# Veo 3.1 API ドキュメント

> AI Studio API で Veo 3.1 モデルを使用して動画を生成します。

## 概要

AI Studio API を使用して Veo 3.1 の生成タスクを作成し、タスク状態を確認します。処理は非同期です。まずタスクを作成して `taskId` を取得し、その後タスク API で結果を確認します。

## 認証

すべてのリクエストで `Authorization` ヘッダーに API Key が必要です。

```http
Authorization: Bearer YOUR_API_KEY
```

## 利用可能なモデル

| modelId | バージョン | プロバイダー | 実行モデル |
| --- | --- | --- | --- |
| `video:veo-3.1-lite` | Veo 3.1 Lite | Generate Veo3.1 Video | veo3_lite |
| `video:veo-3.1-fast` | Veo 3.1 Fast | Generate Veo3.1 Video | veo3_fast |
| `video:veo-3.1-quality` | Veo 3.1 Quality | Generate Veo3.1 Video | veo3 |
| `video:extend-veo3-1-video` | Veo 3.1 Extend | Extend Veo3.1 Video | fast, quality, lite |
| `video:get-veo3-1-1080p-video` | Veo 3.1 Get 1080P | Get 1080P Video |  |
| `video:get-veo3-1-4k-video` | Veo 3.1 Get 4K | Get 4K Video |  |
| `video:fal-fal-ai-veo3-1` | Veo 3.1 | veo3.1 | fal-ai/veo3.1 |
| `video:fal-fal-ai-veo3-1-fast` | Veo 3.1 Fast | veo3.1 | fal-ai/veo3.1/fast |
| `video:fal-fal-ai-veo3-1-image-to-video` | Veo 3.1 Image to Video | veo3.1 | fal-ai/veo3.1/image-to-video |
| `video:fal-fal-ai-veo3-1-fast-image-to-video` | Veo 3.1 Fast Image to Video | veo3.1 | fal-ai/veo3.1/fast/image-to-video |
| `video:fal-fal-ai-veo3` | Veo 3 | veo3 | fal-ai/veo3 |
| `video:fal-fal-ai-veo3-fast` | Veo 3 Fast | veo3 | fal-ai/veo3/fast |

## 1. 生成タスクを作成

### エンドポイント

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

### リクエスト例

```json
{
  "modelId": "video:veo-3.1-lite",
  "isPublic": true,
  "payload": {
    "prompt": "A dog playing in a park",
    "imageUrls": [
      "http://example.com/image1.jpg",
      "http://example.com/image2.jpg"
    ],
    "model": "veo3_lite",
    "watermark": "MyBrand",
    "aspect_ratio": "16:9",
    "enableFallback": false,
    "enableTranslation": true,
    "generationType": "REFERENCE_2_VIDEO",
    "resolution": "720p"
  }
}
```

### 成功レスポンス

```json
{
  "success": true,
  "data": {
    "modelId": "video:veo-3.1-lite",
    "generationId": "generation-id",
    "reservedCredits": 20,
    "taskId": "provider-task-id",
    "state": "queued"
  }
}
```

## 2. タスク状態を確認

### エンドポイント

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

### 成功レスポンス

```json
{
  "success": true,
  "data": {
    "generationId": "generation-id",
    "taskId": "provider-task-id",
    "modelId": "video:veo-3.1-lite",
    "state": "succeeded",
    "mediaUrls": [
      "https://example.com/result.mp4"
    ],
    "reservedCredits": 20,
    "refundedCredits": 0
  }
}
```

