# Runway | Gen4 | Turbo

Runway Gen-4 Turbo I2V is an image-to-video model for generating cinematic video from a single image. It brings still images to life with realistic motion and smooth camera effects. Perfect for visual storytelling and dynamic scene creation.

## API Information

- **Model Slug:** gen4-turbo
- **Branded URL:** https://www.eachlabs.ai/runway/gen4/gen4-turbo
- **Provider:** Runway
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** $0.05 per second of duration (input.duration, default 5)
- **Estimated Processing Time:** 25 seconds
- **Last Updated:** 2026-07-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/gen4-turbo

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.2500
- **Pricing Details:** $0.05 per second of duration (input.duration, default 5)

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | $0.05 per second of duration (input.duration, default 5) |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text prompt for video generation |
| image | string | Yes | - | - | Initial image for video generation (first frame) |
| aspect_ratio | string | No | 16:9 | 16:9,9:16,4:3,3:4,1:1,21:9 | An enumeration. |
| duration | integer | No | 5 | 5,10 | An enumeration. |
| seed | integer | No | - | - | Random seed. Set for reproducible generation |

## 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": "gen4-turbo",
  "input": {
    "image": "https://storage.googleapis.com/magicpoint/inputs/gen4-turbo-input.jpg",
    "prompt": "A cinematic daytime scene where the man walks calmly down the cobblestone alley in golden hour sunlight. The camera gently follows him from behind with a slow dolly motion. Warm light flares across the frame as he passes between buildings. Leaves rustle slightly in a soft breeze, creating subtle movement in the background. The man briefly glances upward, then continues walking. The shadows on the walls stretch long and golden. Everything is peaceful, realistic, and shot like a high-end drama film. Natural motion, 4K clarity, cinematic atmosphere.\n"
  }
}'
```

## 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

**gen4-turbo — Image-to-Video AI Model**

Developed by Runway as part of the gen4 family, **gen4-turbo** is a specialized image-to-video model that transforms static images into cinematic videos with realistic motion and smooth camera effects. Rather than starting from scratch with text alone, gen4-turbo accepts a reference image as its foundation, allowing you to lock in composition, subject design, and visual direction before animating the scene. This image-first workflow solves a critical problem for creators: generating video variations that maintain consistent visual identity while exploring different motion and camera behaviors—without the overhead of manual keyframing or complex technical prompts.

Released on April 7, 2025, gen4-turbo prioritizes speed and iteration efficiency, making it ideal for rapid A/B testing, concept exploration, and pre-visualization work. It's positioned as a faster, more credit-efficient alternative to standard gen4, enabling filmmakers and content creators to test multiple motion directions and camera angles in the time it would take to render a single high-fidelity shot elsewhere.

## 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.