# Kling 4.0

> Create 3–30 second Kling 4.0 videos from text, a photo, or reference images and videos. 720p or 1080p, native audio, private output, credits shown first.

- [Canonical Kling 4.0 page](https://mixvio.ai/models/kling-4)
- [Official model source](https://kling.ai/quickstart/kling-4-model-user-guide)

## Route summary

- **Provider:** Kuaishou
- **Media:** video
- **Inputs:** Text · Start photo · Last frame · Up to 10 photos · 5 videos
- **Output:** 720p–1080p video + audio
- **Duration:** 3–30s
- **Native audio:** Yes
- **Credits:** 33–593 credits
- **Availability:** Available

## Capabilities

- **Lip sync and stereo:** Native stereo stays on. In this studio take, the singer’s mouth follows the vocal for the full 30 seconds.
- **Native 30-second video:** One generation can run 3–30 seconds. This vertical introduction stays on one speaker for 30 seconds.
- **One continuous story:** The shot starts with a glowing star in an open hand and continues as a neon creature appears in the air.
- **Two subjects in one shot:** The red supercar and the motorcycle share one waterfront shot, so both subjects stay in the same scene.

## How to use

1. **Start from text, one photo, or references:** Use text for a new scene, image to video for one owned start photo and an optional last frame, or reference to video for up to 10 photos and 5 videos. Prefill a Key Feature or Example if you want. Nothing runs until you generate.
2. **Set length, resolution, and ratio:** Choose every whole second from 3 to 30, and 720p or 1080p. Text uses 16:9, 9:16, 1:1, or 21:9. Image to video follows the photo. Reference to video can use auto, 16:9, 9:16, 1:1, or 21:9. Tag files with @Image1 and @Video1. Native stereo stays on.
3. **Generate, review, then iterate:** Confirm the credit estimate, then generate. Review identity, motion, and sound before you publish or change the prompt.

## Pricing

From 33 credits for 3 seconds at 720p, 83 credits for the default 5-second 1080p video, up to 494 credits for 30 seconds at 1080p with no reference video. A 10-second 720p video with 10 seconds of reference video is 132 credits. The top of the table is 593 credits. Photos do not change the quote. Reference-video seconds do.

- [MixVio pricing](https://mixvio.ai/pricing)

## FAQ

### What can I generate with Kling 4.0 on MixVio?

Text to video, image to video, or reference to video. Text uses 16:9, 9:16, 1:1, or 21:9. Image to video takes one start photo and an optional last frame, and follows that photo. Reference to video takes up to 10 photos and 5 videos, 15 files total, and can use auto, 16:9, 9:16, 1:1, or 21:9. Duration is every whole second from 3 to 30. Output is 720p or 1080p. Native stereo audio stays on.

### How many credits does Kling 4.0 use?

A 3-second 720p video is 33 credits. The default 5-second 1080p video is 83 credits. A 30-second 1080p video with no reference video is 494 credits. A 10-second 720p video with 10 seconds of reference video is 132 credits. The top of the table is 593 credits for 30 seconds at 1080p with 30 seconds of reference video. Photos do not change the quote. Reference-video seconds do. Confirm the reservation before you generate. Failed runs cost no credits.

### Does Kling 4.0 on MixVio include 4K, HDR, or Flash?

No. This route is 720p and 1080p only. 4K, 10-bit HDR, Kling 4.0 Flash, and the two-minute extension are not on MixVio. Kling 3.0 still offers 4K on its own page.

### Can I upload keyframes, elements, or a voice?

Image to video accepts one start photo and an optional last frame. Reference to video accepts up to 10 photos and 5 videos. A 10-keyframe editor, element library, voice reference, and video edit are not on this route. Tag reference files with @Image1 and @Video1.

### Is Kling 4.0 available on the Free plan?

Yes, when the workspace balance covers the quote. Kling 4.0 is on the Free, Creator, and Pro plans. The generator shows the exact reservation before you generate. Failed runs cost no credits.

### What limits apply to reference photos and videos?

Each photo is up to 30MB, with the short side at least 300 pixels and an aspect ratio from 0.4 to 2.5. Each reference video is 3–30.05 seconds, up to 300MB, with both sides from 700 to 4,553 pixels, 23.9–60 FPS, and the same aspect range. Up to 5 videos, and their durations together stay within 30.05 seconds. Prompts stop at 2,500 characters.

### Does audio turn off?

No. Kling 4.0 on MixVio includes native stereo audio on every video. There is no audio toggle, and audio does not add a separate credit line.

### How is Kling 4.0 different from Kling 3.0 on MixVio?

Kling 4.0 runs 3–30 seconds at 720p or 1080p, with a start photo plus optional last frame, or a pack of up to 10 photos and 5 videos. Kling 3.0 runs 5, 10, or 15 seconds at 720p, 1080p, or 4K, with an optional end frame and no reference-video pack on the public page.