# Kling API 文档

> 通过 AI Studio API 使用 Kling 模型生成视频。

## 概览

使用 AI Studio API 创建 Kling 生成任务并查询任务状态。接口采用异步流程：先创建任务拿到 `taskId`，再通过任务查询接口轮询结果。

## 认证方式

所有请求都需要在 `Authorization` 请求头中携带 API Key。

```http
Authorization: Bearer YOUR_API_KEY
```

## 可用模型

| modelId | 版本 | 服务商 | 运行模型 |
| --- | --- | --- | --- |
| `video:kling-3-0` | Kling 3.0 | Kling 3.0 | kling-3.0 |
| `video:kling-3-0-motion-control` | Kling 3.0 Motion Control | Kling-3.0 motion-control | kling-3.0/motion-control |
| `video:kling-v3-turbo-text-to-video` | Kling V3 Turbo Text to Video | Kling | kling/v3-turbo-text-to-video |
| `video:kling-v3-turbo-image-to-video` | Kling V3 Turbo Image to Video | Kling | kling/v3-turbo-image-to-video |
| `video:kling-2-6-text-to-video` | Kling 2.6 Text to Video | Kling 2.6 Text to Video | kling-2.6/text-to-video |
| `video:kling-2-6-image-to-video` | Kling 2.6 Image to Video | Kling 2.6 Image to Video | kling-2.6/image-to-video |
| `video:kling-2-6-motion-control` | Kling 2.6 Motion Control | Kling 2.6 motion-control | kling-2.6/motion-control |
| `video:kling-v2-5-turbo-text-to-video-pro` | Kling 2.5 Turbo Text to Video Pro | Kling | kling/v2-5-turbo-text-to-video-pro |
| `video:kling-v2-5-turbo-image-to-video-pro` | Kling 2.5 Turbo Image to Video Pro | Kling | kling/v2-5-turbo-image-to-video-pro |
| `video:kling-v2-1-master-text-to-video` | Kling V2.1 Master Text to Video | Kling V2.1 Master Text to Video | kling/v2-1-master-text-to-video |
| `video:kling-v2-1-master-image-to-video` | Kling V2.1 Master Image to Video | Kling V2.1 Master Image to Video | kling/v2-1-master-image-to-video |
| `video:kling-v2-1-pro` | Kling V2.1 Pro | Kling V2.1 Pro | kling/v2-1-pro |
| `video:kling-v2-1-standard` | Kling V2.1 Standard | Kling V2.1 Standard | kling/v2-1-standard |
| `video:kling-ai-avatar-standard` | Kling AI Avatar Standard | Kling AI Avatar Standard | kling/ai-avatar-standard |
| `video:kling-ai-avatar-pro` | Kling AI Avatar Pro | Kling AI Avatar Pro | kling/ai-avatar-pro |
| `video:fal-fal-ai-kling-video-v3-pro-text-to-video` | Kling v3 Pro Text to Video | kling-video | fal-ai/kling-video/v3/pro/text-to-video |
| `video:fal-fal-ai-kling-video-v3-standard-text-to-video` | Kling v3 Standard Text to Video | kling-video | fal-ai/kling-video/v3/standard/text-to-video |
| `video:fal-fal-ai-kling-video-v3-pro-image-to-video` | Kling v3 Pro Image to Video | kling-video | fal-ai/kling-video/v3/pro/image-to-video |
| `video:fal-fal-ai-kling-video-v3-standard-image-to-video` | Kling v3 Standard Image to Video | kling-video | fal-ai/kling-video/v3/standard/image-to-video |
| `video:fal-fal-ai-kling-video-v3-4k-image-to-video` | Kling v3 4K Image to Video | kling-video | fal-ai/kling-video/v3/4k/image-to-video |
| `video:fal-fal-ai-kling-video-v3-4k-text-to-video` | Kling v3 4K Text to Video | kling-video | fal-ai/kling-video/v3/4k/text-to-video |
| `video:fal-fal-ai-kling-video-o1-image-to-video` | Kling O1 Image to Video | kling-video | fal-ai/kling-video/o1/image-to-video |
| `video:fal-fal-ai-kling-video-v2-6-pro-text-to-video` | Kling v2.6 Pro Text to Video | kling-video | fal-ai/kling-video/v2.6/pro/text-to-video |
| `video:fal-fal-ai-kling-video-v2-6-pro-image-to-video` | Kling v2.6 Pro Image to Video | kling-video | fal-ai/kling-video/v2.6/pro/image-to-video |
| `video:fal-fal-ai-kling-video-v2-6-standard-motion-control` | Kling v2.6 Motion Control | kling-video | fal-ai/kling-video/v2.6/standard/motion-control |

## 1. 创建生成任务

### 接口地址

```http
POST https://localhost:3000/api/ai-studio/execute
Content-Type: application/json
Authorization: Bearer YOUR_API_KEY
```

### 请求示例

```json
{
  "modelId": "video:kling-3-0",
  "isPublic": true,
  "payload": {
    "model": "kling-3.0"
  }
}
```

