

inputs » frameImages » frame frame object

Target frame position for the image. Supports first and last frame.

Allowed values4 values

: First frame of the video.
: Last frame of the video.
: Frame index 0 (first frame).
: Frame index -1 (last frame).

inputs » video video string: Video input (UUID or URL). Source video for prompt-based editing. Dimensions and duration match the input video.

inputs » referenceVideos referenceVideos array of stringsitems: 1: List of reference videos (UUID, URL).

inputs » elements elements array of objectsmin items: 1max items: 3

Reusable asset elements for video generation. Each element can contain images, videos, or voices that are saved for reuse. Reference elements in the prompt using <<<element_1>>>, <<<element_2>>>, etc. in order.

Properties7 properties

inputs » elements » id id stringrequired: Unique identifier for this element. Use to create a new element or reference a previously created one.

inputs » elements » description description string: Description of the element.

inputs » elements » frontalImage frontalImage string: Frontal reference image for the element. Required when using image-based elements.

inputs » elements » images images array of stringsmin items: 1max items: 3: Reference images for the element. Up to 3 images. Requires frontalImage.

inputs » elements » videos videos array of stringsitems: 1: Reference video for the element. Cannot be combined with images or voices.

inputs » elements » voices voices array of stringsitems: 1: Voice audio for the element. Can only be combined with images, not videos.

inputs » elements » tags tags array of stringsmin items: 1: Classification tags for the element.

Core Parameters

Primary parameters that define the task output.

numberResults integermin: 1max: 4default: 1: Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

model stringrequiredvalue: klingai:kling-video@o3-standard: Identifier of the model to use for generation.

positivePrompt stringmin: 2max: 2500: Text prompt describing elements to include in the generated output.

width integerrequired*paired with height: Width of the generated media in pixels.

height integerrequired*paired with width: Height of the generated media in pixels.

resolution string: Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.
Allowed values1 value

duration integermin: 3max: 15step: 1default: 5: Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

Provider Settings

Parameters specific to this model provider. These must be nested inside the providerSettings.klingai object.

providerSettings » klingai » keepOriginalSound keepOriginalSound boolean: Maintain the original sound from the reference video.

providerSettings » klingai » multiPrompt multiPrompt array of objectsmax items: 6

Sequential prompt segments for multi-shot generation. The sum of all segment durations must equal the root-level duration.

Properties2 properties

providerSettings » klingai » multiPrompt » prompt prompt stringrequiredmin: 2max: 2500: Text prompt describing the content for this segment.

providerSettings » klingai » multiPrompt » duration duration integerrequiredmin: 1: Duration in seconds for this segment.

providerSettings » klingai » sound sound boolean: Enable native audio generation.

Notes

Kling 3.0 Omni Standard supports multiple generation modes:

Text-to-Video: Provide a prompt with width, height, and duration.
Image-to-Video: Provide frame images via inputs.frameImages (up to 2, first/last). Dimensions are inherited from the image and cannot be set manually.
Video Editing: Provide a source video via inputs.video for prompt-based editing. Dimensions and duration match the input video.
Motion Control: Provide a reference video via inputs.referenceVideos (max 1). Can be combined with inputs.referenceImages for additional visual guidance.
Reference-to-Video: Provide reference images via inputs.referenceImages to guide the visual style. Can be combined with other modes.

Elements allows you to include reusable assets like characters, objects, or voices in your video by referencing them in the prompt (e.g. <<<element_1>>>). Elements can be used with Text-to-Video, Image-to-Video, Motion Control, and Reference-to-Video modes, but is not available when using Video Editing (inputs.video).

The combined total of reference images and elements must not exceed 7 items. When inputs.referenceVideos is provided, this limit drops to 4 items.

Parameter Dependencies

Dimensions

The following dimension combinations are supported:

Configuration	Dimensions
`720p (16:9)`	`1280x720`
`960p (1:1)`	`960x960`
`720p (9:16)`	`720x1280`

Pricing

720p · 1s · (no input + no audio)$0.084

720p · 1s · (video input + no audio)$0.126

720p · 1s · (audio + no input)$0.112