Post-Cutoff
Search For AI agents

KuaishouKling 3 familyCurrentVideo generationReleased Feb 2026

Kling 3.0 (VIDEO 3.0 / 3.0 Omni)

Kuaishou’s flagship video model with native audio and multi-shot generation. Official API is async (submit task, poll task id).

Model idfal-ai/kling-video/v3/standard/text-to-video

Price$0.084 standard per second

Checked25 October 2026

Where it stands

15newer video generation models since its release

The 5 newest are listed. All video generation models

After it from Kuaishou
Kling 4.0 (and 4.0 Flash)15 Oct 2026
Weights
Closed weights; access is hosted only.

How to call it

5 ways to use Kling 3.0 (VIDEO 3.0 / 3.0 Omni), with the model id each provider expects.

Providers, model ids, endpoints and docs for Kling 3.0 (VIDEO 3.0 / 3.0 Omni)
ProviderModel idEndpointDocs
Kling AI API https://api-singapore.klingai.com kling.ai
fal.ai fal-ai/kling-video/v3/standard/text-to-video fal.ai
fal.ai (Pro image-to-video, generate_audio parameter) fal-ai/kling-video/v3/pro/image-to-video fal.ai
fal.ai (3.0 Omni, Pro image-to-video) fal-ai/kling-video/o3/pro/image-to-video fal.ai
Web app kling.ai

Pricing

Prices for Kling 3.0 (VIDEO 3.0 / 3.0 Omni)
Standard per second$0.084
Standard per second audio$0.126
Pro per second$0.112
Pro per second audio$0.168

As published: “USD per second of output on fal (fal-ai/kling-video/v3/standard and /v3/pro, audio off / audio on, read 2026-10-25). Artificial Analysis lists Kling 3.0 1080p (Pro) at $10.08 per minute and 3.0 Omni 1080p (Pro) at $8.40 per minute on Kling’s own API”.

Source: fal.ai, checked 25 October 2026.

Specs

Input
Text, images and video
Output
Video and audio
Context window
Not published
Max output
Not published
Open weights
No
Licence
Proprietary
Released
February 2026
Status
Current
Type
Video generation

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Multi-shot storyboards

    Generates multi-shot narrative sequences in one job, with storyboard control over shots.

    Source: kling.ai

  • Native multilingual audio

    Native audio (dialogue/SFX) generated with the video, multilingual; clips up to 15 s.

    Source: kling.ai

  • Unified Omni model with element consistency

    VIDEO 3.0 Omni (successor of O1) unifies generation and editing with stronger element/character consistency; IMAGE 3.0 / 3.0 Omni siblings.

    Source: kling.ai

Notes

Released early Feb 2026 (official guide says Feb 6; other sources Feb 7). Artificial Analysis (read 2026-10-25): text-to-video 3.0 Omni Pro #17 (1020), 3.0 Pro #18 (1000, the board’s anchor); image-to-video 3.0 Omni Pro #17 (1004), 3.0 Pro #18 (1000). Successor: kling-4-0.

# via fal.ai
curl -X POST https://fal.run/fal-ai/kling-video/v3/standard/text-to-video -H "Authorization: Key $FAL_KEY" \
  -H "Content-Type: application/json" -d '{"prompt":"a samurai walks through falling snow, cinematic","duration":"5"}'

Sources: https://kling.ai/quickstart/klingai-video-3-model-user-guide , https://kling.ai/document-api/quickStart/productIntroduction/overview , https://fal.ai/models/fal-ai/kling-video/v3/standard/text-to-video/api

Not yet checked against an official source: Official API model_name strings not verified (docs are JS-rendered); fal ids verified: kling-video/v3/{standard,pro}/{text,image}-to-video, plus turbo/4K variants, and the 3.0 Omni ids kling-video/o3/{standard,pro}/image-to-video.