### 成功响应

```json
{
  "success": true,
  "data": {
    "modelId": "video:kling-3-0",
    "generationId": "generation-id",
    "reservedCredits": 20,
    "taskId": "provider-task-id",
    "state": "queued"
  }
}
```

## 2. 查询任务状态

### 接口

```http
GET https://localhost:3000/api/ai-studio/tasks/{taskId}
Authorization: Bearer YOUR_API_KEY
```

### 成功响应

```json
{
  "success": true,
  "data": {
    "generationId": "generation-id",
    "taskId": "provider-task-id",
    "modelId": "video:kling-3-0",
    "state": "succeeded",
    "mediaUrls": [
      "https://example.com/result.mp4"
    ],
    "reservedCredits": 20,
    "refundedCredits": 0
  }
}
```

## 请求字段

### Kling 3.0

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 否 | `"kling-3.0"` | kling-3.0 | The model name to use for generation. Required field. - Must be `kling-3.0` for this endpoint |
| `input` | object | 否 | `-` | - | - |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `-` | - | Text prompt describing the video to generate. |
| `image_urls` | string[] | 否 | `-` | - | Optional first-frame or ending-frame reference images. |
| `sound` | boolean | 否 | `true` | - | Whether to generate sound effects. |
| `duration` | enum | 否 | `"5"` | 5, 10 | Video duration in seconds. |
| `aspect_ratio` | enum | 否 | `"16:9"` | 16:9, 9:16, 1:1 | Output aspect ratio. |
| `mode` | enum | 否 | `"std"` | std, pro | Generation mode. |
| `multi_shots` | boolean | 否 | `false` | - | Enable multi-shot generation mode. |

### Kling 3.0 Motion Control

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling-3.0/motion-control"` | kling-3.0/motion-control | The model name to use for generation. Required field. - Must be `kling-3.0/motion-control` for this endpoint |
| `input` | object | 是 | `-` | - | - |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 否 | `-` | - | (Optional) Text prompt words, used to guide the generation of animation content. Can be empty or 0 - 2500 characters long. |
| `input_urls` | string[] | 是 | `-` | - | (Required) Include a URL of an image |
| `video_urls` | string[] | 是 | `-` | - | (Required) Include a video URL |
| `mode` | string | 否 | `-` | - | (Optional) Video Quality Mode. std: Standard Mode (720p). pro: Professional Mode (1080p) |
| `character_orientation` | string | 否 | `-` | - | (Optional) Reference source for character orientation. video: Refer to video (recommended); image: Refer to image. Default value: video |
| `background_source` | string | 否 | `-` | - | (Optional) Background source. input_video: Use video background; input_image: Use image background. Default value: input_video |

### Kling V3 Turbo Text to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling/v3-turbo-text-to-video"` | kling/v3-turbo-text-to-video | The model name to use for generation. Required field. - Must be `kling/v3-turbo-text-to-video` for this endpoint |
| `input` | object | 是 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"Outdoor terrace of a European villa, by a dining table with a blue and white checkered tablecloth, a young white woman in a blue and white striped short-sleeve shirt and khaki shorts, with a brown belt, sits barefoot, opposite a young white man in a white T-shirt.The camera zooms in, the woman swirls the juice in a glass, her eyes looking at the distant woods, and says, \"These trees will turn yellow in a month, won't they?\"Close-up of the man, he lowers his head and says, \"But they'll be green again next summer.\"Then the woman turns her head, smiles at the man opposite, and says, \"Are you always this optimistic? Or just about summer?\"Then the man lifts his head, looks at the woman and says, \"Only about summers with you.\""` | - | The text description of the video you want to generate (Max length: 2500 characters) |
| `duration` | number | 是 | `5` | - | Video duration in seconds. |
| `aspect_ratio` | enum | 是 | `"16:9"` | 1:1, 9:16, 16:9 | The aspect ratio of the generated video frame |
| `resolution` | enum | 是 | `"720p"` | 720p, 1080p | Resolution of the generated video (720p or 1080p) |

### Kling V3 Turbo Image to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling/v3-turbo-image-to-video"` | kling/v3-turbo-image-to-video | The model name to use for generation. Required field. - Must be `kling/v3-turbo-image-to-video` for this endpoint |
| `input` | object | 是 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"Outdoor terrace of a European villa, by a dining table with a blue and white checkered tablecloth, a young white woman in a blue and white striped short-sleeve shirt and khaki shorts, with a brown belt, sits barefoot, opposite a young white man in a white T-shirt.The camera zooms in, the woman swirls the juice in a glass, her eyes looking at the distant woods, and says, \"These trees will turn yellow in a month, won't they?\"Close-up of the man, he lowers his head and says, \"But they'll be green again next summer.\"Then the woman turns her head, smiles at the man opposite, and says, \"Are you always this optimistic? Or just about summer?\"Then the man lifts his head, looks at the woman and says, \"Only about summers with you.\""` | - | The text prompt describing the video to generate (Max length: 2500 characters) |
| `image_urls` | string[] | 是 | `["https://static.aiquickdraw.com/tools/example/1770688028208_jxcvxCQm.png"]` | - | URL of the image to be used for the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB) |
| `duration` | number | 是 | `5` | - | Video duration in seconds. |
| `resolution` | enum | 是 | `"720p"` | 720p, 1080p | Resolution of the generated video (720p or 1080p) |

