Wan 3.0 Prime Video API

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	wan3.0-video-prime
Type	Video generation (all-purpose reference, fast)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

Wan 3.0 Prime fast video generation API for text, first/last frames, reference images, audio, files, and webpages, with 480P, 720P, or 1080P output and optional synchronized audio.

Production guidance

The submission returns a taskId immediately; use callback.url for terminal notifications in production.
Poll GET /v1/tasks/:id for local debugging or callback reconciliation.
First/last-frame mode cannot be combined with reference arrays. Reference video input is not available yet.

Best suited for

Fast text-to-video clips

Describe the complete scene, motion, and camera in the prompt and get the clip back with a shorter wait.

prompt

Image and audio references

Combine image or audio references and address them in order in the prompt.

promptreference_image_urlsreference_audio_urls

First/last-frame transitions

Control the beginning and ending frames with two images.

first_frame_urllast_frame_url

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan3.0-video-prime",
  "input": {
    "prompt": "A glass of iced matcha latte on a sunlit café table; a slow push-in as condensation drips down the glass and a wooden spoon stirs, soft bokeh, warm morning light, gentle café ambience.",
    "resolution": "480P",
    "aspect_ratio": "16:9",
    "duration": 2,
    "audio": true
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "wan3.0-video-prime",
  "input": {
    "prompt": "A glass of iced matcha latte on a sunlit café table; a slow push-in as condensation drips down the glass and a wooden spoon stirs, soft bokeh, warm morning light, gentle café ambience.",
    "resolution": "480P",
    "aspect_ratio": "16:9",
    "duration": 2,
    "audio": true
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "wan3.0-video-prime",
  "input": {
    "prompt": "A glass of iced matcha latte on a sunlit café table; a slow push-in as condensation drips down the glass and a wooden spoon stirs, soft bokeh, warm morning light, gentle café ambience.",
    "resolution": "480P",
    "aspect_ratio": "16:9",
    "duration": 2,
    "audio": true
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value wan3.0-video-prime.

example wan3.0-video-prime

input object required

Model input parameters.

prompt string required

Describe the scene, motion, camera, lighting, and sound. In reference mode, use Image1 or Audio1 in the order of the supplied arrays.

first_frame_url string optional

One publicly reachable image used as the first frame. Do not combine with reference media arrays.

example https://example.com/first-frame.jpg

last_frame_url string optional

One publicly reachable image used as the last frame together with first_frame_url.

example https://example.com/last-frame.jpg

reference_image_urls string[] optional

Up to 10 publicly reachable reference image URLs for all-purpose reference generation.

example ["https://example.com/reference.jpg"]

reference_audio_urls string[] optional

Up to 5 WAV or MP3 reference audio URLs. Pair audio with an image.

example ["https://example.com/voice.mp3"]

reference_file_urls string[] optional

At most one publicly reachable document or presentation URL. Do not combine with reference_link_urls.

example ["https://example.com/brand-guide.pdf"]

reference_link_urls string[] optional

At most one publicly reachable webpage URL that does not require login. Do not combine with reference_file_urls.

example ["https://example.com/product-page"]

resolution enum optional

Output video resolution.

default 1080P enum: 480P720P1080P

aspect_ratio enum optional

Output aspect ratio; adaptive follows the media and prompt.

default adaptive enum: adaptive16:94:31:13:49:16

duration integer optional

Output duration in seconds, from 2 to 30.

default 5

audio boolean optional

Include a synchronized audio track in the output video.

default true example false

seed integer optional

Fixed random seed for reproducible results, from 0 to 2147483647.

callback object optional

Optional terminal-state callback configuration.

url string required

HTTPS URL that receives terminal task notifications.

when enum optional

Callback trigger timing.

default final enum: final

Example requests

Two-second text-to-video

A low-resolution example sourced from the verified golden task.

Request body

{
  "model": "wan3.0-video-prime",
  "input": {
    "prompt": "A glass of iced matcha latte on a sunlit café table; a slow push-in as condensation drips down the glass and a wooden spoon stirs, soft bokeh, warm morning light, gentle café ambience.",
    "resolution": "480P",
    "aspect_ratio": "16:9",
    "duration": 2,
    "audio": true
  }
}

Portrait reference generation

Place public media URLs in the matching array and refer to them in the prompt.

Request body

{
  "model": "wan3.0-video-prime",
  "input": {
    "prompt": "The subject from Image1 walks toward the camera on a rainy night street.",
    "reference_image_urls": [
      "https://example.com/reference.jpg"
    ],
    "resolution": "720P",
    "aspect_ratio": "9:16",
    "duration": 5,
    "audio": true
  }
}

First/last-frame transition

Control the opening and closing frames with two images and fix the seed for reproducibility. First/last-frame mode cannot be combined with reference_* arrays. Replace the example URLs with publicly accessible images.

Request body

{
  "model": "wan3.0-video-prime",
  "input": {
    "prompt": "A flower bud slowly opens into full bloom in the morning sun, static camera, soft natural light, a light breeze.",
    "first_frame_url": "https://example.com/first-frame.jpg",
    "last_frame_url": "https://example.com/last-frame.jpg",
    "resolution": "720P",
    "aspect_ratio": "16:9",
    "duration": 5,
    "audio": true,
    "seed": 42
  }
}

Reference image + audio + document

The reference image supplies the presenter's look, the reference audio supplies the voice, and the document supplies brand information; the prompt refers to media in order as Image1 and Audio1. Use either reference_file_urls or reference_link_urls, not both. Replace the example URLs with publicly accessible media.

Request body

{
  "model": "wan3.0-video-prime",
  "input": {
    "prompt": "The presenter from Image1 introduces a new product to the camera in a bright studio, speaking in the voice from Audio1, styled to match the brand guidelines in the document.",
    "reference_image_urls": [
      "https://example.com/reference.jpg"
    ],
    "reference_audio_urls": [
      "https://example.com/voice.mp3"
    ],
    "reference_file_urls": [
      "https://example.com/brand-guide.pdf"
    ],
    "resolution": "1080P",
    "aspect_ratio": "16:9",
    "duration": 8,
    "audio": true
  }
}

Reference image + webpage

The reference image supplies the product's look and the webpage supplies product details; the page must be reachable without login. Replace the example URLs with publicly accessible media.

Request body

{
  "model": "wan3.0-video-prime",
  "input": {
    "prompt": "The product from Image1 rotates slowly on a plain background, with close-ups of the details highlighted on the webpage.",
    "reference_image_urls": [
      "https://example.com/reference.jpg"
    ],
    "reference_link_urls": [
      "https://example.com/product-page"
    ],
    "resolution": "720P",
    "aspect_ratio": "1:1",
    "duration": 5,
    "audio": false
  }
}

Getting the result

POST /v1/tasks returns a taskId immediately.
When the task succeeds, download the video from output[].url.
When it fails, fix the request from the error message instead of repeating the same invalid payload.

FAQ

How do I retrieve the result?

Use the returned taskId. On success, download the video from output[].url or receive a terminal callback at callback.url.

Can first-frame input be combined with reference images?

First/last-frame mode and reference_* arrays are mutually exclusive. Choose the mode that matches the media role.

How does it differ from wan3.0-video?

Prime is the fast route with the same parameters and output options and shorter generation time; it currently does not accept reference video input.

Wan 3.0 Prime Video API

Model summary

Production guidance

Best suited for

Request parameters

Example requests

Getting the result

FAQ

How do I retrieve the result?

Can first-frame input be combined with reference images?

How does it differ from wan3.0-video?

Next steps