# Minimax Hailuo V2.3 | Standard | Image to Video

Produce detailed, cinematic motion from still images with precise lighting and texture control. Hailuo-2.3 Standard offers reliable 768p quality for consistent, creative video storytelling.

## API Information

- **Model Slug:** minimax-hailuo-v2-3-standard-image-to-video
- **Branded URL:** https://www.eachlabs.ai/minimax/hailuo-v2-3/minimax-hailuo-v2-3-standard-image-to-video
- **Provider:** MiniMax
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** 6s video generation = $0.28
- **Estimated Processing Time:** 135 seconds
- **Last Updated:** 2026-06-10
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/minimax-hailuo-v2-3-standard-image-to-video

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.2800
- **Pricing Details:** 6s video generation = $0.28

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| duration in_i "6,6" | 6s video generation = $0.28 |
| duration in_i "10,10" | 10s video generation = $0.56 |
| Default (fallback) | $0.2800 |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text prompt for video generation |
| image_url | string | Yes | - | - | URL of the image to use as the first frame |
| duration | string | No | 6 | 6,10 | The duration of the video in seconds. |
| prompt_optimizer | boolean | No | true | - | Whether to use the model's prompt optimizer |

## 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": "minimax-hailuo-v2-3-standard-image-to-video",
  "input": {
    "prompt": "Ultra realistic cinematic video of a crystal-clear mountain stream flowing through a lush forest. Water gently ripples and flows over smooth rocks and pebbles, forming small cascades and swirling eddies. Sunlight filters through tall trees, casting soft reflections and shimmering highlights on the surface. Green moss and ferns cover the riverbanks, and tiny droplets sparkle in the air. The camera follows the water’s movement downstream, capturing the fluid motion, natural sound of flowing water, and peaceful forest ambience. 8K resolution, cinematic lighting, high frame rate, hyper-realistic textures, dynamic water flow.",
    "image_url": "https://storage.googleapis.com/magicpoint/inputs/minimax-hailuo-2.3-standard-image-to-video-input.jpg"
  }
}'
```

## 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

**minimax-hailuo-v2.3-standard-image-to-video — Image-to-Video AI Model**

Developed by Minimax as part of the **hailuo-v2.3** family, **minimax-hailuo-v2.3-standard-image-to-video** transforms static images into cinematic videos with precise motion, lighting, and texture control, solving the challenge of realistic animation from stills for creators seeking professional storytelling without complex editing.

This **image-to-video AI model** excels in maintaining anatomical integrity during complex movements and temporal stability in stylized scenes, delivering reliable 768p outputs ideal for consistent creative workflows. Users searching for "Minimax image-to-video" or "best image-to-video AI" discover its balanced speed and quality, supporting durations up to 10 seconds at 768p or 6 seconds at 1080p.

With input images in JPG, JPEG, or PNG formats (aspect ratios between 2:5 and 5:2, min 300px short side, under 20MB), it generates smooth, high-fidelity clips perfect for rapid prototyping in animation or marketing visuals.

## 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.