### Kling 2.6 Text to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling-2.6/text-to-video"` | kling-2.6/text-to-video | Name of the model used for the generation task. Required field. - This endpoint must use the `kling-2.6/text-to-video` model |
| `input` | object | 否 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"Scene: A fashion live-streaming sales setting, with clothes hanging on racks and the host's figure reflected in a full-length mirror. Lines: [African female host] turns around to showcase the hoodie's cut. [African female host, in a cheerful tone] says: \"360-degree flawless tailoring, slimming and versatile.\" She then [African female host] leans closer to the camera. [African female host, in a lively tone] says: \"Double-sided fleece fabric, $30 off immediately when you order now.\""` | - | Text prompt for video generation (maximum length: 1000 characters) |
| `sound` | boolean | 是 | `false` | - | This parameter specifies whether the generated video contains sound (boolean: true/false) |
| `aspect_ratio` | enum | 是 | `"1:1"` | 1:1, 16:9, 9:16 | This parameter defines the video aspect ratio |
| `duration` | enum | 是 | `"5"` | 5, 10 | Video duration (unit: seconds) |

### Kling 2.6 Image to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling-2.6/image-to-video"` | kling-2.6/image-to-video | Name of the model used for the generation task. Required field. - This endpoint must use the `kling-2.6/image-to-video` model |
| `input` | object | 否 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"In a bright rehearsal room, sunlight streams through the windows, and a standing microphone is placed in the center of the room. [Campus band female lead singer] stands in front of the microphone with her eyes closed, and other members stand around her. [Campus band female lead singer, singing loudly] Lead vocal: \"I will do my best to heal you, with all my heart and soul...\" The background is a cappella harmonies, and the camera slowly pans around the band members."` | - | Text prompt for video generation (maximum length: 1000 characters) |
| `image_urls` | string[] | 是 | `["https://static.aiquickdraw.com/tools/example/1764851002741_i0lEiI8I.png"]` | - | Image URLs for video generation. (Uploaded file URLs, not file content; supported types: image/jpeg, image/png; maximum file size: 10.0MB) |
| `sound` | boolean | 是 | `false` | - | This parameter specifies whether the generated video contains sound (boolean: true/false) |
| `duration` | enum | 是 | `"5"` | 5, 10 | Video duration (unit: seconds) |

### Kling 2.6 Motion Control

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling-2.6/motion-control"` | kling-2.6/motion-control | The model name to use for generation. Required field. - Must be `kling-2.6/motion-control` for this endpoint |
| `input` | object | 否 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 否 | `"The cartoon character is dancing."` | - | A text description of the desired output. Maximum length is 2500 characters. (Max length: 2500 characters) |
| `input_urls` | string[] | 是 | `["https://static.aiquickdraw.com/tools/example/1767694885407_pObJoMcy.png"]` | - | An array containing a single image URL. The photo must clearly show the subject's head, shoulders, and torso. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/jpg; Max size: 10.0MB,size needs to be greater than 300px, aspect ratio 2:5 to 5:2.) |
| `video_urls` | string[] | 是 | `["https://static.aiquickdraw.com/tools/example/1767525918769_QyvTNib2.mp4"]` | - | An array containing a single video URL. The duration must be between 3 to 30 seconds, and the video must clearly show the subject's head, shoulders, and torso. (File URL after upload, not file content; Accepted types: video/mp4, video/quicktime, video/x-matroska; Max size: 100.0MB) |
| `character_orientation` | enum | 是 | `"video"` | image, video | Generate the orientation of the characters in the video. 'image': same orientation as the person in the picture (max 10s video). 'video': consistent with the orientation of the characters in the video (max 30s video). |
| `mode` | enum | 是 | `"720p"` | 720p, 1080p | Output resolution mode. Use 'std' for 720p or 'pro' for 1080p. |

### Kling 2.5 Turbo Text to Video Pro

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling/v2-5-turbo-text-to-video-pro"` | kling/v2-5-turbo-text-to-video-pro | The model name to use for generation. Required field. - Must be `kling/v2-5-turbo-text-to-video-pro` for this endpoint |
| `input` | object | 否 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"Real-time playback. Wide shot of a ruined city: collapsed towers, fires blazing, storm clouds with lightning. Camera drops fast from the sky over burning streets and tilted buildings. Smoke and dust fill the air. A lone hero walks out of the ruins, silhouetted by fire. Camera shifts front: his face is dirty with dust and sweat, eyes firm, a faint smile. Wind blows, debris rises. Extreme close-up: his eyes reflect the approaching enemy. Music and drums hit. Final wide shot: fire forms a blazing halo behind him — reborn in flames with epic cinematic vibe."` | - | The text description of the video you want to generate (Max length: 2500 characters) |
| `duration` | enum | 否 | `"5"` | 5, 10 | The duration of the generated video in seconds |
| `aspect_ratio` | enum | 否 | `"16:9"` | 16:9, 9:16, 1:1 | The aspect ratio of the generated video frame |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | Things to avoid in the generated video (Max length: 2500 characters) |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) |

