# Kling 2.5 Turbo Pro Text-to-Video

> Generate a short, cinematic video from a text prompt with smooth, fluid motion and strong prompt adherence.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/kuaishou/kling-video/v2.5-turbo/text-to-video`
- **Model ID**: `kuaishou/kling-video/v2.5-turbo/text-to-video`
- **Category**: text-to-video
- **Kind**: inference
- **Tags**: kling, kling-video, kuaishou, text-to-video, video-generation

## Pricing

- **Price**: $0.07 per output second

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/kuaishou/kling-video/v2.5-turbo/text-to-video` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/kuaishou/kling-video/v2.5-turbo/text-to-video/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/kuaishou/kling-video/v2.5-turbo/text-to-video/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/kuaishou/kling-video/v2.5-turbo/text-to-video/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`prompt`** (`string`, _required_):
  Text description of the video to generate.

- **`duration`** (`duration`, _optional_):
  Length of the generated video in seconds.
  - Default: `"5"`
  - Options: `"5"`, `"10"`

- **`cfg_scale`** (`number`, _optional_):
  How strongly the video follows the prompt. Higher values increase prompt adherence; lower values allow more creative motion.
  - Default: `0.5`
  - Range: `0` to `1`

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

- **`negative_prompt`** (`string`, _optional_):
  Describe content to avoid in the generated video.
  - Default: `"blur, distort, and low quality"`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "A lone red sailboat glides across a calm turquoise bay at sunrise, the camera slowly tracking alongside as light glints off the water and distant mountains catch the first warm glow",
  "duration": "5",
  "cfg_scale": 0.5,
  "aspect_ratio": "16:9",
  "negative_prompt": "blur, distort, and low quality"
}
```

**Output**

```json
"https://media.modelrunner.ai/iBfyuB8HXGcmNZYnI37XN.mp4"
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/kuaishou/kling-video/v2.5-turbo/text-to-video \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A lone red sailboat glides across a calm turquoise bay at sunrise, the camera slowly tracking alongside as light glints off the water and distant mountains catch the first warm glow",
  "duration": "5",
  "cfg_scale": 0.5,
  "aspect_ratio": "16:9",
  "negative_prompt": "blur, distort, and low quality"
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("kuaishou/kling-video/v2.5-turbo/text-to-video", {
  input: {
  "prompt": "A lone red sailboat glides across a calm turquoise bay at sunrise, the camera slowly tracking alongside as light glints off the water and distant mountains catch the first warm glow",
  "duration": "5",
  "cfg_scale": 0.5,
  "aspect_ratio": "16:9",
  "negative_prompt": "blur, distort, and low quality"
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "kuaishou/kling-video/v2.5-turbo/text-to-video",
        arguments={
  "prompt": "A lone red sailboat glides across a calm turquoise bay at sunrise, the camera slowly tracking alongside as light glints off the water and distant mountains catch the first warm glow",
  "duration": "5",
  "cfg_scale": 0.5,
  "aspect_ratio": "16:9",
  "negative_prompt": "blur, distort, and low quality"
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/kuaishou/kling-video/v2.5-turbo/text-to-video)
- [OpenAPI Schema](https://modelrunner.ai/models/kuaishou/kling-video/v2.5-turbo/text-to-video/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/kuaishou/kling-video/v2.5-turbo/text-to-video/llms.txt)