Alibaba

Wan 3.0 Video

wan3.0-video

Alibaba's new-generation video generation model in the Wan series, capable of producing roughly 30-second 1080p clips in a single pass, supporting reference materials to maintain subject consistency, and the first to support structured document-type inputs

wan3.0-video wan3.0-video-prime

Try wan3.0-video

Input

Audio

Showcases

View all showcases

Output

video

Fill in the parameters and run — results show up here.

Pricing

wan3.0-video per second

Specifications	Unit Price
480P	$0.040
720P	$0.080
1080P	$0.160

Overview

wan3.0-video is a model in the Alibaba Wan series for reference-to-video generation, accessible through the unified HiAPI.ai interface. Conditioned on multimodal reference materials, it can output a single video with audio up to 30 seconds long and up to 1080P, making it suitable for creating advertising shorts, explainer videos, and long narrative segments that require characters, products, or styles to stay consistent across a sequence of shots.

Key Features

Combined multimodal reference conditions — Up to 10 images, 5 videos, and 5 audio clips can serve as generation conditions simultaneously, and the prompt references materials by their array order.
Single-pass narrative up to 30 seconds — Output duration can be set between 2 and 30 seconds; the combined duration of reference videos and output must not exceed 30 seconds.
Structured document and web page input — Supports up to one document or one login-free web page as a reference, turning materials such as PPTs and PDFs into video content.
Controllable first/last frames and audio track toggle — You can specify first-frame and last-frame images separately and choose whether the output includes an audio track synchronized with the visuals.

Capabilities

Multimodal reference generation: Generates video conditioned on images, videos, audio, documents, or web pages, with the prompt pointing to specific materials precisely via indices such as Image1 and Video1, making it easy to control the source of subjects and styles.

First/last frame constraints: Passing first_frame_url and last_frame_url anchors the starting and ending frames of a clip, which is suitable for connecting existing shots or controlling where a transition lands.

Adjustable duration and resolution: Output duration ranges from 2 to 30 seconds, and resolution is selectable from 480P to 1080P; aspect ratios include adaptive and 16:9 among six options, making it easy to match the frame format to the distribution channel.

Synchronized audio track output: By default, the output video includes a synchronized audio track, but the audio track can be disabled for unified post-production dubbing; audio references must be used paired with images or videos.

Reproducible generation: Specifying a seed fixes the random seed, making it easy to reproduce the same result when tuning parameters or generating in batches.

Use Cases

Product-image-to-ad for brand and e-commerce teams — Generate cinematic short videos with product images and reference videos as input, producing videos that can be used directly as ad creative or on product detail pages.
Character-consistent narrative for content teams — Upload character reference images and audio to generate a sequence of shots that keeps the character's appearance consistent, for short dramas or serialized content production.
Training and explainer document-to-video — Use PPTs, PDFs, or login-free web pages as references to produce explainer videos for internal training or product introductions.
Shot extension and completion for existing footage — Use a reference video plus first and last frames to generate connecting clips, filling narrative gaps or extending the duration of already-shot footage.

Limitations and Model Selection Advice

Reference materials have clear limits: at most 10 images, at most 5 videos totaling no more than 15 seconds, at most 5 audio clips of 1 to 15 seconds each, and at most one document and one web page; first-frame mode cannot be used together with the reference materials array. The quality of the prompt's descriptions of subjects, actions, camera, and sound directly affects result stability, so debugging time should be budgeted. Billing is by output seconds, so the cost of combining long durations with high resolution should be evaluated in advance. If only short clips are needed and reference consistency is not required, a lighter video model can be used.

What's new

View changelog →

New model wan3.0-video-prime video generation model now available Nov 3, 2026

Frequently asked questions

View all FAQs →

What type of video model is Wan 3.0 Video?

It is prompt-led and can also use endpoint frames or image, video, and audio references according to the active contract.
Which output settings does Wan 3.0 Video support?

2-30 seconds, 480P, 720P, 1080P, and adaptive, 16:9, 4:3, 1:1, 3:4, 9:16.
Can it generate sound or use audio references?

Optional image, video, audio, file and link references; synchronized audio
How is Wan 3.0 Video billed?

Billing follows output duration and the live tier. Resolution, mode, or audio differences are reflected by the page price and task record.

Create a generation task

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

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: wan3.0-video

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for wan3.0-video and route default — see the parameter table below.

seedintegerOptionalmin 0max 2147483647

Random seed used to reproduce existing generation results; pass a fixed integer when deterministic output is required.

audiobooleanOptionalDefault: true

Whether to also generate an audio track synchronized with the visuals in the output video. Boolean, default true.

promptstringRequiredminLength 1maxLength 20000

Text prompt describing the scene, motion, camera, lighting, and sound; in reference mode, refer to the corresponding assets in array order as Image1, Video1, Audio1.

durationintegerOptionalDefault: 5min 2max 30

Output video duration in seconds, default 5; the sum of the reference video duration and the output duration must not exceed 30 seconds.

resolutionstringOptionalDefault: "1080P"

Output resolution, string, default 1080P.

Options:480P720P1080P

aspect_ratiostringOptionalDefault: "adaptive"

Aspect ratio of the output image, string, default adaptive, meaning it adapts based on the input media and prompt.

Options:adaptive16:94:31:13:49:16

last_frame_urlstringOptional

A publicly accessible image that, together with first_frame_url, specifies the last frame of the video.

first_frame_urlstringOptional

A publicly accessible image used as the first frame of the video; cannot be used together with the reference media array.

reference_file_urlsarrayOptionalmaxItems 1

Array of URLs for reference documents or presentation slides, at most 1, and must be publicly accessible.

Array [ string ]

reference_link_urlsarrayOptionalmaxItems 1

Array of URLs for reference web pages, at most 1, and the web page must be publicly accessible without login.

Array [ string ]

reference_audio_urlsarrayOptionalmaxItems 5

Array of URLs for reference audio, at most 5 clips of WAV or MP3, each 1 to 15 seconds; audio must be used together with images or videos.

Array [ string ]

reference_image_urlsarrayOptionalmaxItems 10

Array of URLs for reference images, at most 10, used for general reference generation.

Array [ string ]

reference_video_urlsarrayOptionalmaxItems 5

Array of URLs for reference videos, at most 5 clips, each 1 to 15 seconds, with a total duration not exceeding 15 seconds.

Array [ string ]

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan3.0-video",
  "input": {
    "audio": true,
    "prompt": "…",
    "duration": 5,
    "resolution": "1080P",
    "aspect_ratio": "adaptive"
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "wan3.0-video",
    input: {
      "audio": true,
      "prompt": "…",
      "duration": 5,
      "resolution": "1080P",
      "aspect_ratio": "adaptive"
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "wan3.0-video",
        "input": {
          "audio": True,
          "prompt": "…",
          "duration": 5,
          "resolution": "1080P",
          "aspect_ratio": "adaptive"
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}