---
title: Veo 2 | Runware Docs
url: https://runware.ai/docs/models/google-veo-2
description: High fidelity text to video generation with camera control
---
# Veo 2

Veo 2 is a text to video model that produces high resolution clips with strong control over camera movement, composition, and scene dynamics. It supports cinematic framing, object aware motion, extended durations, and up to 4K outputs for production grade workflows.

- **ID**: `google:2@0`
- **Status**: live
- **Creator**: Google
- **Release Date**: December 16, 2024
- **Capabilities**: Text to Video, Image to Video

## Pricing

Each generation will cost $0.5/s for 720p.

- **720p · 5s**: `$2.5`

## Compatibility & Validation

Provide exactly one of: `inputs.frameImages` or `width/height`.

---

When `inputs.video` is provided, `width/height` cannot be used.

---

When `inputs.video` is provided, `duration` must be `7`.

---

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `720p (16:9)` | `1280x720` |
| `720p (9:16)` | `720x1280` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/google-veo-2#request-tasktype)

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

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/google-veo-2#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/google-veo-2#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/google-veo-2#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/google-veo-2#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/google-veo-2#request-webhookurl)

- **Type**: `string`
- **Format**: `URI`

Specifies a webhook URL where JSON responses will be sent 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/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/google-veo-2#request-deliverymethod)

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

Determines how the API delivers task results.

**Allowed values**:

- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. Required for long-running tasks like video generation.

**Learn more** (1 resource):

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

### [uploadEndpoint](https://runware.ai/docs/models/google-veo-2#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/google-veo-2#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/google-veo-2#request-safety-checkcontent)

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

Enable or disable content safety checking. When enabled, defaults to `fast` mode.

#### [mode](https://runware.ai/docs/models/google-veo-2#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `none`

Safety checking mode for video generation.

**Allowed values**:

- `none` Disables checking.
- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/google-veo-2#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/google-veo-2#request-includecost)

- **Type**: `boolean`
- **Default**: `false`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/google-veo-2#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/google-veo-2#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`

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 frame position.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. 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 frame position, use an object with `image` and `frame`.

```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/google-veo-2#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/google-veo-2#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).

### [video](https://runware.ai/docs/models/google-veo-2#request-inputs-video)

- **Path**: `inputs.video`
- **Type**: `string`

Video to extend (UUID or URL).

**Generation Parameters**

Core parameters for controlling the generated content.

### [model](https://runware.ai/docs/models/google-veo-2#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `google:2@0`

Identifier of the model to use for generation.

**Learn more** (3 resources):

- [Text To Image: Model Selection The Foundation Of Generation](https://runware.ai/docs/guides/text-to-image#model-selection-the-foundation-of-generation) (guide)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/guides/image-inpainting#model-specialized-inpainting-models) (guide)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/guides/image-outpainting#other-critical-parameters) (guide)

### [positivePrompt](https://runware.ai/docs/models/google-veo-2#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `3000`

Text prompt describing elements to include in the generated output.

**Learn more** (2 resources):

- [Text To Image: Prompts Guiding The Generation](https://runware.ai/docs/guides/text-to-image#prompts-guiding-the-generation) (guide)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/guides/image-outpainting#other-critical-parameters) (guide)

### [width](https://runware.ai/docs/models/google-veo-2#request-width)

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

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Image To Image: Dimensions Changing Aspect Ratio](https://runware.ai/docs/guides/image-to-image#dimensions-changing-aspect-ratio) (guide)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/guides/image-outpainting#dimensions-critical-for-outpainting) (guide)

### [height](https://runware.ai/docs/models/google-veo-2#request-height)

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

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Image To Image: Dimensions Changing Aspect Ratio](https://runware.ai/docs/guides/image-to-image#dimensions-changing-aspect-ratio) (guide)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/guides/image-outpainting#dimensions-critical-for-outpainting) (guide)

### [duration](https://runware.ai/docs/models/google-veo-2#request-duration)

- **Type**: `float`
- **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` `6` `7` `8`

### [seed](https://runware.ai/docs/models/google-veo-2#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `4294967295`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Provider Settings**

Parameters specific to this model provider. These must be nested inside the \`providerSettings.google\` object.

### [enhancePrompt](https://runware.ai/docs/models/google-veo-2#request-providersettings-google-enhanceprompt)

- **Path**: `providerSettings.google.enhancePrompt`
- **Type**: `boolean`
- **Default**: `true`

Enable automatic prompt enhancement. Affects reproducibility.

## Response Parameters

### [taskType](https://runware.ai/docs/models/google-veo-2#response-tasktype)

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

Type of the task.

### [taskUUID](https://runware.ai/docs/models/google-veo-2#response-taskuuid)

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

UUID of the task.

### [videoUUID](https://runware.ai/docs/models/google-veo-2#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/google-veo-2#response-videourl)

- **Type**: `string`
- **Format**: `URI`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/google-veo-2#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/google-veo-2#response-videodatauri)

- **Type**: `string`
- **Format**: `URI`

Data URI of the output video.

### [seed](https://runware.ai/docs/models/google-veo-2#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/google-veo-2#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/google-veo-2#response-cost)

- **Type**: `float`

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

## Examples

### Windblown Salt Flats Caravan (Image to Video)

[Watch video](https://assets.runware.ai/examples/google-veo-2/43056e3f-52d0-4860-b687-79b3eacfffdb.mp4)

**Request**:

