# Vidu Q4 Reference to Video API

> Vidu Q4 Preview by Shengshu builds a 3 to 16 second video at up to 4K from up to 12 reference images and 3 voice clips, keeping characters, products, and voices consistent across the clip.

Source: https://www.sandbase.ai/models/vidu/q4/reference-to-video
API reference: https://www.sandbase.ai/models/vidu/q4/reference-to-video/docs

## Facts

- Provider: Vidu
- Type: Video model
- Model ID: `vidu/q4/reference-to-video`
- Price: From $0.47 per run
- Capabilities: reference to video
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

- Unified Run API: `POST https://api.sandbase.ai/v1/run`

```bash
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "vidu/q4/reference-to-video",
  "audio": true,
  "prompt": "[@reference_image_1] walks along the beach at sunset holding [@reference_image_2], then turns to the camera and smiles.",
  "duration": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "reference_image_urls": [
    "https://storage.googleapis.com/falserverless/web-examples/vidu/new-examples/reference1.png",
    "https://storage.googleapis.com/falserverless/web-examples/vidu/new-examples/reference2.png"
  ]
}'
```

The response returns a run id; poll `GET https://api.sandbase.ai/v1/run/{id}` until the status is `completed` or `failed`.

## FAQ

### How do I call Vidu Q4 Reference to Video through SandBase?

Create a SandBase API key, then send requests with the model ID "vidu/q4/reference-to-video" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

### Do I need a separate Vidu account?

No. One SandBase API key and balance gives you access to Vidu Q4 Reference to Video and the other models in the catalog; you do not need to sign up with Vidu separately.

## README

### Vidu Q4 Reference to Video

Vidu Q4 Preview reference-to-video: build a 3–16 second clip at up to 4K from up to 12 reference images and 3 voice clips, keeping characters, products, and voices consistent.

#### Fields

| Field | Type | Default | Notes |
|---|---|---|---|
| `prompt` | string, required | — | Up to 5,000 characters. Tag references as `[@reference_image_1]` and `[reference_audio_1]`. |
| `reference_image_urls` | image URL[], required | — | 1–12 images of characters, products, objects, or locations. |
| `reference_audio_urls` | audio URL[] | — | Up to 3 mp3 clips, 3–12 seconds each, for voice consistency. |
| `aspect_ratio` | `16:9` / `9:16` / `4:3` / `3:4` / `1:1` | `16:9` | Output frame shape. |
| `audio` | boolean | true | Generate dialogue and sound effects. Same price on or off. |
| `resolution` | `540p` / `720p` / `1080p` / `2K` / `4K` | `720p` | Sets the per-second rate. |
| `duration` | integer 3–16 | 5 | Output length in seconds. |
| `seed` | integer | random | Fix it to compare prompt changes. |

#### Billing

You pay for output seconds: $0.045 at 540p, $0.095 at 720p, $0.12 at 1080p, $0.19 at 2K, $0.39 at 4K.

| Output | 540p | 720p | 1080p | 2K | 4K |
|---|---|---|---|---|---|
| 3s | $0.135 | $0.285 | $0.36 | $0.57 | $1.17 |
| 5s (default) | $0.225 | $0.475 | $0.60 | $0.95 | $1.95 |
| 8s | $0.36 | $0.76 | $0.96 | $1.52 | $3.12 |
| 16s | $0.72 | $1.52 | $1.92 | $3.04 | $6.24 |

Failed runs are not charged.

#### Prompting

- Refer to each reference by its position in the list, for example `[@reference_image_2]` holds the product.
- Describe subject, action, camera, and sound. Put spoken lines in quotes.

#### Also on SandBase

`vidu/q4/image-to-video` animates a single first frame. Vidu Q3 endpoints such as `vidu/q3/reference-to-video/mix` remain available.