### Kling 2.5 Turbo Image to Video Pro

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling/v2-5-turbo-image-to-video-pro"` | kling/v2-5-turbo-image-to-video-pro | The model name to use for generation. Required field. - Must be `kling/v2-5-turbo-image-to-video-pro` for this endpoint |
| `input` | object | 否 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"A team of paratroopers descends into enemy territory, as they pass through clouds, the camera switches to a slow pan above the battlefield lighting up with"` | - | The text prompt describing the video to generate (Max length: 2500 characters) |
| `image_url` | string | 是 | `"https://file.aiquickdraw.com/custom-page/akr/section-images/1755256297923kmjpynul.png"` | - | URL of the image to be used for the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB) |
| `tail_image_url` | string | 否 | `"https://file.aiquickdraw.com/custom-page/akr/section-images/1755256297923kmjpynul.png"` | - | Tail frame image of video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB) |
| `duration` | enum | 否 | `"5"` | 5, 10 | The duration of the generated video in seconds |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | Negative prompt to exclude certain elements from the video (Max length: 500 characters) |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) |

### Kling V2.1 Master Text to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling/v2-1-master-text-to-video"` | kling/v2-1-master-text-to-video | The model name to use for generation. Required field. - Must be `kling/v2-1-master-text-to-video` for this endpoint |
| `input` | object | 否 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"First-person view from a soldier jumping from a transport plane — the camera shakes with turbulence, oxygen mask reflections flicker — as the clouds part, the battlefield below pulses with anti-air fire and missile trails."` | - | The text prompt describing the video you want to generate (Max length: 5000 characters) |
| `duration` | enum | 否 | `"5"` | 5, 10 | The duration of the generated video in seconds |
| `aspect_ratio` | enum | 否 | `"16:9"` | 16:9, 9:16, 1:1 | The aspect ratio of the generated video frame |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | Elements to avoid in the generated video (Max length: 500 characters) |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) |

### Kling V2.1 Master Image to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling/v2-1-master-image-to-video"` | kling/v2-1-master-image-to-video | The model name to use for generation. Required field. - Must be `kling/v2-1-master-image-to-video` for this endpoint |
| `input` | object | 否 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"A team of paratroopers descends into enemy territory, as they pass through clouds, the camera switches to a slow pan above the battlefield lighting up with"` | - | The text prompt describing the video to generate (Max length: 5000 characters) |
| `image_url` | string | 是 | `"https://file.aiquickdraw.com/custom-page/akr/section-images/1755256297923kmjpynul.png"` | - | URL of the image to be used for the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB) |
| `duration` | enum | 否 | `"5"` | 5, 10 | The duration of the generated video in seconds |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | Negative prompt to exclude certain elements from the video (Max length: 500 characters) |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) |

### Kling V2.1 Pro

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling/v2-1-pro"` | kling/v2-1-pro | The model name to use for generation. Required field. - Must be `kling/v2-1-pro` for this endpoint |
| `input` | object | 否 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"POV shot of a gravity surfer diving between ancient ruins suspended midair, glowing moss lights the path, the board hisses as it carves through thin mist, echoes rise with speed"` | - | Text prompt describing the video to generate (Max length: 5000 characters) |
| `image_url` | string | 是 | `"https://file.aiquickdraw.com/custom-page/akr/section-images/1754892534386c8wt0qfs.webp"` | - | URL of the image to be used for the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB) |
| `duration` | enum | 否 | `"5"` | 5, 10 | The duration of the generated video in seconds |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | Terms to avoid in the generated video (Max length: 500 characters) |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) |
| `tail_image_url` | string | 否 | `""` | - | URL of the image to be used for the end of the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB) |

### Kling V2.1 Standard

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling/v2-1-standard"` | kling/v2-1-standard | The model name to use for generation. Required field. - Must be `kling/v2-1-standard` for this endpoint |
| `input` | object | 否 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"Begin with the uploaded image as the first frame. Gradually animate the scene: steam rises and drifts upward from the train; lantern lights flicker subtly; cloaked figures begin to move slowly — walking, turning, adjusting their belongings. Floating dust or magical particles catch the light. The text “KLING 2.1 STANDARD API — Now on AI Studio” softly pulses with a golden glow. The camera pushes forward slightly, then slowly fades to black."` | - | Text prompt describing the desired video content (Max length: 5000 characters) |
| `image_url` | string | 是 | `"https://file.aiquickdraw.com/custom-page/akr/section-images/1755256596169mkkwr2ag.webp"` | - | URL of the image to be used for the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB) |
| `duration` | enum | 否 | `"5"` | 5, 10 | The duration of the generated video in seconds |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | Description of elements to avoid in the generated video (Max length: 500 characters) |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) |