```json
{
  "taskType": "videoInference",
  "taskUUID": "2ceae46c-accb-4844-98d2-ae1a8e5ef2ce",
  "model": "google:2@0",
  "positivePrompt": "Extend the source video seamlessly. The caravan continues across a vast white salt plain patterned with shallow reflective water and cracked mineral textures. The camera gradually rises from a low tracking angle into a wider aerial reveal, showing elegant curved wagon canopies, fluttering streamers, pack animals, and long shifting shadows in late afternoon light. Wind pushes thin sheets of dust across the ground while the lead rider signals a gentle change of direction toward distant hexagonal stone formations emerging through heat haze. Preserve continuity of subjects, motion, wardrobe, and environment from the input clip. Emphasize realistic fabric movement, hoof impacts, drifting grit, mirror-like reflections in wet patches, and a cinematic sense of scale.",
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/2e333524-54e1-4c42-be0c-7b102851986a.mp4"
  }
}
```

**Response**:

```json
{
  "taskType": "videoInference",
  "taskUUID": "2ceae46c-accb-4844-98d2-ae1a8e5ef2ce",
  "videoUUID": "1c58cd90-030c-48c6-88ed-cdbf5312c453",
  "videoURL": "https://vm.runware.ai/video/os/a18d05/ws/5/vi/1c58cd90-030c-48c6-88ed-cdbf5312c453.mp4",
  "seed": 2100582426,
  "cost": 4
}
```

---

### Rain-Swept Funicular Ascent (Image to Video)

[Watch video](https://assets.runware.ai/examples/google-veo-2/8423e292-2f22-4741-9d21-ad06ba0e89a4.mp4)

**Request**:

```json
{
  "taskType": "videoInference",
  "taskUUID": "833712d1-4906-430d-8eca-678cd82248ad",
  "model": "google:2@0",
  "positivePrompt": "Starting from the provided first-frame image, create a cinematic sequence of a scarlet funicular ascending a steep rain-soaked hillside through a dense historic harbor district. The camera begins close to street level with water droplets splashing in puddles and slowly glides upward alongside the car, revealing layered rooftops, narrow stairways, swaying laundry lines, glistening rails, and the distant sea under heavy storm clouds. Emphasize realistic rain streaks, wheel spray, subtle vibration of cables, pedestrians hurrying under umbrellas, and warm cabin lights glowing against the cool weather. Preserve the composition and subject from the input frame while adding rich depth, natural object-aware motion, atmospheric perspective, and polished cinematic realism.",
  "width": 1280,
  "height": 720,
  "duration": 6,
  "seed": 46890,
  "providerSettings": {
    "google": {
      "enhancePrompt": true
    }
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/88753993-812c-4cfd-8b01-64651d63d9ec.jpg",
        "frame": "first"
      }
    ]
  }
}
```

**Response**:

