Kling 4.0 API
Kling 4.0 generates 3–30 second videos from text, images or references, and edits existing clips, at 720p or 1080p.
Explore the model lineup
Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.

Kling V4 Reference to Video
Kling V4 Reference to Video by Kuaishou generates a 3-30 second video that keeps characters, objects and motion from reference images and videos.

Kling V4 Text to Video
Kling V4 Text to Video by Kuaishou turns a text prompt into a 3-30 second video at 720p or 1080p.

Kling V4 Image to Video
Kling V4 Image to Video by Kuaishou animates a start image, optionally toward an end image, into a 3-30 second video.

Kling V4 Video Edit
Kling V4 Video Edit by Kuaishou edits a 3-30 second source video from a text instruction and optional reference images.
Model lineup
The most used endpoints first.
| Model | Task | What it does |
|---|---|---|
| Kling V4 Reference to Video | Reference → video | Kling V4 Reference to Video by Kuaishou generates a 3-30 second video that keeps characters, objects and motion from reference images and videos |
| Kling V4 Text to Video | Text → video | Kling V4 Text to Video by Kuaishou turns a text prompt into a 3-30 second video at 720p or 1080p |
| Kling V4 Image to Video | Image → video | Kling V4 Image to Video by Kuaishou animates a start image, optionally toward an end image, into a 3-30 second video |
| Kling V4 Video Edit | Video → video | Kling V4 Video Edit by Kuaishou edits a 3-30 second source video from a text instruction and optional reference images |
Kling 4.0 on SandBase
Kling 4.0 is the newest Kling generation. Its main change is clip length: every endpoint works with 3–30 second videos, up from 15 seconds on Kling 3.0.
- Text to video: 3–30 seconds at 720p or 1080p.
- Image to video: animate a start image, optionally toward an end image.
- Reference to video: keep characters, objects and motion from reference images and videos.
- Video edit: change a 3–30 second source clip with a text instruction and optional reference images.
Need 4K, Motion Control or talking avatars? Those are on Kling 3.0. Every version is on Kling API.
Start using Kling 4.0 API on SandBase
One API key and one request shape for every model on this page.
- 01
Create an API key
Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.
TERMINALexport SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY" - 02
Submit a run
Send a request to the Unified Run API with model kwaivgi/kling-video/v4/text-to-video. Only the model field changes between models on this page.
TERMINALcurl https://api.sandbase.ai/v1/run \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "kwaivgi/kling-video/v4/text-to-video", "prompt": "A single drop of water falls from a leaf into a shallow dish, golden window light, macro shot"}' - 03
Fetch the result
The response includes a run id. Poll it every few seconds until the status is completed, then download the output URL.
TERMINALcurl https://api.sandbase.ai/v1/run/$RUN_ID \ -H "Authorization: Bearer $SANDBASE_API_KEY"
Questions, answered
How long can Kling 4.0 videos be?
3 to 30 seconds on every Kling 4.0 endpoint.
What resolutions does Kling 4.0 support?
Text to Video lists 720p and 1080p. Check each model page for its options.
Kling 4.0 or Kling 3.0?
Use 4.0 for clips longer than 15 seconds and reference-guided video. Use 3.0 for native 4K and Motion Control.
Can Kling 4.0 edit an existing video?
Yes. Kling V4 Video Edit changes a 3–30 second clip from a text instruction and optional reference images.
Build with Kling 4.0 API.
One key, consistent APIs, and usage-based pricing across every model on this page.