## リクエストフィールド

### Veo 3.1 Lite

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | はい | `"A dog playing in a park"` | - | Text prompt describing the desired video content. Required for all generation modes. - Should be detailed and specific in describing video content<br>- Can include actions, scenes, style and other information<br>- For image-to-video, describe how you want the image to come alive |
| `imageUrls` | string[] | いいえ | `["http://example.com/image1.jpg","http://example.com/image2.jpg"]` | - | Image URL list (used in image-to-video mode). Supports 1 or 2 images: - **1 image**: The generated video will unfold around this image, with the image content presented dynamically<br>- **2 images**: The first image serves as the video's first frame, and the second image serves as the video's last frame, with the video transitioning between them<br>- Must be valid image URLs<br>- Images must be accessible to the API server. |
| `model` | enum | いいえ | `"veo3_lite"` | veo3_lite | The model name to use for generation. Required field. - Must be `veo3_lite` for this endpoint |
| `generationType` | enum | いいえ | `"TEXT_2_VIDEO"` | TEXT_2_VIDEO, FIRST_AND_LAST_FRAMES_2_VIDEO, REFERENCE_2_VIDEO | Video generation mode (optional). Specifies different video generation approaches: - **TEXT_2_VIDEO**: Text-to-video - Generate videos using only text prompts<br>- **FIRST_AND_LAST_FRAMES_2_VIDEO**: First and last frames to video - Flexible image-to-video generation mode - 1 image: Generate video based on the provided image - 2 images: First image as first frame, second image as last frame, generating transition video<br>- **REFERENCE_2_VIDEO**: Reference-to-video - Generate videos based on reference images, requires 1-3 images in imageUrls (minimum 1, maximum 3) **Important Notes**:<br>- REFERENCE_2_VIDEO mode currently supports the veo3_fast and veo3_lite models.<br>- If not specified, the system will automatically determine the generation mode based on whether imageUrls are provided |
| `aspect_ratio` | enum | いいえ | `"16:9"` | 16:9, 9:16, Auto | Video aspect ratio. Specifies the dimension ratio of the generated video. Available options: - 16:9: Landscape video format. - 9:16: Portrait video format, suitable for mobile short videos<br>- Auto: In auto mode, the video will be automatically center-cropped based on whether your uploaded image is closer to 16:9 or 9:16. Default value is 16:9. |
| `enableFallback` | boolean | いいえ | `false` | - | Deprecated Enable fallback functionality. When set to true, if the official Veo3.1 video generation service is unavailable or encounters exceptions, the system will automatically switch to a backup model for video generation to ensure task continuity and reliability. Default value is false. - When fallback is enabled, backup model will be used for the following errors: - public error minor upload - Your prompt was flagged by Website as violating content policies - public error prominent people upload<br>- Fallback mode requires 16:9 aspect ratio and uses 1080p resolution by default<br>- **Note**: Videos generated through fallback mode cannot be accessed via the Get 1080P Video endpoint<br>- **Credit Consumption**: Successful fallback has different credit consumption, please see https://AI Studio/pricing for pricing details **Note: This parameter is deprecated. Please remove this parameter from your requests. The system has automatically optimized the content review mechanism without requiring manual fallback configuration.** |
| `enableTranslation` | boolean | いいえ | `false` | - | Enable prompt translation to English. When set to true, the system will automatically translate prompts to English before video generation for better generation results. Default value is true. - true: Enable translation, prompts will be automatically translated to English<br>- false: Disable translation, use original prompts directly for generation |
| `watermark` | string | いいえ | `"MyBrand"` | - | Watermark text. - Optional parameter<br>- If provided, a watermark will be added to the generated video |
| `resolution` | enum | いいえ | `"720p"` | 720p, 1080p, 4k | Output resolution. |
| `duration` | enum | いいえ | `8` | 4, 6, 8 | The duration of the generated video, in seconds. Optional values are 4, 6, 8.<br>**Important Note**:<br>- The REFERENCE_2_VIDEO mode currently only supports a duration of 8 seconds. |

