DocsKling 2.6 I2V
Model
kling-2.6-i2v
Image-to-video Kling 2.6 variant with required image input.
Model supplement for /unified-video/quote and /unified-video/generateScope: Depends on API key scopes configured in backend
Best for
Teams that want a dedicated image-to-video Kling 2.6 flow.
Dedicated I2V flow
Required image input
Audio-sensitive pricing
What you can send
- Required: model, prompt, images
- Optional: duration, generateAudio, projectId
- Require at least one image. aspectRatio, negativePrompt, cfgScale, and cameraControl are not supported on this model.
Field rules
prompt
Max 1000 characters.
images
Required. MidSync uses the first image.
duration
Supported: 5, 10.
generateAudio
Forwarded as sound and affects price.
Pricing
Audio
5s
10s
Off
46
92
On
92
184
Frontend notes
- Make image input required.
- Do not expose aspectRatio, negativePrompt, cfgScale, or cameraControl on this model.
- Keep the same price display logic as T2V.
- Use callback as the main completion flow.
Ready to test with your own key?
Create a general API key in Settings, then come back here to copy a request example.