# Wan 3.0 Prime Reference to Video

> Alibaba Wan 3.0 Prime reference-to-video via Fal.AI — the higher-fidelity Wan 3.0 tier. Combines up to 10 reference images, 5 reference video clips, and 5 reference audio clips — each cited in the prompt by position (Image 1, Video 1, Audio 1) — into one coherent video that keeps character identity, style, motion, and sound cues. 2-30 second output at 480p/720p/1080p with optional generated audio.

- **Provider**: fal
- **Model ID**: alibaba/wan-3.0-prime/reference-to-video
- **Category**: video_generation
- **Credits**: from 23,460 for the default configuration — varies by input, see Pricing
- **Pricing Type**: input_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `prompt` (string, **required**): Text prompt directing how the reference media is used. Address references positionally, e.g. 'the subject in Image 1 walks past Video 1'.
- `enable_safety_checker` (boolean, optional): Enable content moderation for input and output. (Default: `true`)
- `aspect_ratio` (string, optional): Output aspect ratio, or 'adaptive' to let the model choose. (Default: `adaptive`; Options: `adaptive`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`)
- `file_url` (string, optional): Document URL to base the video on. Enables enable_thinking automatically.
- `seed` (integer, optional): Random seed for reproducible generation. Random when omitted. (Range: min: 0, max: 2,147,483,647)
- `resolution` (string, optional): Output video resolution tier. (Default: `1080p`; Options: `480p`, `720p`, `1080p`)
- `reference_video_urls` (array, optional): Reference video URLs (motion, camera, scene), cited as Video 1, Video 2, and so on. Up to 5 clips totaling at most 15 seconds, each at least 16 fps. Reference video seconds are billed in addition to the output duration.
- `enable_prompt_expansion` (boolean, optional): Enable intelligent prompt rewriting. Disabling it saves roughly 20-60 seconds of latency but is likely to degrade quality. (Default: `true`)
- `duration` (integer, optional): Output duration in seconds (2-30). Billed per second of output plus any reference video seconds. (Default: `5`; Range: min: 2, max: 30)
- `enable_thinking` (boolean, optional): Enable enhanced reasoning before generation. Turned on automatically when file_url or web_url is provided. (Default: `false`)
- `web_url` (string, optional): Public webpage URL to base the video on (pages behind a login cannot be read). Enables enable_thinking automatically.
- `reference_audio_urls` (array, optional): Reference audio URLs (voice, music, sound cues), cited as Audio 1, Audio 2, and so on. Up to 5 clips totaling at most 15 seconds.
- `audio` (boolean, optional): Include generated audio. Costs the same either way. (Default: `true`)
- `reference_image_urls` (array, optional): Reference image URLs (character, object, or style), cited in the prompt as Image 1, Image 2, and so on. Up to 10 images.

## Example Request

```json
{
  "model": "alibaba/wan-3.0-prime/reference-to-video",
  "input": {
    "duration": 5,
    "aspect_ratio": "adaptive",
    "prompt": "The woman in Image 1 walks along a rainy neon-lit street at night, holding the umbrella from Image 2, cinematic tracking shot.",
    "resolution": "1080p",
    "reference_image_urls": [
      "https://storage.googleapis.com/falserverless/example_inputs/hailuo23/pro_i2v_in.jpg"
    ]
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "fal",
  "model": "alibaba/wan-3.0-prime/reference-to-video",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null,
  "credits_used": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

When the job is `completed`, `result` holds the output URL(s) or data and `credits_used` the net credits charged. When it is `failed`, `error` and `error_code` say why and the charge is refunded.

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Pricing

Charged by input. Rules are checked top to bottom and the first match applies:

- When `resolution` = `480p`: 158.1 credits per second of the input media (measured by the gateway)
- When `resolution` = `720p`: 325.5 credits per second of the input media (measured by the gateway)
- Otherwise: 651 credits per second of the input media (measured by the gateway)

Default configuration: 23,460 credits.

These are list prices. The amount charged is rounded, and large charges are discounted progressively. `POST /predictions/estimate` with the same `model` and `input` returns the charge for that input without creating a job (an estimate when the price depends on the output).

## Output Type

json

## Tags

wan, wan-prime, alibaba, video-generation, reference-to-video, multimodal-reference, character-consistency

## Documentation

https://fal.ai/models/alibaba/wan-3.0-prime/reference-to-video