#### input フィールド

_このモデルのフィールド設定はありません。_

### Veo 3.1 Fast

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | はい | `"A dog playing in a park"` | - | Text prompt describing the desired video content. Required for all generation modes. - Should be detailed and specific in describing video content<br>- Can include actions, scenes, style and other information<br>- For image-to-video, describe how you want the image to come alive |
| `imageUrls` | string[] | いいえ | `["http://example.com/image1.jpg","http://example.com/image2.jpg"]` | - | Image URL list (used in image-to-video mode). Supports 1 or 2 images: - **1 image**: The generated video will unfold around this image, with the image content presented dynamically<br>- **2 images**: The first image serves as the video's first frame, and the second image serves as the video's last frame, with the video transitioning between them<br>- Must be valid image URLs<br>- Images must be accessible to the API server. |
| `model` | enum | いいえ | `"veo3_fast"` | veo3_fast | The model name to use for generation. Required field. - Must be `veo3_fast` for this endpoint |
| `generationType` | enum | いいえ | `"TEXT_2_VIDEO"` | TEXT_2_VIDEO, FIRST_AND_LAST_FRAMES_2_VIDEO, REFERENCE_2_VIDEO | Video generation mode (optional). Specifies different video generation approaches: - **TEXT_2_VIDEO**: Text-to-video - Generate videos using only text prompts<br>- **FIRST_AND_LAST_FRAMES_2_VIDEO**: First and last frames to video - Flexible image-to-video generation mode - 1 image: Generate video based on the provided image - 2 images: First image as first frame, second image as last frame, generating transition video<br>- **REFERENCE_2_VIDEO**: Reference-to-video - Generate videos based on reference images, requires 1-3 images in imageUrls (minimum 1, maximum 3) **Important Notes**:<br>- REFERENCE_2_VIDEO mode currently supports the veo3_fast and veo3_lite models.<br>- If not specified, the system will automatically determine the generation mode based on whether imageUrls are provided |
| `aspect_ratio` | enum | いいえ | `"16:9"` | 16:9, 9:16, Auto | Video aspect ratio. Specifies the dimension ratio of the generated video. Available options: - 16:9: Landscape video format. - 9:16: Portrait video format, suitable for mobile short videos<br>- Auto: In auto mode, the video will be automatically center-cropped based on whether your uploaded image is closer to 16:9 or 9:16. Default value is 16:9. |
| `enableFallback` | boolean | いいえ | `false` | - | Deprecated Enable fallback functionality. When set to true, if the official Veo3.1 video generation service is unavailable or encounters exceptions, the system will automatically switch to a backup model for video generation to ensure task continuity and reliability. Default value is false. - When fallback is enabled, backup model will be used for the following errors: - public error minor upload - Your prompt was flagged by Website as violating content policies - public error prominent people upload<br>- Fallback mode requires 16:9 aspect ratio and uses 1080p resolution by default<br>- **Note**: Videos generated through fallback mode cannot be accessed via the Get 1080P Video endpoint<br>- **Credit Consumption**: Successful fallback has different credit consumption, please see https://AI Studio/pricing for pricing details **Note: This parameter is deprecated. Please remove this parameter from your requests. The system has automatically optimized the content review mechanism without requiring manual fallback configuration.** |
| `enableTranslation` | boolean | いいえ | `false` | - | Enable prompt translation to English. When set to true, the system will automatically translate prompts to English before video generation for better generation results. Default value is true. - true: Enable translation, prompts will be automatically translated to English<br>- false: Disable translation, use original prompts directly for generation |
| `watermark` | string | いいえ | `"MyBrand"` | - | Watermark text. - Optional parameter<br>- If provided, a watermark will be added to the generated video |
| `resolution` | enum | いいえ | `"720p"` | 720p, 1080p, 4k | Output resolution. |
| `duration` | enum | いいえ | `8` | 4, 6, 8 | The duration of the generated video, in seconds. Optional values are 4, 6, 8.<br>**Important Note**:<br>- The REFERENCE_2_VIDEO mode currently only supports a duration of 8 seconds. |