### Kling AI Avatar Standard

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling/ai-avatar-standard"` | kling/ai-avatar-standard | The model name to use for generation. Required field. - Must be `kling/ai-avatar-standard` for this endpoint |
| `input` | object | 否 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `image_url` | string | 是 | `"https://file.aiquickdraw.com/custom-page/akr/section-images/17579268936223zs9l3dt.png"` | - | The URL of the image to use as your avatar (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB) |
| `audio_url` | string | 是 | `"https://file.aiquickdraw.com/custom-page/akr/section-images/17579258340109gghun47.mp3"` | - | The URL of the audio file (must be the URL of the uploaded file, not the file content; supported formats: audio/mpeg, audio/wav, audio/x-wav, audio/aac, audio/mp4, audio/ogg; audio size is limited to 100M, and the duration cannot exceed 5 minutes) |
| `prompt` | string | 是 | `""` | - | The prompt to use for the video generation (Max length: 5000 characters) |

### Kling AI Avatar Pro

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `model` | enum | 是 | `"kling/ai-avatar-pro"` | kling/ai-avatar-pro | The model name to use for generation. Required field. - Must be `kling/ai-avatar-pro` for this endpoint |
| `input` | object | 否 | `-` | - | Input parameters for the generation task |

#### input 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `image_url` | string | 是 | `"https://file.aiquickdraw.com/custom-page/akr/section-images/175792685809077e8h8k3.png"` | - | The URL of the image to use as your avatar (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB) |
| `audio_url` | string | 是 | `"https://file.aiquickdraw.com/custom-page/akr/section-images/1757925802302srqfkcqh.mp3"` | - | The URL of the audio file (must be the URL of the uploaded file, not the file content; supported formats: audio/mpeg, audio/wav, audio/x-wav, audio/aac, audio/mp4, audio/ogg; audio size is limited to 100M, and the duration cannot exceed 5 minutes) |
| `prompt` | string | 是 | `""` | - | The prompt to use for the video generation (Max length: 5000 characters) |

### Kling v3 Pro Text to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | object | 否 | `"Close-up of glowing fireflies dancing in a dark forest at twilight. Soft bioluminescent particles float through the air. Shallow depth of field, bokeh lights in background. Magical atmosphere, gentle movement."` | - | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |
| `duration` | enum | 否 | `"5"` | 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | The duration of the generated video in seconds |
| `multi_prompt` | object | 否 | `null` | - | List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations. |
| `shot_type` | enum | 否 | `"customize"` | customize, intelligent | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | - |
| `aspect_ratio` | enum | 否 | `"16:9"` | 16:9, 9:16, 1:1 | The aspect ratio of the generated video frame |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |

#### input 字段

_该模型暂无字段配置。_

### Kling v3 Standard Text to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | object | 否 | `"Cinematic drone shot flying through ancient stone ruins covered in moss and vines at golden hour. Camera starts low, rises through crumbling archways, revealing a vast misty valley beyond. Volumetric light rays pierce through gaps in the stone. Epic scale, photorealistic, 8K quality."` | - | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |
| `duration` | enum | 否 | `"5"` | 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | The duration of the generated video in seconds |
| `multi_prompt` | object | 否 | `null` | - | List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations. |
| `shot_type` | enum | 否 | `"customize"` | customize, intelligent | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | - |
| `aspect_ratio` | enum | 否 | `"16:9"` | 16:9, 9:16, 1:1 | The aspect ratio of the generated video frame |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |

#### input 字段

_该模型暂无字段配置。_

### Kling v3 Pro Image to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |
| `duration` | enum | 否 | `"5"` | 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | The duration of the generated video in seconds |
| `multi_prompt` | object | 否 | `null` | - | List of prompts for multi-shot video generation. If provided, divides the video into multiple shots. |
| `shot_type` | enum | 否 | `"customize"` | customize, intelligent | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| `end_image_url` | object | 否 | `-` | - | URL of the image to be used for the end of the video |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | - |
| `elements` | object | 否 | `[{"frontal_image_url":"https://v3b.fal.media/files/b/0a8cfd5f/-kZL-ha3Iuelku5IHXC-A_glasses.png","reference_image_urls":["https://v3b.fal.media/files/b/0a8cfd62/psPCmzrD1y9vDgdyNfKAL_glasses_back.png"]},{"video_url":"https://v3b.fal.media/files/b/0a8cfd66/b03SOiQvKLlFx_jqdNZ9z_child_video.mp4"}]` | - | Elements (characters/objects) to include in the video. Each example can either be an image set (frontal + reference images) or a video. Reference in prompt as @Element1, @Element2, etc. |
| `start_image_url` | string | 是 | `"https://storage.googleapis.com/falserverless/example_inputs/kling-v3/pro-i2v/start_image.png"` | - | URL of the image to be used for the video |
| `prompt` | object | 否 | `"The craftsman slowly examines the bowl, turning it gently in his weathered hands. His eyes reflect years of wisdom. Subtle smile forms on his face. Dust particles drift in warm light. Breathing motion, blinking eyes."` | - | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |

