# MiniMax H3 Max Reference to Video — API Reference

Model ID: `model_minimax-h3-max-reference-to-video`

---

## Authentication

- **API_KEY** and **API_SECRET** are found in your [Scenario Project Settings](https://app.scenario.com/team&tab=api_keys) under API Keys.
- Set them as environment variables `SCENARIO_SDK_API_KEY` and `SCENARIO_SDK_API_SECRET` — both SDKs pick them up by default.
- For raw HTTP (cURL), use Basic Auth: `Authorization: Basic base64("<API_KEY>:<API_SECRET>")`.

### Install the SDK

- JavaScript / TypeScript: `npm install @scenario-labs/sdk`
- Python: `pip install scenario-sdk`

---

## Generate

**Endpoint:** `POST https://api.cloud.scenario.com/v1/generate/custom/model_minimax-h3-max-reference-to-video`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `prompt` | string | yes | - | Describe the video. Refer to uploads by order: Image 1, Image 2, Video 1, Audio 1, and so on. |
| `referenceImages` | assetId[] | - | - | Images to guide subjects or style (up to 9, max 30 MB each). Refer to them as Image 1, Image 2, and so on. Combined images, videos, and audio must not exceed 12 files. First 4 (1024×1024) are included; additional images are billed. |
| `referenceVideos` | assetId[] | - | - | Videos to guide motion (up to 3, each 2–15s and 2–15s in total, max 50 MB each). Refer to them as Video 1, Video 2, and so on. Billed per second of uploaded duration at the output resolution. |
| `referenceAudio` | assetId[] | - | - | Audio to guide the video (up to 3, each 2–15s and 2–15s in total, max 15 MB each). Requires at least one reference image or video. |
| `duration` | number | - | `5` | How long the video lasts, in seconds (5–15). Longer videos cost more. |
| `resolution` | string | - | `768P` | The native generation resolution. Reference video billing depends on this value. |
| `aspectRatio` | string | - | `adaptive` | The shape of the video. Auto picks a fitting shape. |
| `promptExpansionMode` | string | - | `balanced` | How much to rewrite the prompt before generation. Balanced returns in about a second; quality spends up to ~30s on a richer prompt. |
| `seed` | number | - | - | Optional seed for reproducible results. A random seed is used when omitted. |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_minimax-h3-max-reference-to-video" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'EOF'
{
  "prompt": "A fantasy landscape",
  "duration": 5,
  "resolution": "768P",
  "aspectRatio": "adaptive",
  "promptExpansionMode": "balanced"
}
EOF
```

**Python**

```python
import os
from scenario_sdk import Scenario

client = Scenario(
    api_key=os.environ.get("SCENARIO_SDK_API_KEY"),
    api_secret=os.environ.get("SCENARIO_SDK_API_SECRET"),
)

body = {
    "prompt": "A fantasy landscape",
    "duration": 5,
    "resolution": "768P",
    "aspectRatio": "adaptive",
    "promptExpansionMode": "balanced"
}

response = client.generate.run_model(
    model_id="model_minimax-h3-max-reference-to-video",
    body=body,
)
print(response)
```

**JavaScript**

```javascript
import Scenario from "@scenario-labs/sdk";

const client = new Scenario({
  apiKey: process.env["SCENARIO_SDK_API_KEY"],
  apiSecret: process.env["SCENARIO_SDK_API_SECRET"],
});

const body = {
  "prompt": "A fantasy landscape",
  "duration": 5,
  "resolution": "768P",
  "aspectRatio": "adaptive",
  "promptExpansionMode": "balanced"
};

const response = await client.generate.runModel("model_minimax-h3-max-reference-to-video", { body });
console.info(response);
```

---

## Retrieve Results

After submitting a generation request, you receive a `jobId`. Poll the job until `job.status` is `"success"`. The generated asset IDs are in `job.metadata.assetIds`.

**Endpoint:** `GET https://api.cloud.scenario.com/v1/jobs/{jobId}`

### Example Requests

**cURL**

```bash
curl -X GET "https://api.cloud.scenario.com/v1/jobs/<JOB_ID>" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)"
```

**Python**

```python
job = client.jobs.retrieve(job_id="<JOB_ID>")
print(job.status)
print(job.metadata.asset_ids)
```

**JavaScript**

```javascript
// Option 1 — wait on the response from runModel using the SDK helper
const completed = await response.job.wait();
console.info(completed.status);
console.info(completed.metadata?.assetIds);

// Option 2 — retrieve a job by its ID
const job = await client.jobs.retrieve("<JOB_ID>");
console.info(job.status);
console.info(job.metadata?.assetIds);
```

**Example response:**

```json
{
  "job": {
    "jobId": "job_abc123",
    "status": "success",
    "metadata": {
      "assetIds": [
        "asset_abc123"
      ]
    }
  }
}
```

> **Important:** Generated asset URLs are **temporary** and expire after a short period. Download and store any images you wish to keep before the URL expires. More info: [Content Delivery Network (CDN)](https://docs.scenario.com/get-started/documentation/content-delivery-network-cdn).

---

*Generated by [Scenario](https://app.scenario.com)*