Kling 4.0 - Longer scenes. Native sound. One prompt.

Text to Video turns a prompt—or a list of per-shot prompts—into a finished clip. Image to Video animates from a start frame, with an optional end frame to land the shot exactly where you want it.

Reference to Video blends up to 10 reference images (@Image1, @Image2…) and an optional reference clip (@Video1) into one scene, so characters, products, and locations stay on-model. Video Edit rewrites an uploaded 3–30s clip from a text instruction while keeping its timing and length.

Kling 4.0 is billed by the second and by resolution. A 5-second clip costs 127 credits at 720p or 189 credits at 1080p; a full 30-second 1080p clip costs 1,134 credits. Audio is always included at no extra cost.

When a reference or source video is involved, the per-second rate drops and both the input clip and the output count toward the total. Editing a 10-second clip costs 303 credits at 720p or 454 credits at 1080p. Studio always shows the exact cost before you generate.

720p costs about a third less than 1080p. Iterate on prompts, timing, and shot breakdowns at 720p, then re-run the version you like at 1080p for the final export.