```json
{
  "taskType": "videoInference",
  "taskUUID": "833712d1-4906-430d-8eca-678cd82248ad",
  "videoUUID": "0bb106fb-53ea-4cc5-b6a8-64319fac936f",
  "videoURL": "https://vm.runware.ai/video/os/a23d05/ws/5/vi/0bb106fb-53ea-4cc5-b6a8-64319fac936f.mp4",
  "seed": 46890,
  "cost": 3
}
```

---

### Submerged Grand Library Drift (Image to Video)

[Watch video](https://assets.runware.ai/examples/google-veo-2/8aa115e9-9878-45d9-9ed2-1983ce4ddf0e.mp4)

**Request**:

```json
{
  "taskType": "videoInference",
  "taskUUID": "903f5a6f-e062-402e-8711-ffe95e4a63f7",
  "model": "google:2@0",
  "positivePrompt": "A cinematic underwater journey through a vast historic library hall, beginning in eerie stillness and gradually building into a sweeping current that lifts loose pages, nudges ladders, and sends clusters of bubbles upward. The camera glides slowly forward between long tables and towering shelves, then arcs slightly to reveal the full scale of the chamber. Maintain strong continuity with the guided first and last frames: same architecture, same submerged atmosphere, same suspended books, but increasing motion and tension over time. Sunbeams ripple through the water from the fractured ceiling above, fabric banners sway gently, tiny particles shimmer, and the final moments resolve into a dramatic spiral of paper and light. Rich environmental detail, believable fluid dynamics, graceful object-aware motion, high-end cinematic framing.",
  "width": 1280,
  "height": 720,
  "duration": 8,
  "seed": 65113,
  "providerSettings": {
    "google": {
      "enhancePrompt": true
    }
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/37b129bc-ec36-4c94-a7d7-ea29cb014325.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/cffa590a-0be5-435a-aac0-29c3b987d7fe.jpg",
        "frame": "last"
      }
    ]
  }
}
```

**Response**:

```json
{
  "taskType": "videoInference",
  "taskUUID": "903f5a6f-e062-402e-8711-ffe95e4a63f7",
  "videoUUID": "36f01ec2-17b9-4007-8874-753017055be1",
  "videoURL": "https://vm.runware.ai/video/os/a01d21/ws/5/vi/36f01ec2-17b9-4007-8874-753017055be1.mp4",
  "seed": 65113,
  "cost": 4
}
```

---

### Windblown Salt Flats Pilgrimage (Text to Video)

[Watch video](https://assets.runware.ai/examples/google-veo-2/9c5a49a8-4388-4da0-a305-5a4a183ce091.mp4)

**Request**:

```json
{
  "taskType": "videoInference",
  "taskUUID": "0f009bb2-2d77-422b-b560-360bbca5f7e0",
  "model": "google:2@0",
  "positivePrompt": "A long-lens cinematic shot gliding low across shimmering white salt flats after rainfall, reflecting a pale apricot sky. In the distance, a small procession of travelers in weathered indigo robes leads two tall pack animals carrying bundles of colored glass kites and brass instruments. Gusts of wind drag thin sheets of water across the ground, creating rippling mirror reflections. As the camera advances, the group crests a subtle rise and hundreds of tethered kites suddenly catch the wind, lifting and circling overhead in elegant arcs. Fine dust, fluttering fabric, hoof splashes, and drifting reflections create rich object-aware motion. The mood is solemn yet wondrous, with natural light, expansive composition, atmospheric depth, and precise realistic textures. Smooth forward tracking shot, subtle rack focus, production-grade cinematography.",
  "width": 1280,
  "height": 720,
  "duration": 8,
  "seed": 1366,
  "providerSettings": {
    "google": {
      "enhancePrompt": true
    }
  }
}
```

**Response**:

```json
{
  "taskType": "videoInference",
  "taskUUID": "0f009bb2-2d77-422b-b560-360bbca5f7e0",
  "videoUUID": "c3effabd-5462-4c94-a6e5-88103289ded1",
  "videoURL": "https://vm.runware.ai/video/os/a10d08/ws/5/vi/c3effabd-5462-4c94-a6e5-88103289ded1.mp4",
  "seed": 1366,
  "cost": 4
}
```