#### input 字段

_该模型暂无字段配置。_

### Kling v3 Standard Image to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |
| `duration` | enum | 否 | `"5"` | 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | The duration of the generated video in seconds |
| `multi_prompt` | object | 否 | `null` | - | List of prompts for multi-shot video generation. If provided, divides the video into multiple shots. |
| `shot_type` | enum | 否 | `"customize"` | customize, intelligent | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| `end_image_url` | object | 否 | `-` | - | URL of the image to be used for the end of the video |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | - |
| `elements` | object | 否 | `[{"frontal_image_url":"https://v3b.fal.media/files/b/0a8cfd5f/-kZL-ha3Iuelku5IHXC-A_glasses.png","reference_image_urls":["https://v3b.fal.media/files/b/0a8cfd62/psPCmzrD1y9vDgdyNfKAL_glasses_back.png"]},{"video_url":"https://v3b.fal.media/files/b/0a8cfd66/b03SOiQvKLlFx_jqdNZ9z_child_video.mp4"}]` | - | Elements (characters/objects) to include in the video. Each example can either be an image set (frontal + reference images) or a video. Reference in prompt as @Element1, @Element2, etc. |
| `start_image_url` | string | 是 | `"https://storage.googleapis.com/falserverless/example_inputs/kling-v3/standard-i2v/start_image.png"` | - | URL of the image to be used for the video |
| `prompt` | object | 否 | `"Camera slowly orbits around the vase. Soft light shifts across the ceramic surface. The pampas grass sways gently. Shadows move elegantly. Smooth continuous motion, premium feel."` | - | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |

#### input 字段

_该模型暂无字段配置。_

### Kling v3 4K Image to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |
| `duration` | enum | 否 | `"5"` | 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | The duration of the generated video in seconds |
| `multi_prompt` | object | 否 | `null` | - | List of prompts for multi-shot video generation. If provided, divides the video into multiple shots. |
| `shot_type` | enum | 否 | `"customize"` | customize, intelligent | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| `end_image_url` | object | 否 | `-` | - | URL of the image to be used for the end of the video |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | - |
| `elements` | object | 否 | `[{"frontal_image_url":"https://v3b.fal.media/files/b/0a8cfd5f/-kZL-ha3Iuelku5IHXC-A_glasses.png","reference_image_urls":["https://v3b.fal.media/files/b/0a8cfd62/psPCmzrD1y9vDgdyNfKAL_glasses_back.png"]},{"video_url":"https://v3b.fal.media/files/b/0a8cfd66/b03SOiQvKLlFx_jqdNZ9z_child_video.mp4"}]` | - | Elements (characters/objects) to include in the video. Each example can either be an image set (frontal + reference images) or a video. Reference in prompt as @Element1, @Element2, etc. |
| `start_image_url` | string | 是 | `"https://storage.googleapis.com/falserverless/example_inputs/kling-v3/pro-i2v/start_image.png"` | - | URL of the image to be used for the video |
| `prompt` | object | 否 | `"The craftsman slowly examines the bowl, turning it gently in his weathered hands. His eyes reflect years of wisdom. Subtle smile forms on his face. Dust particles drift in warm light. Breathing motion, blinking eyes."` | - | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |

#### input 字段

_该模型暂无字段配置。_

### Kling v3 4K Text to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | object | 否 | `"Close-up of glowing fireflies dancing in a dark forest at twilight. Soft bioluminescent particles float through the air. Shallow depth of field, bokeh lights in background. Magical atmosphere, gentle movement."` | - | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. |
| `duration` | enum | 否 | `"5"` | 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | The duration of the generated video in seconds |
| `multi_prompt` | object | 否 | `null` | - | List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations. |
| `shot_type` | enum | 否 | `"customize"` | customize, intelligent | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | - |
| `aspect_ratio` | enum | 否 | `"16:9"` | 16:9, 9:16, 1:1 | The aspect ratio of the generated video frame |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |

#### input 字段

_该模型暂无字段配置。_

### Kling O1 Image to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `end_image_url` | object | 否 | `"https://v3b.fal.media/files/b/tiger/BwHi22qoQnqaTNMMhe533.png"` | - | Image to use as the last frame of the video. |
| `duration` | enum | 否 | `"5"` | 3, 4, 5, 6, 7, 8, 9, 10 | Video duration in seconds. |
| `start_image_url` | string | 是 | `"https://v3b.fal.media/files/b/rabbit/NaslJIC7F2WodS6DFZRRJ.png"` | - | Image to use as the first frame of the video. Max file size: 10.0MB, Min width: 300px, Min height: 300px, Min aspect ratio: 0.40, Max aspect ratio: 2.50, Timeout: 20.0s |
| `prompt` | string | 是 | `"Create a magical timelapse transition. The snow melts rapidly to reveal green grass, and the tree branches burst into bloom with pink flowers in real-time. The lighting shifts from cold winter light to warm spring sunshine. The camera pushes in slowly towards the tree. Disney-style magical transformation, cinematic, 8k."` | - | Use @Image1 to reference the start frame, @Image2 to reference the end frame. |

