Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front. See what's new

Kuaishou: Kling VIDEO 3.0 Standard

Kling VIDEO 3.0 Standard generates synchronized video and audio from text and images with a balance of quality, speed, and cost. It supports reference-based generation and prompt-driven edits while maintaining temporal stability and clear motion. Native audio output includes dialogue and ambient sound that aligns with the visual content.
Compare models
kling-video-3-0-standard
AvailableKuaishouVideoAsync
Price
From $0.084
Modalities
Video

About Kling VIDEO 3.0 Standard

Kling VIDEO 3.0 Standard is the entry tier of Kling's VIDEO 3.0 line, producing 720p clips with synchronized audio from a text prompt or a starting image. Kling's 3.0 generation adds multi-shot storytelling and native dialogue, ambient sound, and effects. Standard is the choice when you want that feature set at a balance of quality, speed, and cost, and do not need Pro's 1080p.

Where it works well

  • Audio comes out with the video: dialogue, ambient sound, and effects aligned to the picture, with no separate sound step.
  • It takes both text-to-video and image-to-video, so a still can be animated or a scene written from scratch.
  • Kling's 3.0 series adds multi-shot storytelling, where one prompt can describe several camera setups.
  • Reference-based generation and prompt-driven edits keep characters and objects coherent between frames.

When to choose another model

  • Output is 720p; for 1080p or 4K delivery use the Pro or 4K variants.
  • Fine motion and detail trail Pro, so close-ups of faces and hands are where the difference shows first.
  • Clip length is capped at what the 3.0 series allows per generation, so longer scenes must be assembled from several clips.

Getting started

  1. Create API key

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

  2. Send your first request

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

    Image to videoMotion controlStart and end frames to videoText 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 '{
      "duration": 5,
      "operation": "image-to-video",
      "model": "kling-video-3-0-standard",
      "prompt": "Cinematic sunrise over a calm lake with gentle camera motion.",
      "image_url": "https://example.com/image.jpg"
    }'

Parameters

Image to video

ParameterValues and limitsDefaultNotes
duration≥ 3, ≤ 155Use an integer. Use multiples of 1.
end_imageNot providedNot providedLast frame: a public image URL or a data URL. Send it with a first frame (image, image_url or start_image).
imageNot providedNot providedFirst frame (image, image_url or start_image): a public image URL or a data URL. Add end_image for a last frame.
image_urlNot providedNot providedFirst frame (image, image_url or start_image): a public image URL or a data URL. Add end_image for a last frame.
n11Use an integer.
negative_promptNot providedNot providedMinimum length: 2 characters. Maximum length: 2500 characters.
operationRequiredNot providedNot providedNot provided
output_formatmov, mp4, webmmp4Not provided
promptNot providedNot providedMinimum length: 2 characters. Maximum length: 2500 characters.
seconds≥ 3, ≤ 155Use an integer. Use multiples of 1.
start_imageNot providedNot providedFirst frame (image, image_url or start_image): a public image URL or a data URL. Add end_image for a last frame.

Motion control

ParameterValues and limitsDefaultNotes
imageInputs: ≥ 1, ≤ 1Not providedCharacter image: a public image URL or a data URL. image, image_url and reference_images (one item) are aliases; send one.
image_urlInputs: ≥ 1, ≤ 1Not providedCharacter image: a public image URL or a data URL. image, image_url and reference_images (one item) are aliases; send one.
n11Use an integer.
operationRequiredNot providedNot providedNot provided
output_formatmov, mp4, webmmp4Not provided
promptNot providedNot providedMinimum length: 2 characters. Maximum length: 2500 characters.
reference_imagesInputs: ≥ 1, ≤ 1Not providedCharacter image: a public image URL or a data URL. image, image_url and reference_images (one item) are aliases; send one.
video_urlNot providedNot providedMotion video: a public video URL. The output follows its motion and length. video_urls takes one URL and is an alias. Send operation: motion-control; otherwise the request is read as video-to-video.
video_urlsInputs: ≥ 1, ≤ 1Not providedMotion video: a public video URL. The output follows its motion and length. video_urls takes one URL and is an alias. Send operation: motion-control; otherwise the request is read as video-to-video.

Start and end frames to video

ParameterValues and limitsDefaultNotes
duration≥ 3, ≤ 155Use an integer. Use multiples of 1.
end_imageInputs: ≥ 1, ≤ 1Not providedLast frame: a public image URL or a data URL. A request with end_image is start-end-to-video.
imageInputs: ≥ 1, ≤ 1Not providedFirst frame: a public image URL or a data URL. image, image_url and start_image are aliases; send one.
image_urlInputs: ≥ 1, ≤ 1Not providedFirst frame: a public image URL or a data URL. image, image_url and start_image are aliases; send one.
n11Use an integer.
negative_promptNot providedNot providedMinimum length: 2 characters. Maximum length: 2500 characters.
operationRequiredNot providedNot providedNot provided
output_formatmov, mp4, webmmp4Not provided
promptNot providedNot providedMinimum length: 2 characters. Maximum length: 2500 characters.
seconds≥ 3, ≤ 155Use an integer. Use multiples of 1.
start_imageInputs: ≥ 1, ≤ 1Not providedFirst frame: a public image URL or a data URL. image, image_url and start_image are aliases; send one.

