---
title: KlingAI 2.5 Turbo Pro | Runware Docs
url: https://runware.ai/docs/models/klingai-2-5-turbo-pro
description: Cinematic text to video and image to video at scale
---
# KlingAI 2.5 Turbo Pro

![KlingAI 2.5 Turbo Pro](https://assets.runware.ai/covers/klingai-2-5-turbo-pro.jpg)

KlingAI 2.5 Turbo Pro is a high performance video generation model for cinematic work. It converts prompts or stills into smooth 1080p clips with strong motion, precise camera control and tight prompt adherence. Ideal for creative tools, ads, trailers and sports scenes.

- **Status**: live
- **ID**: `klingai:6@1`
- Try in Playground
- **Creator**: Kling AI
- **Release Date**: September 23, 2025
- **Capabilities**: Text to Video, Image to Video, Checkpoint

## Pricing

$0.07 per second · ~2m 28s per request

**4 example generations**

- [text-to-video](https://runware.ai/docs/models/klingai-2-5-turbo-pro/examples#example-mycelium-textile-laboratory-b-roll) · 5s: `$0.35` (~2m 27s)
- [text-to-video](https://runware.ai/docs/models/klingai-2-5-turbo-pro/examples#example-industrial-sprinkler-activation-explainer-clip) · 5s: `$0.35` (~3m 45s)
- [first-last-frame](https://runware.ai/docs/models/klingai-2-5-turbo-pro/examples#example-volcanic-observatory-documentary-titles) · 5s: `$0.35` (~2m 28s)
- [first-frame](https://runware.ai/docs/models/klingai-2-5-turbo-pro/examples#example-antique-watch-restoration-social-reel) · 10s: `$0.70` (~1m 9s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `720p (16:9)` | `1280x720` |
| `720p (1:1)` | `720x720` |
| `720p (9:16)` | `720x1280` |
| `1080p (16:9)` | `1920x1080` |
| `1080p (1:1)` | `1080x1080` |
| `1080p (9:16)` | `1080x1920` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-outputformat)

- **Type**: `string`
- **Default**: `MP4`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP4\`: Widely supported video container (H.264), recommended for general use.
- \`WEBM\`: Optimized for web delivery.
- \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem).

**Allowed values**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [frameImages](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`
- **Size (each)**: `300 px or more`

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.

When the `frame` parameter is omitted, automatic distribution rules apply:

- **1 image**: Used as the first frame.
- **2 images**: First and last frames.

**Examples**:

**Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]
```

**First and last frames:** With two images, they automatically become the first and last frames of the video sequence. You can mix shorthand and object formats.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [frame](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. Supports first and last frame.

**Allowed values**:

- `first` First frame of the video.
- `last` Last frame of the video.
- `0` Frame index 0 (first frame).
- `-1` Frame index -1 (last frame).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `klingai:6@1`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `2500`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [negativePrompt](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-negativeprompt)

- **Type**: `string`
- **Min**: `2`
- **Max**: `2500`

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

**Learn more** (1 resource):

- [Prompts: Negative Prompts](https://runware.ai/docs/learn/prompts#negative-prompts) (learn)

### [width](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-width)

- **Type**: `integer`
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-height)

- **Type**: `integer`
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [duration](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-duration)

- **Type**: `integer`
- **Default**: `5`

Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

**Allowed values**: `5` `10`

### [CFGScale](https://runware.ai/docs/models/klingai-2-5-turbo-pro#request-cfgscale)

- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.5`

Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.

**Learn more** (1 resource):

- [Cfg Scale](https://runware.ai/docs/learn/cfg-scale) (learn)

## Response Parameters

### [taskType](https://runware.ai/docs/models/klingai-2-5-turbo-pro#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/klingai-2-5-turbo-pro#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/klingai-2-5-turbo-pro#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/klingai-2-5-turbo-pro#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/klingai-2-5-turbo-pro#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/klingai-2-5-turbo-pro#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [NSFWContent](https://runware.ai/docs/models/klingai-2-5-turbo-pro#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/klingai-2-5-turbo-pro#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/klingai-2-5-turbo-pro/8d463647-77e3-46bf-8af6-5d3a593bbf4a.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "7715d6c7-24d1-4c56-b454-b91b98999a25",
  "model": "klingai:6@1",
  "positivePrompt": "Five-second photorealistic documentary b-roll, one continuous shot inside a clean biomaterials laboratory. A lab technician wearing muted sage-green nitrile gloves carefully peels a broad sheet of freshly grown mycelium textile from a shallow stainless-steel cultivation tray. The flexible cream-colored material has a dense, suede-like surface with delicate branching fibers visible along its irregular edge. Begin in a tight three-quarter close-up level with the tray; as the technician raises and gently bends the sheet, the camera makes a slow, controlled lateral slider move from left to right with a subtle push-in, keeping the lifted edge in crisp focus. The textile flexes naturally, tiny condensation droplets catch the light, and faint cool vapor drifts behind it. Soft window daylight mixed with warm laboratory task lighting, restrained palette of ivory, sage, brushed steel, and amber, shallow depth of field, realistic hand motion and material physics, polished 16:9 commercial stock footage, no cuts, no labels, no logos, no text.",
  "negativePrompt": "fantasy organisms, mushrooms sprouting from the sheet, synthetic plastic texture, damaged hands, extra fingers, duplicated tools, excessive vapor, shaky camera, fast motion, jump cuts, text, labels, logos, watermark",
  "width": 1280,
  "height": 720,
  "duration": 5
}
```

