Kling AI · video model · Released Dec 3, 2025Kling v2.6
Kling v2.6 is a video model from Kling AI, released Dec 3, 2025. It handles text to video and image to video.
- Arena score
- 1,294#26 of 48 · image to video
- Starting price
- —Not published
- Longest clip
- —Not published
- Resolution
- —No audio track
How it rates and what it costs
- Text to video arena
- 1,216 ±7#29 of 48 · 73,362 votes
- Image to video arena
- 1,294 ±8#26 of 48 · 202,113 votes
Arena scores come from blind, side-by-side human votes on the same prompts (higher is better; ± is the 95% range). Boards updated Sep 22, 2026.
The details
- Lab
- Kling AI
- Type
- Video model
- Released
- Dec 3, 2025
- Inputs
- Text prompts, Reference images
- Output
- Video
- Can do
- Text to video, Image to video
- Weights
- Proprietary
- Availability
- 1 API host
More video models from Kling AI
About Kling v2.6
How good is Kling v2.6?
In blind side-by-side votes, Kling v2.6 scores 1,216 for text to video (#29 of 48) and 1,294 for image to video (#26 of 48). Higher is better; scores within about 16 points of each other are effectively tied.
Who makes Kling v2.6?
Kling v2.6 is a video model from Kling AI, released Dec 3, 2025.
What can Kling v2.6 do?
Kling v2.6 accepts text prompts and reference images and produces video. In practice: text to video and image to video.
Is Kling v2.6 open source?
No. Kling v2.6 is proprietary; you use it through an API or partner apps.
Where can I use Kling v2.6?
It is listed by 1 API host we track.
What are the alternatives to Kling v2.6?
The closest video models from other labs, by release date, are Wan v2.6 (Alibaba (Qwen), Dec 16, 2025), Seedance v1.5 Pro (ByteDance Seed, Dec 16, 2025), Veo 3.1 (Google, Oct 15, 2025) and Grok Imagine Video (xAI, Jan 28, 2026).