Wan 3.0 API

Name: Wan 3.0 API - Example AI Video
Uploaded: 2026-11-05
Description: Sample video generated with the Wan 3.0 API on VideoGenAPI

Interactive demo

Try Wan 3.0 right now

Explore the interface and see how easy it is to generate videos with Wan 3.0. Create an account and pick a plan to start generating.

Playground Demo - Wan 3.0

Demo Mode

Describe your video *

magic_button AI Powered

Be specific for best results 0/1000

Generation Type

Video Settings

Sign up to generate videos

Create a free account to access the full playground and generate videos with Wan 3.0 on a monthly plan.

timer ~150s generation

rocket_launch Get Started Free

Demo Preview

Demo Mode

Wan 3.0

by Alibaba

Wan 3.0 by Alibaba: text-to-video and image-to-video with native audio, 2 to 30 seconds at 480p, 720p or 1080p. Billed per second from your balance: $0.10/s at 480p, $0.20/s at 720p, $0.40/s at 1080p.

1080p • 2-30s • ~150s processing

Gallery

Wan 3.0 examples

Discover what's possible with Wan 3.0 AI video generation

A street musician plays a warm jazz melody on a saxophone under a neon sign in light rain at night, close-up on her face, she smiles at the passing crowd, ambient city sounds

Generated with the Wan 3.0 API at up to 1080p. Results vary with prompt detail and requested duration.

What is the Wan 3.0 API?

The Wan 3.0 API is a REST interface that lets developers generate AI videos programmatically using Alibaba's Wan 3.0 model. It supports text-to-video, image-to-video through a single POST endpoint. VideoGenAPI handles authentication, billing, and provider infrastructure - you only need one API key to start building with the Wan 3.0 API.

Alibaba

Provider

REST

API protocol

~150s

Avg. generation

How to use the Wan 3.0 API

Integrate the Wan 3.0 API in your app in under 5 minutes with these four steps.

1

Create your VideoGenAPI account

Sign up free at VideoGenAPI.com and generate your API key from the dashboard. No Alibaba account needed.
2

Send a request to the Wan 3.0 API

POST to https://videogenapi.com/api/v1/generate with your API key, model "wan-3", and a text prompt describing your video.
3

Poll for completion

Use the returned generation_id to poll GET /api/v1/status/{id} until the job completes. Video completion webhooks are not available yet.
4

Download your video

Once status is "completed", retrieve the video URL from the response and embed it in your app, website, or workflow.

Get your Wan 3.0 API key

Documentation

About Wan 3.0

info Overview

Wan 3.0 is Alibaba's newest video model. It entered public beta on August 6, 2026 and was released on August 24, doubling the 15-second limit of Wan 2.7 to 30 seconds per generation. It generates sound with the picture and is tuned for realistic faces, with expressions that follow the dialogue. Unlike earlier Wan flagships, Wan 3.0 has no open weights: it is only available as a hosted API. On VideoGenAPI you call it with the same endpoint and key as every other model, without an Alibaba Cloud account. It handles text-to-video and image-to-video (with an optional end frame) from 2 to 30 seconds at 480p, 720p or 1080p, in six aspect ratios including adaptive framing. Wan 3.0 is billed per second from your balance: $0.10 at 480p, $0.20 at 720p and $0.40 at 1080p. For the launch details, see Wan 3.0 API is live on VideoGenAPI (/blog/wan-3-api-launch); for the release and the open-source question, Alibaba Wan 3.0 (/blog/wan-3-0-release).

stars Key Strengths

check_circle Up to 30 seconds in one generation, from 2 seconds for quick loops
check_circle Native audio generated with the video, on by default
check_circle Text-to-video and image-to-video with an optional end frame
check_circle 480p, 720p or 1080p, six aspect ratios including adaptive
check_circle Per-second billing from your balance, refunded if a generation fails

check_circle Supported Features

Text to Video
Image to Video

settings Specifications

Max Resolution: 1080p
Duration Range: 2-30s
Avg. Processing: ~150s

workspace_premium Why Wan 3.0 via VideoGenAPI?

check_circle
Unified API: Access Wan 3.0 alongside 18 other models with one API key - no separate Alibaba setup.
check_circle
Per-second pricing: $0.10 per second at 480p, $0.20 at 720p and $0.40 at 1080p, from your balance on top of a monthly plan. Failed generations are refunded.
check_circle
Production-ready: one REST endpoint, status polling, an MCP server for AI agents, and full docs.