#### input 字段

_该模型暂无字段配置。_

### Kling v2.6 Pro Text to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | - |
| `duration` | enum | 否 | `"5"` | 5, 10 | The duration of the generated video in seconds |
| `aspect_ratio` | enum | 否 | `"16:9"` | 16:9, 9:16, 1:1 | The aspect ratio of the generated video frame |
| `cfg_scale` | number | 否 | `0.5` | - | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| `prompt` | string | 是 | `"Old friends reuniting at a train station after 20 years, one exclaims 'Is that really you?!' other tearfully replies 'I promised I'd come back, didn't I?', train whistle, steam hissing, emotional orchestral swell, crowd murmur"` | - | - |

#### input 字段

_该模型暂无字段配置。_

### Kling v2.6 Pro Image to Video

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | 是 | `"A king walks slowly and says \"My people, here I am! I am here to save you all\""` | - | - |
| `negative_prompt` | string | 否 | `"blur, distort, and low quality"` | - | - |
| `voice_ids` | object | 否 | `-` | - | Optional Voice IDs for video generation. Reference voices in your prompt with <<<voice_1>>> and <<<voice_2>>> (maximum 2 voices per task). Get voice IDs from the kling video create-voice endpoint: https://fal.ai/models/fal-ai/kling-video/create-voice |
| `duration` | enum | 否 | `"5"` | 5, 10 | The duration of the generated video in seconds |
| `end_image_url` | object | 否 | `-` | - | URL of the image to be used for the end of the video |
| `start_image_url` | string | 是 | `"https://v3b.fal.media/files/b/0a84ab29/BSJXz9Ht-jgRgMf4IGxLU_upscaled.png"` | - | URL of the image to be used for the video |
| `generate_audio` | boolean | 否 | `true` | - | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. |

#### input 字段

_该模型暂无字段配置。_

### Kling v2.6 Motion Control

#### Payload 字段

| 字段 | 类型 | 必填 | 默认值 / 示例 | 可选值 | 说明 |
| --- | --- | --- | --- | --- | --- |
| `character_orientation` | enum | 是 | `"video"` | image, video | Controls whether the output character's orientation matches the reference image or video. 'video': orientation matches reference video - better for complex motions (max 30s). 'image': orientation matches reference image - better for following camera movements (max 10s). |
| `video_url` | string | 是 | `"https://v3b.fal.media/files/b/0a8752bc/2xrNS217ngQ3wzXqA7LXr_output.mp4"` | - | Reference video URL. The character actions in the generated video will be consistent with this reference video. Should contain a realistic style character with entire body or upper body visible, including head, without obstruction. Duration limit depends on character_orientation: 10s max for 'image', 30s max for 'video'. |
| `image_url` | string | 是 | `"https://v3b.fal.media/files/b/0a875302/8NaxQrQxDNHppHtqcchMm.png"` | - | Reference image URL. The characters, backgrounds, and other elements in the generated video are based on this reference image. Characters should have clear body proportions, avoid occlusion, and occupy more than 5% of the image area. |
| `keep_original_sound` | boolean | 否 | `true` | - | Whether to keep the original sound from the reference video. |
| `prompt` | object | 否 | `"An african american woman dancing"` | - | - |

