Pick a Kling model to match your output — compared by input type, resolution, credit cost and what each is best at.
The video and image models you can run on Kling AI.
Cinematic video from text / image. standard (720p) · pro (1080p), audio support, multi-shot. 3–15s.
Video from text, image & reference image (up to 4). standard · pro, audio support. 3–15s.
Fast video generation. standard 720p · pro 1080p, text / image input. 3–15s (5s default).
Motion control that transfers a reference video’s motion onto a single image. 720p/1080p, up to 10s (image) / 30s (video).
Motion control that applies a reference video’s motion to a character image. 720p/1080p, up to 10s / 30s.
A comparison of every available model.
Tell us what you want to make and we'll point you to the right Kling model.
Delivery-ready cinematic video
Flagship model with audio and multi-shot, up to 4K for finals.
Cost-conscious everyday clips
The 720p–4K standard model at a lower cost than Kling 3.0.
Fast drafts to test prompts
Lowest-tier 720p / 1080p drafts to validate direction.
Transfer motion from a reference video
High-quality transfer of reference-video motion onto a single image.
Stills to build on
Generate stills up to 4K from text.
Edit an existing image
Edit and recompose from 1–10 reference images.
Common questions when picking a model.