# Google Veo 3 Fast | Image to Video

Veo 3 Fast Image to Video | Google’s high-speed model that turns images into smooth, cinematic motion

## API Information

- **Model Slug:** veo-3-fast-image-to-video
- **Branded URL:** https://www.eachlabs.ai/google/veo3/veo-3-fast-image-to-video
- **Provider:** Google
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** 8s, audio on: $1.20
- **Estimated Processing Time:** 120 seconds
- **Last Updated:** 2026-04-29
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/veo-3-fast-image-to-video

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $1.20
- **Pricing Details:** 8s, audio on: $1.20

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| output.duration_seconds <= "4.5" AND generate_audio == "false" | 4s, audio off: $0.40 |
| output.duration_seconds <= "4.5" AND generate_audio == "true" | 4s, audio on: $0.60 |
| output.duration_seconds <= "6.5" AND generate_audio == "false" | 6s, audio off: $0.60 |
| output.duration_seconds <= "6.5" AND generate_audio == "true" | 6s, audio on: $0.90 |
| generate_audio == "false" | 8s, audio off: $0.80 |
| Rule 6 | 8s, audio on: $1.20 |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| image_url | string | Yes | - | - | The URL of the image used to generate video |
| prompt | string | Yes | - | - | Text prompt for video generation |
| generate_audio | boolean | No | true | - | - |
| aspect_ratio | string | No | 16:9 | 16:9,9:16 | The aspect ratio of the generated video |
| resolution | string | No | 720p | 720p,1080p | Resolution of the generated video |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "veo-3-fast-image-to-video",
  "input": {
    "image_url": "https://storage.googleapis.com/magicpoint/inputs/veo3-fast-i2v-input.jpeg",
    "prompt": "Cinematic video set in a bioluminescent underwater cave system on an alien ocean world, illuminated by glowing turquoise and violet corals. The scene opens with a smooth tracking shot through a tunnel of shimmering water, revealing a vast cavern where a swarm of robotic fish, each engraved with the 'eachlabs.ai' logo, swims in synchronized patterns. The camera follows the swarm as they weave through towering coral structures, their metallic bodies reflecting the cave’s radiant glow. A faint, rhythmic pulse of light emanates from the corals, creating a hypnotic effect. Suddenly, a massive, bioluminescent jellyfish-like creature drifts into view, its tentacles gently pulsating as it emits a low, resonant hum. The audio includes the soft gurgle of water, a futuristic ambient soundtrack with ethereal tones, and the jellyfish’s hum synced with its movements. The video ends with a slow zoom-out, showing the swarm of robotic fish forming the shape of the 'eachlabs.ai' logo against the glowing cave backdrop, followed by a gentle fade to black. The style is photorealistic, with realistic fluid dynamics, vibrant lighting, and an immersive, otherworldly aesthetic."
  }
}'
```

## 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 "Authorization: Bearer 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 `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**veo-3-fast-image-to-video — Image to Video AI Model**

Developed by Google as part of the Veo 3 family, **veo-3-fast-image-to-video** transforms static images into smooth, cinematic video sequences in seconds rather than minutes. This model solves a critical pain point for creators and developers: generating high-quality video from reference imagery without sacrificing speed or budget. Where standard image-to-video models demand 2-3 minutes per generation, Veo 3 Fast delivers results in roughly half that time—making it ideal for workflows that demand rapid iteration, batch processing, or real-time applications.

The model excels at maintaining visual consistency between your input image and generated motion, automatically syncing spatial audio to match the video content. Whether you're building an AI video generator for e-commerce, creating content at scale, or prototyping visual ideas quickly, Veo 3 Fast balances professional-grade output with production-ready speed.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer 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.