# Wan 3.0 Image to Video

Turn images into video with Wan 3.0 Image to Video from fal through one Spiral API key. Wan 3.0 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence. It runs in the background and returns video. Pay as you go, with no subscription.

- Provider: fal
- Category: Video
- Runs: In the background
- Returns: video
- Released: 2026-08-03
- Tool id: `fal` / `alibaba/wan-3.0/image-to-video`
- Page: https://spiral.ai/tools/fal/alibaba/wan-3.0/image-to-video

## Pricing

`resolution`: 480p $0.065, 720p $0.13, 1080p (default) $0.26 per second. Billed on `duration`, default 5.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 1 hour
- Longest run, end to end: 930 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `prompt` | text |  | — | Text prompt describing the motion to generate. |
| `resolution` | one of | 480p, 720p, 1080p | 1080p | Output video resolution tier. |
| `aspect_ratio` | one of | adaptive, 16:9, 4:3, 1:1, 3:4, 9:16 | adaptive | Output aspect ratio, or adaptive selection. |
| `duration` | number (whole) | 2 to 30 | 5 | Output duration in seconds. Set to null for smart duration, which lets the model pick a length from the prompt and reference media. |
| `audio` | true or false |  | true | Include generated audio. |
| `enable_prompt_expansion` | true or false |  | true | Enable intelligent prompt rewriting. Disabling it can save roughly 20-60 seconds of latency but is likely to degrade generation quality. |
| `enable_thinking` | true or false |  | false | Enable enhanced reasoning before generation. |
| `seed` | number (whole) | 0 to 2147483647 | — |  |
| `start_image_url` (required) | URL or file |  | — | First frame of the generated video. |
| `end_image_url` | URL or file |  | — | Last frame of the generated video. Requires start_image_url. |

## Example

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "alibaba/wan-3.0/image-to-video",
    "input": {
      "start_image_url": "<start_image_url>"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=fal&model=alibaba%2Fwan-3.0%2Fimage-to-video

## Common questions

### Wan 3.0 Image to Video

**How much does Wan 3.0 Image to Video cost?**

`resolution`: 480p $0.065, 720p $0.13, 1080p (default) $0.26 per second. Billed on `duration`, default 5. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Wan 3.0 Image to Video through an API?**

Send `POST /v1/runs` with `"provider": "fal"`, `"model": "alibaba/wan-3.0/image-to-video"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with fal to use Wan 3.0 Image to Video?**

No. Spiral runs it on its own fal account and charges your Spiral balance.

**Can my AI agent use Wan 3.0 Image to Video?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