#### input フィールド

_このモデルのフィールド設定はありません。_

### Veo 3.1 Quality

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | はい | `"A dog playing in a park"` | - | Text prompt describing the desired video content. Required for all generation modes. - Should be detailed and specific in describing video content<br>- Can include actions, scenes, style and other information<br>- For image-to-video, describe how you want the image to come alive |
| `imageUrls` | string[] | いいえ | `["http://example.com/image1.jpg","http://example.com/image2.jpg"]` | - | Image URL list (used in image-to-video mode). Supports 1 or 2 images: - **1 image**: The generated video will unfold around this image, with the image content presented dynamically<br>- **2 images**: The first image serves as the video's first frame, and the second image serves as the video's last frame, with the video transitioning between them<br>- Must be valid image URLs<br>- Images must be accessible to the API server. |
| `model` | enum | いいえ | `"veo3"` | veo3 | The model name to use for generation. Required field. - Must be `veo3` for this endpoint |
| `generationType` | enum | いいえ | `"TEXT_2_VIDEO"` | TEXT_2_VIDEO, FIRST_AND_LAST_FRAMES_2_VIDEO, REFERENCE_2_VIDEO | Video generation mode (optional). Specifies different video generation approaches: - **TEXT_2_VIDEO**: Text-to-video - Generate videos using only text prompts<br>- **FIRST_AND_LAST_FRAMES_2_VIDEO**: First and last frames to video - Flexible image-to-video generation mode - 1 image: Generate video based on the provided image - 2 images: First image as first frame, second image as last frame, generating transition video<br>- **REFERENCE_2_VIDEO**: Reference-to-video - Generate videos based on reference images, requires 1-3 images in imageUrls (minimum 1, maximum 3) **Important Notes**:<br>- REFERENCE_2_VIDEO mode currently supports the veo3_fast and veo3_lite models.<br>- If not specified, the system will automatically determine the generation mode based on whether imageUrls are provided |
| `aspect_ratio` | enum | いいえ | `"16:9"` | 16:9, 9:16, Auto | Video aspect ratio. Specifies the dimension ratio of the generated video. Available options: - 16:9: Landscape video format. - 9:16: Portrait video format, suitable for mobile short videos<br>- Auto: In auto mode, the video will be automatically center-cropped based on whether your uploaded image is closer to 16:9 or 9:16. Default value is 16:9. |
| `enableFallback` | boolean | いいえ | `false` | - | Deprecated Enable fallback functionality. When set to true, if the official Veo3.1 video generation service is unavailable or encounters exceptions, the system will automatically switch to a backup model for video generation to ensure task continuity and reliability. Default value is false. - When fallback is enabled, backup model will be used for the following errors: - public error minor upload - Your prompt was flagged by Website as violating content policies - public error prominent people upload<br>- Fallback mode requires 16:9 aspect ratio and uses 1080p resolution by default<br>- **Note**: Videos generated through fallback mode cannot be accessed via the Get 1080P Video endpoint<br>- **Credit Consumption**: Successful fallback has different credit consumption, please see https://AI Studio/pricing for pricing details **Note: This parameter is deprecated. Please remove this parameter from your requests. The system has automatically optimized the content review mechanism without requiring manual fallback configuration.** |
| `enableTranslation` | boolean | いいえ | `false` | - | Enable prompt translation to English. When set to true, the system will automatically translate prompts to English before video generation for better generation results. Default value is true. - true: Enable translation, prompts will be automatically translated to English<br>- false: Disable translation, use original prompts directly for generation |
| `watermark` | string | いいえ | `"MyBrand"` | - | Watermark text. - Optional parameter<br>- If provided, a watermark will be added to the generated video |
| `resolution` | enum | いいえ | `"720p"` | 720p, 1080p, 4k | Output resolution. |
| `duration` | enum | いいえ | `8` | 4, 6, 8 | The duration of the generated video, in seconds. Optional values are 4, 6, 8.<br>**Important Note**:<br>- The REFERENCE_2_VIDEO mode currently only supports a duration of 8 seconds. |

#### input フィールド

_このモデルのフィールド設定はありません。_

### Veo 3.1 Extend

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `taskId` | string | はい | `"veo_task_abcdef123456"` | - | Task ID of the original video generation. Must be a valid taskId returned from the video generation interface. Note: Videos generated after 1080P generation cannot be extended. |
| `prompt` | string | はい | `"The dog continues running through the park, jumping over obstacles and playing with other dogs"` | - | Text prompt describing the extended video content. Should detail how you want the video to be extended, including actions, scene changes, style, etc. |
| `seeds` | number | いいえ | `12345` | - | Random seed parameter for controlling the randomness of generated content. Range: 10000-99999. Same seeds will generate similar video content, different seeds will generate different video content. If not specified, the system will automatically assign random seeds. |
| `model` | enum | いいえ | `"fast"` | fast, quality, lite | Model type for video extension (optional). Defaults to `fast` if not specified. - **fast**: Fast generation mode<br>- **quality**: High quality generation mode<br>- **lite**: Most cost-effective generation mode |
| `watermark` | string | いいえ | `"MyBrand"` | - | Watermark text (optional). If provided, a watermark will be added to the generated video. |

#### input フィールド

_このモデルのフィールド設定はありません。_

### Veo 3.1 Get 1080P

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `taskId` | string | はい | `"veo_task_abcdef123456"` | - | Task ID of the original successful Veo 3.1 generation. |
| `index` | number | いいえ | `0` | - | Video index. Defaults to 0 when omitted. |

#### input フィールド

_このモデルのフィールド設定はありません。_

### Veo 3.1 Get 4K

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `taskId` | string | はい | `"veo_task_abcdef123456"` | - | Task ID of the original successful Veo 3.1 generation. |
| `index` | number | いいえ | `0` | - | Video index. Defaults to 0 when omitted. |

