# Kling video models on AI Gateway

**Published:** February 19, 2026 | **Authors:** Walter Korman , Jeremy Philemon, Matt Lenhard, Jerilyn Zheng

---

Kling video models are now available in AI Gateway, including the newest Kling 3.0 models. Generate cinematic videos from text, images, or motion references with Kling's state-of-the-art video models, now available through AI Gateway and AI SDK.

Kling models are known for their image to video models and multishot capabilities:

- **Image-to-Video Capabilities**: Strong at animating still images into video clips
- **Realistic Motion and Physics**: Known for  coherent motion, facial expressions, and physical interactions
- **High Resolution Output**: Supports up to 1080p generation (pro mode)
- **Multishot Narratives**: Kling 3.0 can generate multi-scene videos from a single narrative prompt
- **Audio Generation**: Create synchronized sound effects and ambient audio alongside your video
- **First & Last Frame Control**: Specify both start and end frames for precise scene transitions

[Video: kling sample reel](//videos.ctfassets.net/e5382hct74si/45UcXHDeD9a75qAdcwXRoY/34f365de2ea70d8bdf6ac0e81e4bc4da/kling-edited-reel.mov)

## Two ways to get started

Video generation is in beta and currently available for Pro and Enterprise plans and paid AI Gateway users.

- **AI SDK 6**: Generate videos programmatically AI SDK 6's `generateVideo`.

```tsx
import { experimental_generateVideo as generateVideo } from 'ai';
const { videos } = await generateVideo({
  model: 'klingai/kling-v2.6-t2v',
  prompt: 'A chef plates a dessert with caramel drizzle. Kitchen ambiance.',
});
```

- **Gateway Playground**: Experiment with video models with no code in the configurable [AI Gateway playground](https://vercel.com/ai-gateway/models/kling-v3.0-t2v) that's embedded in each model page. Compare providers, tweak prompts, and download results without writing code. To access, click any video gen model in the [model list](https://vercel.com/ai-gateway/models?capabilities=video-generation&providers=klingai).

## Available Models

| Model | Type | Description |
| `klingai/kling-v3.0-t2v` | Text-to-Video | Latest generation, highest quality with multishot support |
| `klingai/kling-v3.0-i2v` | Image-to-Video, First-and-Last-Frame | Animate images with v3 quality and multiple frames |
| `klingai/kling-v2.6-t2v` | Text-to-Video | Audio generation support |
| `klingai/kling-v2.6-i2v` | Image-to-Video, First-and-Last-Frame | Use images as reference |
| `klingai/kling-v2.5-turbo-t2v` | Text-to-Video | Faster generation |
| `klingai/kling-v2.5-turbo-i2v` | Image-to-Video, First-and-Last-Frame | Faster generation |

## Simple: Text-to-Video with Audio

Generate a video from a text description.

[Video: kling cherry blososm](//videos.ctfassets.net/e5382hct74si/6Z4Ls0UQgoHhpJeJBaF4cU/8e203abd31fa5a2903e8590b6030742c/03-cherry-blossom.mp4)

In this example, model `klingai/kling-v3.0-t2v` is used to generate a video of a cherry blossom tree with no inputs other than a simple text prompt.

```tsx
import { experimental_generateVideo as generateVideo } from 'ai';
const { videos } = await generateVideo({
  model: 'klingai/kling-v3.0-t2v',
  prompt:
   `Cherry blossom petals falling in slow motion through golden sunlight,
    Japanese garden with a stone lantern, peaceful atmosphere, cinematic`,
  aspectRatio: '16:9',
  duration: 5,
  providerOptions: {
    klingai: {
      mode: 'pro',
    },
  },
});
```

## Advanced: Multishot Video

Generate a narrative video with multiple scenes with only a single prompt. Using Kling 3.0's multishot feature, the model intelligently cuts between shots to tell a complete story:

[Video: kling multi shot](//videos.ctfassets.net/e5382hct74si/4Y8ZngAaKsEC38pAxFVFbH/cfa7f25886e3c314d4a468782feab71b/savanna-storm.mp4)

The prompt is written as a narrative with multiple distinct scenes for the best results. `shotType: 'intelligence'` lets the model decide optimal shot composition and `sound: 'on'` generates synchronized audio for the entire video. Note that the prompt here is in the `providerOptions` since this functionality is specific to Kling. The Kling 3.0 models support this functionality: here `klingai/kling-v3.0-t2v` is used.

```tsx
import { experimental_generateVideo as generateVideo } from 'ai';
const { videos } = await generateVideo({
  model: 'klingai/kling-v3.0-t2v',
  prompt: '',
  aspectRatio: '16:9',
  duration: 10,
  providerOptions: {
    klingai: {
      mode: 'pro',
      multiShot: true,
      shotType: 'intelligence',
      prompt:
       `Elephants walk across a golden savanna under gathering storm clouds.
        Lightning cracks in the distance. Rain begins to fall heavily.
        The herd finds shelter under acacia trees.
        The storm clears revealing a double rainbow.`,
      sound: 'on',
    },
  },
});
```

## Advanced: First & Last Frame Control

Control exactly how your video starts and ends by providing both a first frame and last frame image. This is perfect for time-lapse effects or precise scene transitions:

[Video: flower kling i2v](//videos.ctfassets.net/e5382hct74si/5QRByBqOcxRyYYJve2DKEj/254e1411774622e785739651ad0f6ef9/flower-bloom-1770950527080-0.mp4)

These 2 images were provided as start and end frames.

![Group images flowers](//images.ctfassets.net/e5382hct74si/7rNmMOnFcjbH73BbQMsncd/b990d46d3751c94bc426675f6e2dad07/Group_1__2_.png)

Using AI SDK 6, you can set `image` and `lastFrameImage` with your start and end frames. In this example, `klingai/kling-v3.0-i2v` is used for the model.

```tsx
import { experimental_generateVideo as generateVideo } from 'ai';
const { videos } = await generateVideo({
  model: 'klingai/kling-v3.0-i2v',
  prompt: {
    image: startImage,
    text: `Time-lapse of a pink peony flower blooming.
     The tight bud slowly unfurls, petals gently separating and opening outward.
     Smooth organic movement. Soft natural lighting.`,
  },
  duration: 10,
  providerOptions: {
    klingai: {
      lastFrameImage: endImage,
      mode: 'pro',
    },
  },
});
```

## Learn More

For more examples and detailed configuration options for Kling models, check out the [Video Generation Documentation](https://vercel.com/docs/ai-gateway/capabilities/video-generation). You can also find simple getting started scripts with the [Video Generation Quick Start](https://vercel.com/docs/ai-gateway/getting-started/video).

---

📚 **More updates:** [View all changelog entries](/changelog/sitemap.md) | [Blog](/blog/sitemap.md)