# Kandinsky 6.0 Lite

> Kandinsky 6.0 Lite is a lightweight, high-speed text-to-video model from Kandinsky Lab, built for fast, efficient generation with strong prompt adherence.


## Overview

- **Endpoint**: `https://fal.run/fal-ai/kandinsky6-lite/text-to-video`
- **Model ID**: `fal-ai/kandinsky6-lite/text-to-video`
- **Category**: text-to-video
- **Kind**: inference
**Description**: Kandinsky 6.0 Lite is the speed-focused model in the Kandinsky 6.0 video lineup. It turns text prompts into smooth, consistent short clips at low latency, making it ideal for rapid iteration, drafts, and high-volume pipelines. It natively understands English and Russian prompts, including Russian cultural concepts.

**Tags**: text-to-video, kandinsky, lightweight



## Pricing

Your request will cost **$0.16** per unit. 1 unit = one 5-second 480p video at 10 inference steps.

For more details, see [fal.ai pricing](https://fal.ai/pricing).

## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:


- **`prompt`** (`string`, _required_):
  The text prompt describing the video and its sound.
  - Examples: "A cat and a dog baking a cake together in a kitchen. The cat whisks batter while the dog sniffs the flour; a kitchen timer ticks and a mixer hums in the background."

- **`aspect_ratio`** (`AspectRatioEnum`, _optional_):
  The aspect ratio of the generated video. Default value: `"16:9"`
  - Default: `"16:9"`
  - Options: `"16:9"`, `"9:16"`, `"1:1"`, `"4:3"`, `"3:4"`

- **`generate_audio`** (`boolean`, _optional_):
  Whether to generate a synchronized audio track. Default value: `true`
  - Default: `true`

- **`enable_prompt_expansion`** (`boolean`, _optional_):
  Whether to rewrite the prompt into a detailed video+audio description with the model's own Qwen2.5-VL text encoder before generating.
  - Default: `false`

- **`upscale_factor`** (`float`, _optional_):
  If set, upscale the generated video by this factor with Kandinsky 6 video super-resolution. One of 2, 2.25 or 4; 2.25 turns the 480p output into 1080p.

- **`seed`** (`integer`, _optional_):
  The random seed used for the generation process.

- **`sync_mode`** (`boolean`, _optional_):
  If `True`, the media will be returned as a data URI and the output data won't be available in the request history.
  - Default: `false`

- **`num_inference_steps`** (`integer`, _optional_):
  The number of denoising steps. Lite is tuned for 10. Default value: `10`
  - Default: `10`
  - Range: `4` to `16`



**Required Parameters Example**:

```json
{
  "prompt": "A cat and a dog baking a cake together in a kitchen. The cat whisks batter while the dog sniffs the flour; a kitchen timer ticks and a mixer hums in the background."
}
```

**Full Example**:

```json
{
  "prompt": "A cat and a dog baking a cake together in a kitchen. The cat whisks batter while the dog sniffs the flour; a kitchen timer ticks and a mixer hums in the background.",
  "aspect_ratio": "16:9",
  "generate_audio": true,
  "num_inference_steps": 10
}
```


### Output Schema

The API returns the following output format:

- **`video`** (`File`, _required_):
  The generated video, with its audio track when requested.

- **`seed`** (`integer`, _required_):
  The random seed used for the generation process.



**Example Response**:

```json
{
  "video": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  }
}
```


## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://fal.run/fal-ai/kandinsky6-lite/text-to-video \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
     "prompt": "A cat and a dog baking a cake together in a kitchen. The cat whisks batter while the dog sniffs the flour; a kitchen timer ticks and a mixer hums in the background."
   }'
```

### Python

Ensure you have the Python client installed:

```bash
pip install fal-client
```

Then use the API client to make requests:

```python
import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/kandinsky6-lite/text-to-video",
    arguments={
        "prompt": "A cat and a dog baking a cake together in a kitchen. The cat whisks batter while the dog sniffs the flour; a kitchen timer ticks and a mixer hums in the background."
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)
```

### JavaScript

Ensure you have the JavaScript client installed:

```bash
npm install --save @fal-ai/client
```

Then use the API client to make requests:

```javascript
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/kandinsky6-lite/text-to-video", {
  input: {
    prompt: "A cat and a dog baking a cake together in a kitchen. The cat whisks batter while the dog sniffs the flour; a kitchen timer ticks and a mixer hums in the background."
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);
```


## Additional Resources

### Documentation

- [Model Playground](https://fal.ai/models/fal-ai/kandinsky6-lite/text-to-video)
- [API Documentation](https://fal.ai/models/fal-ai/kandinsky6-lite/text-to-video/api)
- [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=fal-ai/kandinsky6-lite/text-to-video)

### fal.ai Platform

- [Platform Documentation](https://fal.ai/docs/documentation)
- [Python Client](https://fal.ai/docs/api-reference/client-libraries/python)
- [JavaScript Client](https://fal.ai/docs/api-reference/client-libraries/javascript)

### Other agent-readable surfaces

This file covers one model. To find anything else:

- [Platform overview](https://fal.ai/llms.txt): Entry points and representative endpoint IDs
- [Documentation index](https://fal.ai/docs/llms.txt): Every documentation page
- [Full documentation text](https://fal.ai/docs/llms-full.txt): The whole documentation inlined
- Any other model: `https://fal.ai/models/<endpoint-id>/llms.txt`