#### input フィールド

_このモデルのフィールド設定はありません。_

### Veo 3.1

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `negative_prompt` | object | いいえ | `-` | - | A negative prompt to guide the video generation. |
| `seed` | object | いいえ | `-` | - | The seed for the random number generator. |
| `duration` | enum | いいえ | `"8s"` | 4s, 6s, 8s | The duration of the generated video. |
| `resolution` | enum | いいえ | `"720p"` | 720p, 1080p, 4k | The resolution of the generated video. |
| `auto_fix` | boolean | いいえ | `true` | - | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `aspect_ratio` | enum | いいえ | `"16:9"` | 16:9, 9:16 | Aspect ratio of the generated video |
| `safety_tolerance` | enum | いいえ | `"4"` | 1, 2, 3, 4, 5, 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. |
| `prompt` | string | はい | `"Two person street interview in New York City.\nSample Dialogue:\nHost: \"Did you hear the news?\"\nPerson: \"Yes! Veo 3.1 is now available on fal. If you want to see it, go check their website.\""` | - | The text prompt describing the video you want to generate |
| `generate_audio` | boolean | いいえ | `true` | - | Whether to generate audio for the video. |

#### input フィールド

_このモデルのフィールド設定はありません。_

### Veo 3.1 Fast

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `negative_prompt` | object | いいえ | `-` | - | A negative prompt to guide the video generation. |
| `seed` | object | いいえ | `-` | - | The seed for the random number generator. |
| `duration` | enum | いいえ | `"8s"` | 4s, 6s, 8s | The duration of the generated video. |
| `resolution` | enum | いいえ | `"720p"` | 720p, 1080p, 4k | The resolution of the generated video. |
| `auto_fix` | boolean | いいえ | `true` | - | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `aspect_ratio` | enum | いいえ | `"16:9"` | 16:9, 9:16 | Aspect ratio of the generated video |
| `safety_tolerance` | enum | いいえ | `"4"` | 1, 2, 3, 4, 5, 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. |
| `prompt` | string | はい | `"Two person street interview in New York City.\nSample Dialogue:\nHost: \"Did you hear the news?\"\nPerson: \"Yes! Veo 3.1 is now available on fal. If you want to see it, go check their website.\""` | - | The text prompt describing the video you want to generate |
| `generate_audio` | boolean | いいえ | `true` | - | Whether to generate audio for the video. |

#### input フィールド

_このモデルのフィールド設定はありません。_

### Veo 3.1 Image to Video

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `negative_prompt` | object | いいえ | `-` | - | A negative prompt to guide the video generation. |
| `seed` | object | いいえ | `-` | - | The seed for the random number generator. |
| `duration` | enum | いいえ | `"8s"` | 4s, 6s, 8s | The duration of the generated video. |
| `resolution` | enum | いいえ | `"720p"` | 720p, 1080p, 4k | The resolution of the generated video. |
| `auto_fix` | boolean | いいえ | `false` | - | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `aspect_ratio` | enum | いいえ | `"auto"` | auto, 16:9, 9:16 | The aspect ratio of the generated video. Only 16:9 and 9:16 are supported. |
| `safety_tolerance` | enum | いいえ | `"4"` | 1, 2, 3, 4, 5, 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. |
| `prompt` | string | はい | `"A monkey and polar bear host a casual podcast about AI inference, bringing their unique perspectives from different environments (tropical vs. arctic) to discuss how AI systems make decisions and process information.\nSample Dialogue:\nMonkey (Banana): \"Welcome back to Bananas & Ice! I am Banana\"\nPolar Bear (Ice): \"And I'm Ice!\""` | - | The text prompt describing the video you want to generate |
| `generate_audio` | boolean | いいえ | `true` | - | Whether to generate audio for the video. |
| `image_url` | string | はい | `"https://storage.googleapis.com/falserverless/example_inputs/veo31_i2v_input.jpg"` | - | URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be cropped to fit. |

