Skip to main content

Vendor · Language models · Image models · Video models

Kuaishou Models: All 14 Models Compared

Kuaishou has 14 models in the directory: 2 language models, 3 image models and 9 video models.

Models1411 of them since January 2026
Planfrom €9.37Kling AI Standard, per month incl. VAT, free plan available
Most popular37KAT-Coder-Pro V2.5, popularity index out of 100

Summary

In the directory: 2 language models, 3 image models and 9 video models.

All 14 models from Kuaishou

Every model there ever was. Models with a profile lead to every benchmark, price and source.

14 models
Model type

Language models · 2

KAT-Coder-Air V2.5Jul 10, 2026Activen/an/an/a256K24
KAT-Coder-Pro V2.5Jul 10, 2026Activen/an/an/a256K37

Image models · 3

Kling Image 3.0Feb 5, 2026Activen/an/a
Kling Image 3.0 OmniFeb 5, 2026Activen/an/a
Kling Image O1n/aActiven/an/a

Video models · 9

Kling 4.0Oct 15, 2026Activen/abelow 1
Kling 4.0 FlashSep 28, 2026Activen/abelow 1
Kling 3.0 TurboJun 17, 2026Activen/an/a
Kling 3.0 OmniFeb 5, 2026Activen/an/a
Kling 3.0 Standard APIFeb 5, 2026Activen/an/a
Kling 3.0 ProFebruary 2026Active$10.08 per minute18
Kling 2.6 ProJanuary 2026Active$8.40 per minute29
Kling Video O1Dec 15, 2025Activen/an/a
Kling 2.5 Turbon/aActiven/an/a

The current Kuaishou models explained

Kling 4.0

Video model · Oct 15, 2026

Kling 4.0 is an announced video model with stronger motion, multimodal references, and integrated audio handling. Its description lists 3 to 30 seconds, up to ten keyframes, 4K, and generated stereo audio with lip synchronization.

Kling 4.0 Flash

Video model · Sep 28, 2026

Kling 4.0 Flash is the faster variant of Kling 4.0, generating up to 20 seconds of 720p video in 8-bit SDR. It supports text, image, and Omni references, but not first/last frames or multiple keyframes. Access for Ultra Yearly subscribers began on September 28, 2026.

KAT-Coder-Air V2.5

Language model · Jul 10, 2026

KAT-Coder-Air V2.5 is the fast API variant in a family trained around executable environments and verifiable agent tasks. The technical report uses AutoBuilder and KwaiClawEnv to represent that focus on real repository steps. Air offers a 256K context, up to 80K output tokens, and tool calling; public StreamLake documentation gives neither a parameter count nor a weight release.

KAT-Coder-Pro V2.5

Language model · Jul 10, 2026

KAT-Coder-Pro V2.5 is trained for executable repository tasks rather than isolated code snippets. Its technical report names fail-to-pass and pass-to-pass verification, tool-use trajectories, and multi-teacher post-training. Publicly, Kuaishou and KwaiPilot offer it as a proprietary endpoint rather than a downloadable checkpoint.

Kling 3.0 Turbo

Video model · Jun 17, 2026

Kling 3.0 Turbo is a video model from Kuaishou. Kling 3.0 Turbo supports text-to-video and image-to-video.

Kling 3.0 Omni

Video model · Feb 5, 2026

Kling 3.0 Omni is a video model from Kuaishou. Kling 3.0 Omni accepts text, image, and video inputs. Kling’s native model map also describes audio output and storyboards.

Kling 3.0 Standard API

Video model · Feb 5, 2026

Kling 3.0 Standard API is a video model from Kuaishou. This row represents the separately selectable standard API route; it does not claim a separately released base model or weight checkpoint.

Kling Image 3.0

Image model · Feb 5, 2026

Kling Image 3.0 is an image model from Kuaishou. Kuaishou announced Kling Image 3.0 on February 5, 2026.

Kling Image 3.0 Omni

Image model · Feb 5, 2026

Kling Image 3.0 Omni is an image model from Kuaishou. Its hosted TokenHub identifier is kling-image-v3-omni; the table lists it separately for T2I, image references, and image series.

Kling 3.0 Pro

Video model · February 2026

New in Kling 3.0 Pro are native audio, multi-shot storyboards, reference video, and in-video editing alongside text-to-video and image-to-video. Kuaishou describes consistent characters from image or video references, with up to 4K and 15 seconds.

