# Wan 3.0 — API Reference

Model ID: `model_alibaba-wan-3-0`

---

## 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_alibaba-wan-3-0`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `prompt` | string | yes | - | Describe the video you want. When you add reference files, refer to them in your text as "Image 1," "Video 1," "Audio 1" — numbered separately per type, in the order you added each list. |
| `image` | assetId | - | - | An optional opening frame for the video. Required if you set a last frame. Can't be combined with reference images, videos, or audio. |
| `endImage` | assetId | - | - | An optional closing frame. Only works when a first frame is also set. Can't be combined with reference inputs. |
| `referenceImages` | assetId[] | - | - | Images to guide the subjects or style (up to 10, 20MB each). Can't be combined with a first or last frame. |
| `referenceVideos` | assetId[] | - | - | Videos to guide the motion (up to 5, 100MB each, 15s combined). Can't be combined with a first or last frame. |
| `referenceAudios` | assetId[] | - | - | Audio to guide the video (up to 5, 15MB each, 15s combined). Can't be combined with a first or last frame. |
| `document` | assetId | - | - | An optional document to generate a video from (up to 100MB or 50 pages). Turns on thinking mode automatically for richer results. |
| `link` | string | - | - | A public https:// web page URL to generate from. Must be reachable without authentication. Turns on thinking mode automatically. |
| `resolution` | string | - | `720P` | The output quality. 1080P is sharpest but costs more; 480P is cheapest. |
| `aspectRatio` | string | - | `adaptive` | The shape of the video. Adaptive follows your input media if you provide any, otherwise defaults to widescreen (16:9). |
| `duration` | number | - | `5` | How long the clip lasts, in seconds (2-30), or Smart to let Wan choose. Longer clips cost more. |
| `audio` | boolean | - | `true` | Adds a soundtrack to the video. On by default; costs the same either way. |
| `enableThinking` | boolean | - | `false` | Let Wan reason about the request before generating. Required for document or link input (turned on automatically when either is provided). |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_alibaba-wan-3-0" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'EOF'
{
  "prompt": "A fantasy landscape",
  "resolution": "720P",
  "aspectRatio": "adaptive",
  "duration": 5,
  "audio": true,
  "enableThinking": false
}
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",
    "resolution": "720P",
    "aspectRatio": "adaptive",
    "duration": 5,
    "audio": True,
    "enableThinking": False
}

response = client.generate.run_model(
    model_id="model_alibaba-wan-3-0",
    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",
  "resolution": "720P",
  "aspectRatio": "adaptive",
  "duration": 5,
  "audio": true,
  "enableThinking": false
};

const response = await client.generate.runModel("model_alibaba-wan-3-0", { 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)*