#### input フィールド

_このモデルのフィールド設定はありません。_

### Veo 3.1 Fast Image to Video

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `negative_prompt` | object | いいえ | `-` | - | A negative prompt to guide the video generation. |
| `seed` | object | いいえ | `-` | - | The seed for the random number generator. |
| `duration` | enum | いいえ | `"8s"` | 4s, 6s, 8s | The duration of the generated video. |
| `resolution` | enum | いいえ | `"720p"` | 720p, 1080p, 4k | The resolution of the generated video. |
| `auto_fix` | boolean | いいえ | `false` | - | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `aspect_ratio` | enum | いいえ | `"auto"` | auto, 16:9, 9:16 | The aspect ratio of the generated video. Only 16:9 and 9:16 are supported. |
| `safety_tolerance` | enum | いいえ | `"4"` | 1, 2, 3, 4, 5, 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. |
| `prompt` | string | はい | `"A monkey and polar bear host a casual podcast about AI inference, bringing their unique perspectives from different environments (tropical vs. arctic) to discuss how AI systems make decisions and process information.\nSample Dialogue:\nMonkey (Banana): \"Welcome back to Bananas & Ice! I am Banana\"\nPolar Bear (Ice): \"And I'm Ice!\""` | - | The text prompt describing the video you want to generate |
| `generate_audio` | boolean | いいえ | `true` | - | Whether to generate audio for the video. |
| `image_url` | string | はい | `"https://storage.googleapis.com/falserverless/example_inputs/veo31_i2v_input.jpg"` | - | URL of the input image to animate. Should be 720p or higher resolution in 16:9 or 9:16 aspect ratio. If the image is not in 16:9 or 9:16 aspect ratio, it will be cropped to fit. |

#### input フィールド

_このモデルのフィールド設定はありません。_

### Veo 3

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `negative_prompt` | object | いいえ | `-` | - | A negative prompt to guide the video generation. |
| `seed` | object | いいえ | `-` | - | The seed for the random number generator. |
| `duration` | enum | いいえ | `"8s"` | 4s, 6s, 8s | The duration of the generated video. |
| `resolution` | enum | いいえ | `"720p"` | 720p, 1080p | The resolution of the generated video. |
| `auto_fix` | boolean | いいえ | `true` | - | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `aspect_ratio` | enum | いいえ | `"16:9"` | 16:9, 9:16 | The aspect ratio of the generated video. |
| `prompt` | string | はい | `"A casual street interview on a busy New York City sidewalk in the afternoon. The interviewer holds a plain, unbranded microphone and asks: Have you seen Google's new Veo3 model It is a super good model. Person replies: Yeah I saw it, it's already available on fal. It's crazy good."` | - | The text prompt describing the video you want to generate |
| `generate_audio` | boolean | いいえ | `true` | - | Whether to generate audio for the video. |
| `safety_tolerance` | enum | いいえ | `"4"` | 1, 2, 3, 4, 5, 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. |

#### input フィールド

_このモデルのフィールド設定はありません。_

### Veo 3 Fast

#### Payload フィールド

| フィールド | タイプ | 必須 | デフォルト / 例 | 選択肢 | 説明 |
| --- | --- | --- | --- | --- | --- |
| `negative_prompt` | object | いいえ | `-` | - | A negative prompt to guide the video generation. |
| `seed` | object | いいえ | `-` | - | The seed for the random number generator. |
| `duration` | enum | いいえ | `"8s"` | 4s, 6s, 8s | The duration of the generated video. |
| `resolution` | enum | いいえ | `"720p"` | 720p, 1080p | The resolution of the generated video. |
| `auto_fix` | boolean | いいえ | `true` | - | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |
| `aspect_ratio` | enum | いいえ | `"16:9"` | 16:9, 9:16 | The aspect ratio of the generated video. |
| `prompt` | string | はい | `"A casual street interview on a busy New York City sidewalk in the afternoon. The interviewer holds a plain, unbranded microphone and asks: Have you seen Google's new Veo3 model It is a super good model. Person replies: Yeah I saw it, it's already available on fal. It's crazy good."` | - | The text prompt describing the video you want to generate |
| `generate_audio` | boolean | いいえ | `true` | - | Whether to generate audio for the video. |
| `safety_tolerance` | enum | いいえ | `"4"` | 1, 2, 3, 4, 5, 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. |