#### input 字段

_该模型暂无字段配置。_

## 价格

创建生成任务时会预扣积分。创建任务响应中的 `reservedCredits` 是本次请求最终预留的积分数量。

| 模型 | 类型 | 规格 | 价格 | 计费方式 |
| --- | --- | --- | --- | --- |
| Kling 3.0 | 文/图生视频 | std | 14 积分/秒 | 输出秒数 × 14 |
| Kling 3.0 | 文/图生视频 | std | 20 积分/秒 | 输出秒数 × 20 |
| Kling 3.0 | 文/图生视频 | pro | 18 积分/秒 | 输出秒数 × 18 |
| Kling 3.0 | 文/图生视频 | pro | 27 积分/秒 | 输出秒数 × 27 |
| Kling 3.0 Motion Control | 文/图生视频 | 720p | 20 积分/秒 | 输出秒数 × 20 |
| Kling 3.0 Motion Control | 文/图生视频 | 1080p | 27 积分/秒 | 输出秒数 × 27 |
| Kling V3 Turbo Text to Video | 文生视频 | 720p | 18 积分/秒 | 输出秒数 × 18 |
| Kling V3 Turbo Text to Video | 文生视频 | 1080p | 22.5 积分/秒 | 输出秒数 × 22.5 |
| Kling V3 Turbo Image to Video | 图生视频 | 720p | 18 积分/秒 | 输出秒数 × 18 |
| Kling V3 Turbo Image to Video | 图生视频 | 1080p | 22.5 积分/秒 | 输出秒数 × 22.5 |
| Kling 2.6 Text to Video | 文生视频 | 5 | 55 积分 | 单次生成固定价格 |
| Kling 2.6 Text to Video | 文生视频 | 10 | 110 积分 | 单次生成固定价格 |
| Kling 2.6 Text to Video | 文生视频 | 5 | 110 积分 | 单次生成固定价格 |
| Kling 2.6 Text to Video | 文生视频 | 10 | 220 积分 | 单次生成固定价格 |
| Kling 2.6 Image to Video | 图生视频 | 5 | 55 积分 | 单次生成固定价格 |
| Kling 2.6 Image to Video | 图生视频 | 10 | 110 积分 | 单次生成固定价格 |
| Kling 2.6 Image to Video | 图生视频 | 5 | 110 积分 | 单次生成固定价格 |
| Kling 2.6 Image to Video | 图生视频 | 10 | 220 积分 | 单次生成固定价格 |
| Kling 2.6 Motion Control | 文/图生视频 | 720p | 11 积分/秒 | 输出秒数 × 11 |
| Kling 2.6 Motion Control | 文/图生视频 | 1080p | 18 积分/秒 | 输出秒数 × 18 |
| Kling 2.5 Turbo Text to Video Pro | 文生视频 | 5 | 42 积分 | 单次生成固定价格 |
| Kling 2.5 Turbo Text to Video Pro | 文生视频 | 10 | 84 积分 | 单次生成固定价格 |
| Kling 2.5 Turbo Image to Video Pro | 图生视频 | 5 | 42 积分 | 单次生成固定价格 |
| Kling 2.5 Turbo Image to Video Pro | 图生视频 | 10 | 84 积分 | 单次生成固定价格 |
| Kling V2.1 Master Text to Video | 文生视频 | 5 | 160 积分 | 单次生成固定价格 |
| Kling V2.1 Master Text to Video | 文生视频 | 10 | 320 积分 | 单次生成固定价格 |
| Kling V2.1 Master Image to Video | 图生视频 | 5 | 160 积分 | 单次生成固定价格 |
| Kling V2.1 Master Image to Video | 图生视频 | 10 | 320 积分 | 单次生成固定价格 |
| Kling V2.1 Pro | 文/图生视频 | 5 | 50 积分 | 单次生成固定价格 |
| Kling V2.1 Pro | 文/图生视频 | 10 | 100 积分 | 单次生成固定价格 |
| Kling V2.1 Standard | 文/图生视频 | 5 | 25 积分 | 单次生成固定价格 |
| Kling V2.1 Standard | 文/图生视频 | 10 | 50 积分 | 单次生成固定价格 |
| Kling AI Avatar Standard | 文/图生视频 | - | 8 积分/秒 | 输出秒数 × 8 |
| Kling AI Avatar Pro | 文/图生视频 | - | 16 积分/秒 | 输出秒数 × 16 |
| Kling v3 Pro Text to Video | 文生视频 | false | 22 积分/秒 | 输出秒数 × 22 |
| Kling v3 Pro Text to Video | 文生视频 | true | 34 积分/秒 | 输出秒数 × 34 |
| Kling v3 Standard Text to Video | 文生视频 | false | 17 积分/秒 | 输出秒数 × 17 |
| Kling v3 Standard Text to Video | 文生视频 | true | 25 积分/秒 | 输出秒数 × 25 |
| Kling v3 Pro Image to Video | 图生视频 | false | 22 积分/秒 | 输出秒数 × 22 |
| Kling v3 Pro Image to Video | 图生视频 | true | 34 积分/秒 | 输出秒数 × 34 |
| Kling v3 Standard Image to Video | 图生视频 | false | 17 积分/秒 | 输出秒数 × 17 |
| Kling v3 Standard Image to Video | 图生视频 | true | 25 积分/秒 | 输出秒数 × 25 |
| Kling v3 4K Image to Video | 图生视频 | - | 84 积分/秒 | 输出秒数 × 84 |
| Kling v3 4K Text to Video | 文生视频 | - | 84 积分/秒 | 输出秒数 × 84 |
| Kling O1 Image to Video | 图生视频 | - | 22 积分/秒 | 输出秒数 × 22 |
| Kling v2.6 Pro Text to Video | 文生视频 | false | 14 积分/秒 | 输出秒数 × 14 |
| Kling v2.6 Pro Text to Video | 文生视频 | true | 28 积分/秒 | 输出秒数 × 28 |
| Kling v2.6 Pro Image to Video | 图生视频 | false | 14 积分/秒 | 输出秒数 × 14 |
| Kling v2.6 Pro Image to Video | 图生视频 | true | 28 积分/秒 | 输出秒数 × 28 |
| Kling v2.6 Motion Control | 文/图生视频 | - | 14 积分/秒 | 输出秒数 × 14 |

## 常见错误

| 状态 | 含义 |
| --- | --- |
| `400` | Invalid request payload |
| `401` | Missing or invalid API key |
| `402` | Insufficient credits or plan limit |
| `404` | Model or task not found |
| `429` | Rate limit exceeded |
| `500` | Server error |