# MiniMax H3 | Image-to-Video

MiniMax H3 Image-to-Video turns still images into 2K video clips with native audio, using first and last frames to control how each shot moves.

## API Information

- **Model Slug:** minimax-h3-image-to-video
- **Branded URL:** https://www.eachlabs.ai/minimax/minimax-h3/minimax-h3-image-to-video
- **Provider:** Minimax
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** MiniMax H3 2K image-to-video generation is billed at $0.13 per output second.
- **Estimated Processing Time:** 300 seconds
- **Last Updated:** 2026-08-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/minimax-h3-image-to-video

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** MiniMax H3 2K image-to-video generation is billed at $0.13 per output second.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| resolution == "768P" | MiniMax H3 768P image-to-video generation is billed at $0.09 per output second. |
| Rule 2 | MiniMax H3 2K image-to-video generation is billed at $0.13 per output second. |

## Input Schema

No input parameters documented.

## 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-h3-image-to-video",
  "input": {}
}'
```

## 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 H3 | Image-to-Video Overview**

MiniMax H3 | Image-to-Video is a multimodal video generation model from Minimax that turns still images into high-fidelity 2K video clips with native stereo audio in a single pass. It belongs to the **MiniMax H3 (Hailuo 3.0)** family, a frontier-level text-to-video and image-to-video system designed for cinematic short-form content. Its primary differentiator is native 2K output at 24 fps with synchronized dialogue, sound effects, and ambience, while letting you control motion and camera behavior using first and last frames. On each::labs, MiniMax H3 | Image-to-Video focuses on workflows where creators provide one or two key images plus a brief prompt to define how the scene evolves over 5–15 seconds. This makes it ideal for story beats, product shots, and character moments that need precise visual continuity from still to video.

## 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.