#### input フィールド

_このモデルのフィールド設定はありません。_

## 価格

生成タスクの作成時にクレジットが予約されます。作成レスポンスの `reservedCredits` が、そのリクエストで予約されたクレジット数です。

| モデル | タイプ | 仕様 | 価格 | 課金 |
| --- | --- | --- | --- | --- |
| Veo 3.1 Lite | テキスト/画像から動画 | 720p | 10 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Lite | テキスト/画像から動画 | 1080p | 15 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Lite | テキスト/画像から動画 | 4k | 50 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Fast | テキスト/画像から動画 | 720p | 20 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Fast | テキスト/画像から動画 | 1080p | 25 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Fast | テキスト/画像から動画 | 4k | 60 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Quality | テキスト/画像から動画 | 720p | 150 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Quality | テキスト/画像から動画 | 1080p | 155 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Quality | テキスト/画像から動画 | 4k | 190 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Extend | テキスト/画像から動画 | fast | 20 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Extend | テキスト/画像から動画 | lite | 30 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Extend | テキスト/画像から動画 | quality | 250 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Get 1080P | テキスト/画像から動画 | - | 5 クレジット | 生成ごとの固定価格 |
| Veo 3.1 Get 4K | テキスト/画像から動画 | - | 40 クレジット | 生成ごとの固定価格 |
| Veo 3.1 | テキスト/画像から動画 | 720p | 40 クレジット/秒 | 出力秒数 × 40 |
| Veo 3.1 | テキスト/画像から動画 | 720p | 80 クレジット/秒 | 出力秒数 × 80 |
| Veo 3.1 | テキスト/画像から動画 | 1080p | 40 クレジット/秒 | 出力秒数 × 40 |
| Veo 3.1 | テキスト/画像から動画 | 1080p | 80 クレジット/秒 | 出力秒数 × 80 |
| Veo 3.1 | テキスト/画像から動画 | 4k | 80 クレジット/秒 | 出力秒数 × 80 |
| Veo 3.1 | テキスト/画像から動画 | 4k | 120 クレジット/秒 | 出力秒数 × 120 |
| Veo 3.1 Fast | テキスト/画像から動画 | 720p | 20 クレジット/秒 | 出力秒数 × 20 |
| Veo 3.1 Fast | テキスト/画像から動画 | 720p | 30 クレジット/秒 | 出力秒数 × 30 |
| Veo 3.1 Fast | テキスト/画像から動画 | 1080p | 20 クレジット/秒 | 出力秒数 × 20 |
| Veo 3.1 Fast | テキスト/画像から動画 | 1080p | 30 クレジット/秒 | 出力秒数 × 30 |
| Veo 3.1 Fast | テキスト/画像から動画 | 4k | 60 クレジット/秒 | 出力秒数 × 60 |
| Veo 3.1 Fast | テキスト/画像から動画 | 4k | 70 クレジット/秒 | 出力秒数 × 70 |
| Veo 3.1 Image to Video | 画像から動画 | 720p | 40 クレジット/秒 | 出力秒数 × 40 |
| Veo 3.1 Image to Video | 画像から動画 | 720p | 80 クレジット/秒 | 出力秒数 × 80 |
| Veo 3.1 Image to Video | 画像から動画 | 1080p | 40 クレジット/秒 | 出力秒数 × 40 |
| Veo 3.1 Image to Video | 画像から動画 | 1080p | 80 クレジット/秒 | 出力秒数 × 80 |
| Veo 3.1 Image to Video | 画像から動画 | 4k | 80 クレジット/秒 | 出力秒数 × 80 |
| Veo 3.1 Image to Video | 画像から動画 | 4k | 120 クレジット/秒 | 出力秒数 × 120 |
| Veo 3.1 Fast Image to Video | 画像から動画 | 720p | 20 クレジット/秒 | 出力秒数 × 20 |
| Veo 3.1 Fast Image to Video | 画像から動画 | 720p | 30 クレジット/秒 | 出力秒数 × 30 |
| Veo 3.1 Fast Image to Video | 画像から動画 | 1080p | 20 クレジット/秒 | 出力秒数 × 20 |
| Veo 3.1 Fast Image to Video | 画像から動画 | 1080p | 30 クレジット/秒 | 出力秒数 × 30 |
| Veo 3.1 Fast Image to Video | 画像から動画 | 4k | 60 クレジット/秒 | 出力秒数 × 60 |
| Veo 3.1 Fast Image to Video | 画像から動画 | 4k | 70 クレジット/秒 | 出力秒数 × 70 |
| Veo 3 | テキスト/画像から動画 | false | 40 クレジット/秒 | 出力秒数 × 40 |
| Veo 3 | テキスト/画像から動画 | true | 80 クレジット/秒 | 出力秒数 × 80 |
| Veo 3 Fast | テキスト/画像から動画 | false | 20 クレジット/秒 | 出力秒数 × 20 |
| Veo 3 Fast | テキスト/画像から動画 | true | 30 クレジット/秒 | 出力秒数 × 30 |

## 一般的なエラー

| ステータス | 意味 |
| --- | --- |
| `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 |