Supports text-to-video, keyframe-to-video, reference-to-video, and video editing. Always generates video with sound.
Inference service provider
The inference service provider for the kling/kling-v4-omni-reference-video-generation model is Kling AI.
Model capabilities
| Input modalities | Output modality | Supported capabilities |
|---|---|---|
| Image, Text, Video | Video | Text-to-video, keyframe-to-video, reference-to-video, and video editing |
std (720P) and pro (1080P), generates 3–30 second videos, and outputs MP4 (H.264). For usage, see Kling - Video Generation API.
Pricing
This page shows the original model invocation prices only and does not include limited-time promotions. Go to the Model Studio console to view promotional offers.
- China (Beijing)
| Billing item | Price (CNY) | Unit |
|---|---|---|
| Video generation (720P, without reference video) | 1.0 | Per second |
| Video generation (1080P, without reference video) | 1.5 | Per second |
| Video generation (720P, with reference video) | 0.6 | Per second |
| Video generation (1080P, with reference video) | 0.9 | Per second |
Rate limits
- China (Beijing)
| Parameter | Value |
|---|---|
| Requests per second (RPS) | 5 |
| Concurrent processing tasks | 10 (shared) |