# Runway Gen4 | Aleph

Runway Aleph is an advanced model for text-based video editing. It can generate new camera angles, extend scenes, adjust lighting and atmosphere, add or remove objects, and apply different visual styles to videos.

## API Information

- **Model Slug:** runway-gen4-aleph
- **Branded URL:** https://www.eachlabs.ai/runway/gen4/runway-gen4-aleph
- **Provider:** Runway
- **Category:** Video to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** $0.15 per second of output video (15 credits/sec at $0.01/credit)
- **Estimated Processing Time:** 250 seconds
- **Last Updated:** 2026-04-02
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/runway-gen4-aleph

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** $0.15 per second of output video (15 credits/sec at $0.01/credit)

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | $0.15 per second of output video (15 credits/sec at $0.01/credit) |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text prompt guiding the video transformation. Supports complex edits: object add/remove/replace, relighting, restyling, scene generation, and camera angle changes. Max 1000 characters. |
| video_url | string | Yes | - | - | Input video URL to transform. Max 16MB, only the first 5 seconds are used. Supported: MP4, QuickTime, WebM. |
| aspect_ratio | string | Yes | 1280:720 | 1280:720,720:1280,1104:832,832:1104,960:960,1584:672,848:480,480:848 | Output video resolution. 1280:720: standard landscape 16:9 (default). 720:1280: standard portrait 9:16. 1104:832: wide landscape. 832:1104: tall portrait. 960:960: square. 1584:672: ultra-wide cinematic. 848:480: compact landscape. 480:848: compact portrait. |
| seed | integer | No | - | - | Random seed for reproducible generation. Set a specific value to get consistent results across runs with identical inputs. |
| reference_images | array | No | - | 0–1 | Optional reference images to influence style, color, lighting, or content of the output video. Recommended image size: 640x640px to 4K. |
| public_figure_moderation | string | No | auto | auto,low | Content moderation level for public figures. auto: standard moderation (default). low: relaxed moderation, allows more creative freedom. |

## 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": "runway-gen4-aleph",
  "input": {
    "video_url": "https://storage.googleapis.com/magicpoint/inputs/runay-gen4-aleph-input-video.mp4",
    "prompt": "make it morning",
    "aspect_ratio": "1280:720"
  }
}'
```

## 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

**runway-gen4-aleph — Video Editing AI Model**

runway-gen4-aleph is an advanced in-context video editing model that transforms existing videos through simple text prompts, eliminating the need for manual timelines, layers, or masking. Developed by Runway as part of the Gen-4 family, this model solves a critical problem for video creators: the time-intensive process of applying post-production edits like camera angle adjustments, lighting changes, background modifications, and visual effects. Instead of frame-by-frame manual work, creators describe what they want changed in natural language, and the AI handles the execution.

What distinguishes runway-gen4-aleph from frame-based editing tools is its understanding of full video context rather than isolated frames. This temporal awareness ensures characters, objects, and backgrounds remain visually consistent throughout the entire clip, preventing the flickering and discontinuities that plague simpler video-to-video AI models. For creators building AI video editing workflows or developers integrating video transformation capabilities into applications, this consistency is essential for professional output.

## 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.