Kuaishou: Kling Omni Video

Kling Omni Video brings text, image references, and existing clips into a video workflow. It is suited to projects that move between generating a new shot and revising footage using a shared set of visual references.

Compare models

kling-omni-video

AvailableKuaishouVideoAsyncNew

Price: From $0.084
Released: Feb 6, 2026
Modalities: Video

About Kling Omni Video

Kling Omni Video is Kuaishou's all-in-one video model in the Kling Omni family. It takes text, image references and existing clips, and covers text-to-video, image-to-video, reference-to-video and video-to-video in one model. It suits projects that switch between generating a new shot and revising footage while keeping a shared set of visual references.

Where it works well

Four operations in one model: text-to-video, image-to-video, reference-to-video and video-to-video.
Video-to-video lets you revise footage you already have instead of regenerating the whole shot.
Reference-to-video keeps a subject or style consistent across shots from supplied images.
Kuaishou describes Video 3.0 Omni as adding multi-shot storyboards with per-shot duration and camera movement.

When to choose another model

It has no start/end-frame mode; for pinned first and last frames, use Kling 3.0 or 2.5 Turbo Pro.
Its breadth means more inputs to prepare; a plain text prompt is quicker on a simpler model.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Image to videoReference to videoText to videoVideo to videoTokenLab endpoint

POST/v1/videos/generations

curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "operation": "text-to-video",
  "output_audio": false,
  "model": "kling-omni-video",
  "prompt": "Cinematic sunrise over a calm lake with gentle camera motion."
}'

Parameters

Image to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`duration`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`image_url`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`image_urls`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`operation`	Not provided	Not provided	Not provided
`output_audio`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`video_url`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`video_urls`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.

Reference to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`duration`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`image_url`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`image_urls`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`operation`	Not provided	Not provided	Not provided
`output_audio`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`video_url`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`video_urls`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.

Text to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`duration`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`image_url`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`image_urls`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`operation`	Not provided	Not provided	Not provided
`output_audio`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`video_url`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`video_urls`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.

Video to video

Parameter	Values and limits	Default	Notes
`aspect_ratio`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`duration`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`image_url`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`image_urls`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`operation`	Not provided	Not provided	Not provided
`output_audio`	false	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`video_url`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.
`video_urls`	Not provided	Not provided	The current public contract does not specify an input count limit for this field. Do not infer a count from the example request.

Kling VIDEO 3.0 Omni supports multimodal reference input, optional native audio without video input, and up to 15 seconds.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

720p · No video input · Audio off

per second

Official price: $0.084
Verified price: —
Discount: —

1080p · No video input · Audio off

per second

Official price: $0.112
Verified price: —
Discount: —

720p · No video input · Audio on

per second

Official price: $0.112
Verified price: —
Discount: —

1080p · No video input · Audio on

per second

Official price: $0.14
Verified price: —
Discount: —

720p · Includes video input · Audio off

per second

Official price: $0.126
Verified price: —
Discount: —

1080p · Includes video input · Audio off

per second

Official price: $0.168
Verified price: —
Discount: —

	Official priceper second	Verified priceper second	Discount
720p · No video input · Audio off	$0.084	—	—
1080p · No video input · Audio off	$0.112	—	—
720p · No video input · Audio on	$0.112	—	—
1080p · No video input · Audio on	$0.14	—	—
720p · Includes video input · Audio off	$0.126	—	—
1080p · Includes video input · Audio off	$0.168	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 6:31 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Kling Omni Video in Console with a prompt ready to edit or send.

Help me create with kling-omni-video using text-to-video at /v1/videos/generations. Show the result, status, and cost.

Use cases

Best for

Text to Video

Consistent character shots
Supply reference images of a character and generate several shots in which they look the same.
Footage revision
Feed an existing clip through video-to-video to change the style or a detail without reshooting.
Storyboard to shots
Describe each shot of a sequence with its camera movement and produce a connected set of clips.

Prompt examples

Using the two reference images of the courier, a tracking shot following her through a crowded market at golden hour.

Take this clip of a street scene and restyle it as a hand-painted animation, keeping the movement.

Text to video: a paper boat drifting down a rain gutter, low camera, shallow depth of field.

FAQ

Which operations does Kling Omni Video support?

Text-to-video, image-to-video, reference-to-video and video-to-video. That makes it the Kling model to use when your project mixes new generation with changes to clips you already have.

What does reference-to-video mean?

Generating a clip guided by supplied reference images, so a subject or look stays consistent. It is useful for series where the same character appears in many shots.

Does it support start and end frames?

No. Kling 3.0 and Kling 2.5 Turbo Pro offer start-end-to-video if you need to fix both ends of a shot. Choose those models when the shot must land on a specific final image.

How long can a clip be?

Kuaishou's 3.0 announcement mentions clips up to 15 seconds in the Video 3.0 line. Set the length you need in the generation settings, and keep early tests short.

How much does Kling Omni Video cost?

On TokenLab, Kling Omni Video costs $0.084-$0.168 per second. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Kling Omni Video use?

Use https://api.tokenlab.sh/v1/videos/generations for Kling Omni Video. The request example below shows the matching code shape.

Which operations does Kling Omni Video support?

Kling Omni Video supports Image to video, Reference to video, Text to video, Video to video. Select an operation above to see its endpoint and request example.