Kling 2.6 Pro

Video model · January 2026

Kling 2.6 Pro was Kuaishou’s high-resolution Kling generation for API and web access. The proprietary model generated up to 1080p and included native audio in the clip.

Kling Video O1

Video model · Dec 15, 2025

Kling Video O1 is a video model from Kuaishou. Kling Video O1 is a multimodal model for text-to-video, image and element references, first and last frames, reference video, video extension, and editing.

2 more current models are in the model list above.

Where does Kuaishou stand?

Models among the best 20 in the overall index

Anthropic5 models, 4 of them among the best ten
OpenAI5 models, 2 of them among the best ten
Google4 models, 2 of them among the best ten
Meta3 models, 2 of them among the best ten
DeepSeek1 models, 0 of them among the best ten
Moonshot AI1 models, 0 of them among the best ten
xAI1 models, 0 of them among the best ten
Kuaishou0 models, 0 of them among the best ten

Vendors compared

VendorModelsModel typesBest language modelTop 10Open weightsNew in 2026
Anthropic3333 language modelsClaude Opus 5.5 (Rank 1 to 3)4013
OpenAI6546 language models, 6 image models, 2 video models, 9 audio models, 2 specialist modelsGPT-6 Astra (Rank 4 to 8)2427
Google6743 language models, 5 image models, 6 video models, 11 audio models, 2 specialist modelsGemini 4 Carbon (Rank 1 to 5)21926
Meta3229 language models, 1 image model, 1 video model, 1 specialist modelMuse Wonder Full (Rank 6 to 9)2267
DeepSeek2523 language models, 2 image modelsDeepSeek V4.1 Flash 1017 (Rank 13 to 20)0259
Moonshot AI1212 language modelsKimi K3.1 Pro (Rank 10 to 13)0107
xAI1812 language models, 3 image models, 3 video modelsGrok 4.7 (Rank 18 to 24)0112
Kuaishou142 language models, 3 image models, 9 video modelsnot ranked yet0011

Gaps

No audio models in the directory
No language model with a rank in the overall index yet

Every Kuaishou model over time

By release date. Grey: retired models.

20251 model

DecKling Video O1Video model

202611 models

JanKling 2.6 ProVideo model
FebKling 3.0 ProVideo model
FebKling 3.0 OmniVideo model
FebKling Image 3.0Image model
FebKling Image 3.0 OmniImage model
JunKling 3.0 TurboVideo model
SepKling 4.0 FlashVideo model
OctKling 4.0Video model

No documented date2 models

Kling 2.5 TurboVideo model
Kling Image O1Image model

Releases in the last twelve months

1Dec 25
1Jan 26
5Feb 26
0Mar 26
0Apr 26
0May 26
1Jun 26
2Jul 26
0Aug 26
1Sep 26
1Oct 26
0Nov 26

11 releases since January 2026, by release date.

API prices

Current modelPrice
Kling 3.0 Pro$10.08 per minute
Kling 2.6 Pro$8.40 per minute

Plans from Kuaishou

Monthly prices in Germany incl. VAT; “≈” is converted from US dollars. The vendor's models are often also part of other providers' plans, see the AI subscription comparison.

PlanPer monthNote
Kling AI Basicfree
Kling AI Standard≈ €9.37with credits
Kling AI Pro≈ €34.68with credits
Kling AI Team≈ €84.15per seat, Team, with credits
Kling AI Premier≈ €86.24with credits
Kling AI Ultra≈ €170.42with credits

Frequently asked questions about Kuaishou

What Kuaishou models are there?

The directory lists 14 Kuaishou models: 2 language models, 3 image models and 9 video models. It counts every model Kuaishou ever released, including retired ones. 14 are currently available, the newest being Kling 4.0, Kling 4.0 Flash and KAT-Coder-Air V2.5.

What is the latest Kuaishou model?

Kling 4.0, released on Oct 15, 2026. The timeline below shows every release by date.

Can I use Kuaishou models for free?

Yes, with the Kling AI Basic plan. The cheapest paid plan is Kling AI Standard at €9.37 per month incl. VAT.

How large is the context window of the Kuaishou models?

Up to 256,000 tokens (≈ 380 A4 pages), which 2 of the current models reach, including KAT-Coder-Air V2.5. Every model's value is in the model list.