Kling 2.5
Vendor: Kling
Video
Fast video drafts with quick turnaround
- Typical latency
- 30-120s
- Reference inputs
- Up to 2
- toolId
- kling-2-5
Input modes
text-to-videoimage-to-video
Parameters
| Parameter | Type | Default | Values | Notes |
|---|---|---|---|---|
| duration | select | 5 | 5 | 10 | Clip length. Longer clips cost more; re-quote after changing. |
| aspect_ratio | select | 9:16 | 16:9 | 9:16 | 1:1 | Output frame shape. Keep one ratio across a series. |
| use_end_frame | toggle | false | — | When enabled, the second uploaded image pins the final frame of the clip. |
| cfg_scale | slider | 0.5 | 0–1 | How closely the video follows the prompt; higher is stricter but can look stiffer. |
| negative_prompt | text | blur, distort, and low quality | — | Things to avoid in the video. |
Pricing
Pricing will be published shortly — contact us for early access rates
Prices last updated: —
API example
POST /v1/generations — kling-2-5
curl -X POST https://api.mukelabs.com/v1/generations \
-H "Authorization: Bearer $MUKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"toolId": "kling-2-5",
"inputMode": "text-to-video",
"prompt": "your prompt here",
"params": { "duration": "5" },
"references": [],
"idempotencyKey": "a-unique-key-per-task",
"subjectId": "your-user-id"
}'FAQ
How do I call Kling 2.5 on Muke Labs?
Submit POST /v1/generations with toolId "kling-2-5" and one of its input modes (text-to-video, image-to-video), then poll GET /v1/generations/{jobId} for the result.
What does Kling 2.5 cost?
Public pricing for this model is being finalized — contact us for early access rates. All tasks are billed from your prepaid USD balance and failed tasks refund automatically.
What happens if a task fails?
The job returns status "failed" with a typed error code, and its charge is returned to your balance automatically.
Where do I get an API key?
Create one in the developer portal (https://portal.muke.name), then send it as a Bearer token on every request.
Related models
Video
Kling
Kling
Video creation, effects, motion transfer and lip sync
text-to-videoimage-to-video
Video
Kling O1
Kling
Kling O1 — first/last-frame, omni-reference, video reference and video edit
image-to-videoomni-reference
Video
Kling O3
Kling
Kling O3 — image-to-video, omni-reference, video reference and video edit
image-to-videoomni-reference
Video
Auto Video Watermark Remover
Alibaba
Remove logos, captions, and watermarks from a video without drawing a mask
video-upscale