---

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/klingai-2-5-turbo-pro/5a24e1f9-86cc-4f6b-8b51-341444efc4a9.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "ef67d638-2088-4154-895d-65d04fd31bf8",
  "model": "klingai:6@1",
  "positivePrompt": "A precise industrial product explainer in one continuous 5-second macro shot: a chrome commercial fire sprinkler head mounted beneath a dark charcoal ceiling panel inside a controlled testing chamber. Clean laboratory art direction with a deep teal background, warm amber heat, crisp metallic highlights, and no branding or text. Begin in a tight three-quarter close-up as a small controlled flame flickers below the sprinkler and heat shimmer rises around its red glass thermal bulb. The camera makes a slow, steady push-in. After roughly two seconds, the heated glass bulb fractures sharply and the valve releases; a powerful stream of water strikes the circular deflector plate and instantly becomes a broad, symmetrical umbrella of fine droplets. As the spray expands, the camera smoothly pulls back just enough to reveal the even radial coverage pattern while keeping the sprinkler centered and sharply defined. Realistic water physics, visible individual droplets, natural reflections, high-speed product cinematography, technically accurate activation sequence, uncluttered composition, polished engineering-demo aesthetic.",
  "negativePrompt": "people, hands, firefighters, smoke-filled room, building fire, explosion, dramatic destruction, labels, captions, logos, interface graphics, diagrams, split screen, multiple sprinkler heads, warped hardware, detached components, inaccurate water direction, frozen water, excessive motion blur, shaky camera, cartoon rendering",
  "width": 1280,
  "height": 720,
  "duration": 5
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/klingai-2-5-turbo-pro/5b1e4cb6-49c6-4bb5-885a-d6fd1053ec31.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "f9973895-f97c-4da6-9d10-f67822e8e7e8",
  "model": "klingai:6@1",
  "positivePrompt": "Continue naturally from the supplied opening frame in one elegant 10-second macro shot. The tweezers descend with controlled precision and seat the tiny ruby jewel; rack focus follows the jewel into place while the watchmaker’s hand remains steady and anatomically correct. The tweezers withdraw, the balance assembly settles, and the escapement begins ticking with believable mechanical motion. The camera then makes a slow, low clockwise orbit across the movement as interlocking brass gears turn in sequence and polished edges catch warm highlights. Preserve the antique mechanism’s geometry and scale throughout. Fine dust motes drift through the teal rim light, adding depth without obscuring the watch. During the final two seconds, gently pull back to reveal the completed open pocket watch as the gloved hand leaves frame, ending on a refined hero composition suitable for a premium craft-restoration social reel. Smooth cinematic motion, precise macro focus transitions, tactile metal detail, quiet confidence, no cuts, no captions or branding.",
  "negativePrompt": "Text, subtitles, logos, watermarks, jump cuts, time-lapse, warped gears, melting metal, duplicated tools, extra fingers, deformed hands, floating components, incorrect mechanical motion, camera shake, flicker, abrupt focus hunting, excessive sparks, fantasy effects, cartoon styling, oversaturated colors.",
  "width": 720,
  "height": 1280,
  "duration": 10,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/e0825cbe-1275-40c3-a94e-bf649943983f.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

### first-last-frame (first-last-frame)

[Watch video](https://assets.runware.ai/examples/klingai-2-5-turbo-pro/29c9d907-45aa-49c7-b4b4-e8491a906b91.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "3e5d97d2-f433-4b00-95fe-f127b8a9e72d",
  "model": "klingai:6@1",
  "positivePrompt": "Create a single continuous five-second documentary title shot connecting the supplied first and last frames. Keep the square macro composition locked on the same vintage seismograph with consistent geometry, surface wear, lighting, and shallow focus. Begin in tense near-stillness as the paper drum slowly rotates and the needle draws a quiet horizontal line. A subtle low-frequency tremor starts: the red cable quivers, brass screws vibrate, a hanging fluorescent reflection flickers across the mint housing, and tiny grains of volcanic ash drift down through the sulfur-yellow beam. The needle movement grows from delicate ticks into urgent, controlled oscillations while the camera makes an almost imperceptible push toward the graph paper. Without a cut, the moving black trace evolves into precise hand-drawn letterforms, naturally writing the uppercase title “FAULTLINE” across the rotating paper. Motion must feel mechanically credible, escalating but never chaotic. Finish exactly on the supplied final-frame composition with the title sharp and readable, ash suspended in the light, and the machine still trembling faintly. Prestige geological documentary aesthetic, practical analog detail, charcoal black, oxidized orange, pale mint, and acid yellow palette; restrained scientific tension, subtle film grain, no people, no extra text, no logos, no transition away from the machine.",
  "width": 720,
  "height": 720,
  "duration": 5,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/21f8f14f-2673-4b20-b63b-8c8a309f5864.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/24d834e1-35e0-44b1-b1b2-1b3552608986.jpg",
        "frame": "last"
      }
    ]
  }
}
```