# MiniMax H3 Max Turbo Extend Video

MiniMax H3 Max Turbo Extend Video adds prompt-guided footage to existing clips, with optional audio references and adjustable resolution for video editing.

## API Information

- **Model Slug:** minimax-h3-max-turbo-extend-video
- **Branded URL:** https://www.eachlabs.ai/fal/minimax-h3-max/minimax-h3-max-turbo-extend-video
- **Provider:** fal
- **Category:** Video to Video
- **Output Type:** video
- **Status:** active
- **Base Cost:** $0.025–$0.16 per second, depending on resolution
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/minimax-h3-max-turbo-extend-video

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.025–$0.16 per second, depending on resolution
- **Pricing Details:** 480p: $0.025
- **Pricing Details:** 1080p: $0.08
- **Pricing Details:** 2K: $0.16
- **Pricing Details:** default: $0.04

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| video_url | string | Yes | - | - | URL of the video to extend. Must be 1.625 s to 60 s long, up to 50 MB, aspect ratio between 0.4 and 2.5. |
| prompt | string | Yes | - | - | What happens next. Describe the continuation, not the source. |
| duration | integer | No | 5 | 1–15 | Seconds of new footage to add after the source. The actual duration may be slightly longer. |
| resolution | string | No | 768P | 480P, 768P, 1080P, 2K | Output video resolution. |
| aspect_ratio | string | No | auto | auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | Output aspect ratio. 'auto' follows the source video. Other values crop the video to fit the selected ratio. |
| output | string | No | extended | extended, continuation | 'extended' returns the whole source video followed by the new footage. 'continuation' returns only the generated continuation. |
| reference_audio_urls | array | No | - | - | Optional audio references for the continuation (2–15 seconds each, 15 seconds combined). They replace the source soundtrack as the model's audio reference. |
| enable_prompt_expansion | boolean | No | true | - | Automatically enhance the prompt using the source video to help keep the continuation consistent. May increase processing time. |
| seed | string | No | - | - | Seed for the continuation. Random when omitted. |
| enable_safety_checker | boolean | No | true | - | Moderate the source video and the prompt. |

## 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-max-turbo-extend-video",
  "input": {
    "prompt": "The train reaches the end of the viaduct and curves into a dense autumn forest. The camera keeps following from above as the locomotive disappears into a stone tunnel cut into the mountainside, leaving a trail of white steam glowing in the low golden sun over the treetops. The whistle sounds one last time and echoes across the valley.",
    "video_url": "https://cdn-us.eachlabs.ai/defaults/f14f4251c7ac4a10a8212826e6d4ee33.mp4"
  }
}'
```

## 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 |

## 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.