Kuaishou Kling 3.0
Kuaishou's cinematic video model generating clips up to 1080p with native audio, lip sync, and sound effects from text or images.
Kling 3.0 is a cloud video-generation model built by Kuaishou. It produces short video clips from a text prompt, a starting image, or by interpolating between a first and last frame. It can also take reference video to guide the result. Clips run up to 15s at 4k with a synchronized audio track. It also supports a negative prompt and reference images. It runs through Kling, OpenRouter, Runware, and Replicate using your own API key, from about $0.126 per second of output.
- Released
- Feb 2026
- Pricing
- $0.126 per second
- Max resolution
- 4k
- Aspect ratios
- 16:9, 9:16, 1:1
- Clip length
- Up to 15s
- Audio
- Synchronized track
- Image-to-video
- Start & end frame + reference images
- Negative prompt
- Supported
- Image to video rank
- #19
Samples
Generated with Kling 3.0 via Runware. The same two prompts run against every video model in the catalog (one landscape, one portrait), so the only thing that changes between two models’ clips is the model.
Camera motion, scene coherence over time
Fluid motion, fine detail, temporal stability
Kuaishou
Kuaishou builds the Kling family of cinematic video models — high-resolution clips with native audio, lip sync, and multi-shot storytelling.
klingai.com ↗Kuaishou's Kling Image 3.0 model for consistent text-to-image and single-reference image editing at 1K or 2K.
Kuaishou's multi-reference Kling Image 3.0 Omni model with native 2K and 4K output from text and up to ten reference images.
Kuaishou's Kling sound effects model, generating 3 to 10 second clips from a short text description.
Kuaishou's Kling text-to-speech model, reading up to 1,000 characters aloud in English or Chinese system voices.
Kuaishou's unified video model: clips of up to 30 seconds at 1080p with native audio, from text, first and last frames, reference images and videos, or a prompt that edits a source clip.
Kuaishou's faster, lower-cost Kling 4.0 tier: 720p clips of 3 to 20 seconds with native audio, from text, a first frame, reference images and videos, or a prompt that edits a source clip.
One dies in 70 days, one was outranked by its own maker, one still ships. The matchup, re-run for real: six clips, first takes only.
Nine images, four clips, $3.17 in API bills: what ByteDance's Seedream and Seedance actually return on prompts we ran ourselves.
Forty-seven minutes. Three dollars and seventy-three cents. Every prompt, every cost, one API — and the finished ad, embedded.
OpenAI killed Sora. The Chinese open-weight stack took the top three on the arena. And a 10-second clip now starts at fifty cents.