# Minimax H3 Max Insert Video — API Reference

Model ID: `model_minimax-h3-max-insert-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-insert-video`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `video` | assetId | yes | - | The video to insert a new scene into. |
| `prompt` | string | - | - | Describe the new scene to insert. |
| `referenceImages` | assetId[] | - | - | Images to guide subjects or style in the new scene (up to 9). Billed by reference tokens: a square image is 1024 tokens, wider or taller images cost more. |
| `referenceVideos` | assetId[] | - | - | Videos to guide motion in the new scene (up to 3). Billed by reference tokens, by duration (up to ~8s per video) at the output resolution. |
| `startTime` | number | yes | - | Time in the source video, in seconds, where the new scene starts (1.625-60). |
| `resumeTime` | number | yes | - | Time in the source video, in seconds, where the original footage resumes after the new scene (up to 60). |
| `duration` | number | - | `5` | Length of the new scene, in seconds (5-13). Only the new scene is billed. |
| `resolution` | string | - | `768p` | The output quality. Higher resolutions cost more. |
| `colorMatch` | boolean | - | `true` | Match the colors of the new scene to the source video. |
| `enablePromptExpansion` | boolean | - | `true` | Rewrite the prompt using the source video to keep the new scene consistent. May take longer. |
| `seed` | number | - | - | Use a seed for reproducible results. Leave blank for a random seed. |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_minimax-h3-max-insert-video" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'EOF'
{
  "video": "<asset_id>",
  "startTime": 1.625,
  "resumeTime": 1.625,
  "duration": 5,
  "resolution": "768p",
  "colorMatch": true,
  "enablePromptExpansion": true
}
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 = {
    "video": "<asset_id>",
    "startTime": 1.625,
    "resumeTime": 1.625,
    "duration": 5,
    "resolution": "768p",
    "colorMatch": True,
    "enablePromptExpansion": True
}

response = client.generate.run_model(
    model_id="model_minimax-h3-max-insert-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 = {
  "video": "<asset_id>",
  "startTime": 1.625,
  "resumeTime": 1.625,
  "duration": 5,
  "resolution": "768p",
  "colorMatch": true,
  "enablePromptExpansion": true
};

const response = await client.generate.runModel("model_minimax-h3-max-insert-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)*