Text to video

ParameterValues and limitsDefaultNotes
duration≥ 3, ≤ 155Use an integer. Use multiples of 1.
height720, 960, 1280720Use an integer. Use a listed width and height pair: 1280x720 (720p, 16:9), 960x960 (720p, 1:1), 720x1280 (720p, 9:16).
n11Use an integer.
negative_promptNot providedNot providedMinimum length: 2 characters. Maximum length: 2500 characters.
operationRequiredNot providedNot providedNot provided
output_formatmov, mp4, webmmp4Not provided
promptNot providedNot providedMinimum length: 2 characters. Maximum length: 2500 characters.
seconds≥ 3, ≤ 155Use an integer. Use multiples of 1.
width720, 960, 12801280Use an integer. Use a listed width and height pair: 1280x720 (720p, 16:9), 960x960 (720p, 1:1), 720x1280 (720p, 9:16).

Fields outside this contract are rejected.

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.

Text to video · No video input · Audio off

per second
Official price
$0.084
Verified price
—
Discount
—

Text to video · No video input · Audio on

per second
Official price
$0.126
Verified price
—
Discount
—

Text to video · Includes video input · Audio off

per second
Official price
$0.126
Verified price
—
Discount
—

Image to video · No video input · Audio off

per second
Official price
$0.084
Verified price
—
Discount
—

Image to video · No video input · Audio on

per second
Official price
$0.126
Verified price
—
Discount
—

Image to video · Includes video input · Audio off

per second
Official price
$0.126
Verified price
—
Discount
—

Start and end frames to video · No video input

per second
Official price
$0.084
Verified price
—
Discount
—

Start and end frames to video · Includes video input

per second
Official price
$0.126
Verified price
—
Discount
—

Motion control · No video input

per second
Official price
$0.084
Verified price
—
Discount
—

Motion control · Includes video input

per second
Official price
$0.126
Verified price
—
Discount
—

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
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 VIDEO 3.0 Standard in Console with a prompt ready to edit or send.

Help me create with kling-video-3-0-standard using image-to-video at /v1/videos/generations. Show the result, status, and cost.

Use cases

Best for
  • Text to Video
  • Social clips with sound

    Make short vertical or horizontal videos where speech and ambience are generated together, then post them with little editing.

  • Animating product stills

    Turn a product image into a moving shot with a camera push, and judge the framing before paying for a higher tier.

  • Storyboard previews

    Test a multi-shot sequence at 720p to approve pacing and camera angles, then re-run the approved prompt on Pro.

  • Dialogue scenes

    Write a short exchange between two characters and let the model voice it, for pitch videos and concept tests.

Prompt examples

Shot 1: wide of a rainy street at dusk. Shot 2: close-up of a courier checking her phone. She says, 'Almost there.'

Animate this product photo: slow dolly in on the watch, soft reflections, quiet room tone.

Two friends laugh at a cafe table, handheld camera, background chatter, warm afternoon light.

FAQ

What is the difference between Kling VIDEO 3.0 Standard and Pro?

Resolution and fidelity. Kling's 3.0 line runs Standard at 720p and Pro at 1080p, and Pro is positioned for higher quality and finer motion control. Both generate synchronized audio from text or images. Use Standard to iterate and Pro for final output.

Does Standard generate sound?

Yes. Kling's 3.0 models produce native audio, including dialogue, ambient sound, and effects aligned to the visuals. You do not need a separate text-to-speech or sound-effects step for a first cut.

Can I start from an image?

Yes. It takes both text-to-video and image-to-video requests. Supply a still as the first frame or reference, and describe the motion and camera movement you want in the prompt.

Does it support multi-shot prompts?

Kling's 3.0 series supports multi-shot storytelling, so a single prompt can describe several shots with different camera angles. Keep each shot's description short and concrete; contradictory instructions across shots are the usual cause of drift.

How much does Kling VIDEO 3.0 Standard cost?

On TokenLab, Kling VIDEO 3.0 Standard costs $0.084-$0.126 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 VIDEO 3.0 Standard use?

Use https://api.tokenlab.sh/v1/videos/generations for Kling VIDEO 3.0 Standard. The request example below shows the matching code shape.

Which operations does Kling VIDEO 3.0 Standard support?

Kling VIDEO 3.0 Standard supports Image to video, Motion control, Start and end frames to video, Text to video. Select an operation above to see its endpoint and request example.

Compare Kling VIDEO 3.0 Standard

Guides that use Kling VIDEO 3.0 Standard

Sources

Reviewed Oct 2, 2026

More from Kling

Related models