# Veo 3.1 | Image to Video

Transforms a single image into a cinematic, realistic video sequence with depth, camera movement, and natural lighting transitions. Ideal for turning stills into short film-like visuals.

## API Information

- **Model Slug:** veo3-1-image-to-video
- **Branded URL:** https://www.eachlabs.ai/google/veo3-1/veo3-1-image-to-video
- **Provider:** Google
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Veo3.1, 8s, 720p, Audio On
- **Estimated Processing Time:** 85 seconds
- **Last Updated:** 2026-05-04
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/veo3-1-image-to-video

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $3.20
- **Pricing Details:** Veo3.1, 8s, 720p, Audio On

### Pricing Rules

| Rule | Condition | Price |
| --- | --- | --- |
| multiple_conditions | duration == "4" AND resolution == "720p" AND generate_audio == "false" | $0.8000 |
| multiple_conditions | duration == "4" AND resolution == "720p" AND generate_audio == "true" | $1.60 |
| multiple_conditions | duration == "4" AND resolution == "1080p" AND generate_audio == "false" | $0.8000 |
| multiple_conditions | duration == "4" AND resolution == "1080p" AND generate_audio == "true" | $1.60 |
| multiple_conditions | duration == "4" AND resolution == "4k" AND generate_audio == "false" | $1.60 |
| multiple_conditions | duration == "4" AND resolution == "4k" AND generate_audio == "true" | $2.40 |
| multiple_conditions | duration == "6" AND resolution == "720p" AND generate_audio == "false" | $1.20 |
| multiple_conditions | duration == "6" AND resolution == "720p" AND generate_audio == "true" | $2.40 |
| multiple_conditions | duration == "6" AND resolution == "1080p" AND generate_audio == "false" | $1.20 |
| multiple_conditions | duration == "6" AND resolution == "1080p" AND generate_audio == "true" | $2.40 |
| multiple_conditions | duration == "6" AND resolution == "4k" AND generate_audio == "false" | $2.40 |
| multiple_conditions | duration == "6" AND resolution == "4k" AND generate_audio == "true" | $3.60 |
| multiple_conditions | duration == "8" AND resolution == "720p" AND generate_audio == "false" | $1.60 |
| multiple_conditions | duration == "8" AND resolution == "720p" AND generate_audio == "true" | $3.20 |
| multiple_conditions | duration == "8" AND resolution == "1080p" AND generate_audio == "false" | $1.60 |
| multiple_conditions | duration == "8" AND resolution == "1080p" AND generate_audio == "true" | $3.20 |
| multiple_conditions | duration == "8" AND resolution == "4k" AND generate_audio == "false" | $3.20 |
| multiple_conditions | duration == "8" AND resolution == "4k" AND generate_audio == "true" | $4.80 |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | The text prompt describing the video you want to generate |
| image_url | string | Yes | - | - | 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. |
| aspect_ratio | string | No | 16:9 | 9:16,16:9 | The aspect ratio of the generated video |
| duration | integer | No | 8 | 4,6,8 | The duration of the generated video in seconds |
| generate_audio | boolean | No | true | - | Whether to generate audio for the video. If false, %33 less credits will be used. |
| resolution | string | No | 720p | 720p,1080p | Resolution of the generated video |
| auto_fix | boolean | No | false | - | Whether to automatically attempt to fix prompts that fail content policy or other validation checks by rewriting them. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "veo3-1-image-to-video",
  "input": {
    "prompt": "A photorealistic swamp podcast scene at golden dusk. A frog wearing sunglasses and a turtle sit behind sleek microphones on a small wooden deck above glowing swamp water. Neon fireflies drift lazily in the humid air. Dialogue: Frog: “So, Tuck… be honest — did you really beat the rabbit, or was that PR?” Turtle: smirks “Let’s just say… he sprinted, I strategized.” Realistic lip-sync, subtle laughter, gentle swamp ambience with frogs croaking in the distance, cinematic soft light and natural reflections on the water.",
    "image_url": "https://storage.googleapis.com/magicpoint/inputs/veo3-1-image-to-video-input.png"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "X-API-Key: YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `X-API-Key` |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**veo3.1-image-to-video — Image-to-Video AI Model**

veo3.1-image-to-video, Google's cutting-edge update within the Veo 3.1 family, transforms static images into cinematic 4K videos with professional-grade realism, native vertical support, and precise character consistency—solving the challenge of animating stills for social media and film pre-visualization without quality loss.

Developed by Google DeepMind and released with major updates in January 2026, this **image-to-video AI model** excels at "Ingredients to Video" workflows, accepting up to four reference images to generate dynamic sequences up to 8 seconds long. Ideal for creators seeking **Google image-to-video** tools, it delivers depth, camera motion, and natural transitions directly from your uploads, making it a top choice for high-resolution outputs that outpace competitors capped at 1080p.

Whether you're a developer integrating **veo3.1-image-to-video API** or experimenting in the playground, it streamlines production of short-form content for TikTok, YouTube Shorts, and beyond.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `X-API-Key: YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.