Latest models
- Kling 3.0 (February 5, 2026) Current
Video, Image and Omni models with clips up to 15 seconds and native multilingual audio. Kling 4.0 Flash opened to limited early access on September 28, 2026, with a wider 4.0 rollout planned for October. Source: Kuaishou and Kling ↗
Checked October 7, 2026. See the full AI model tracker.
What we like
- Clips up to 15 seconds in Kling 3.0
- Native audio, including speech in several languages
- Text, image, reference and in-video editing in one model
Watch out for
- Newer versions roll out to subscribers and early-access users first
- Credit use can add up when you iterate
- Kling 4.0 is not generally available yet; check the site
Kling is a family of AI image and video models from Kuaishou. Kuaishou announced Kling AI 3.0 on February 5, 2026, including Video 3.0, Video 3.0 Omni, Image 3.0 and Image 3.0 Omni.
What is current
Kling 3.0 brings clips up to 15 seconds, native audio including speech in several languages, and a single model for text-to-video, image-to-video, reference-to-video and in-video editing. Kling 4.0 Flash opened to a limited group on September 28, 2026, with a wider Kling 4.0 rollout planned for October. See our news summary and the model tracker.
How prompting works
Describe each shot, its camera movement and the sound. For consistent characters, upload a reference image or video and say what stays the same.
Who should use it
Creators who want longer clips and strong multimodal control. Compare it in Veo vs Kling.