Use cases

What you can build with Wan 3.0

1

Product demos and explainers

Carry a full walkthrough or reveal in one 20 to 30 second shot, without stitching clips.

2

Talking characters

Presenters, testimonials and short scenes where faces and voice need to stay in sync.

3

Controlled transitions

Pin the first and last frame to land exactly on a logo, a packshot or the next scene.

API reference

Wan 3.0 API documentation

Quick start guide to integrate Wan 3.0 in your application

code Endpoint

POST https://videogenapi.com/api/v1/generate

tune Wan 3.0 API parameters

Request parameters accepted by the Wan 3.0 API on POST /api/v1/generate
Parameter	Type	Required	Wan 3.0 values
model	string	Yes	`"wan-3"`
prompt	string	Yes	Scene description, up to 1,000 characters.
image_url	string	No	Public jpg, png, gif or webp URL. Animates the image (image-to-video).
duration	integer	No	2 to 30 seconds, up to 15s on every plan.
resolution	string	No	480p, 720p, 1080p.
aspect_ratio	string	No	16:9, 4:3, 1:1 or 9:16 (text-to-video).
seed	integer	No	Fixed value for reproducible output, -1 for random.
add_audio	boolean	No	Wan 3.0 generates native audio with the video.

Average generation time: ~150s. Poll GET /api/v1/status/{id} with the returned generation_id. Full reference: /docs/generate.

send Request Example

{
  "model": "wan-3",
  "prompt": "A street musician plays a warm jazz melody on a saxophone under a neon sign in light rain at night, close-up on her face, she smiles at the passing crowd, ambient city sounds",
  "duration": 10,
  "resolution": "480p"
}

download Response Example

{
  "success": true,
  "generation_id": "gen_abc123xyz",
  "status": "in_progress",
  "estimated_time": 150}

integration_instructions Code Examples

const response = await fetch('https://videogenapi.com/api/v1/generate', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer YOUR_API_KEY'
  },
  body: JSON.stringify({
    model: 'wan-3',
    prompt: 'A street musician plays a warm jazz melody on a saxophone under a neon sign in light rain at night, close-up on her face, she smiles at the passing crowd, ambient city sounds',
    duration: 10  })
});

const data = await response.json();
console.log(data.generation_id);

import requests

response = requests.post(
    'https://videogenapi.com/api/v1/generate',
    headers={
        'Content-Type': 'application/json',
        'Authorization': 'Bearer YOUR_API_KEY'
    },
    json={
        'model': 'wan-3',
        'prompt': 'A street musician plays a warm jazz melody on a saxophone under a neon sign in light rain at night, close-up on her face, she smiles at the passing crowd, ambient city sounds',
        'duration': 10    }
)

data = response.json()
print(data['generation_id'])

$ch = curl_init('https://videogenapi.com/api/v1/generate');
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, [
    'Content-Type: application/json',
    'Authorization: Bearer YOUR_API_KEY'
]);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode([
    'model' => 'wan-3',
    'prompt' => 'A street musician plays a warm jazz melody on a saxophone under a neon sign in light rain at night, close-up on her face, she smiles at the passing crowd, ambient city sounds',
    'duration' => 10]));

$response = curl_exec($ch);
$data = json_decode($response, true);
echo $data['generation_id'];

curl -X POST https://videogenapi.com/api/v1/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "wan-3",
    "prompt": "A street musician plays a warm jazz melody on a saxophone under a neon sign in light rain at night, close-up on her face, she smiles at the passing crowd, ambient city sounds",
    "duration": 10  }'

Wan 3.0 image-to-video request

curl -X POST https://videogenapi.com/api/v1/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "wan-3",
    "prompt": "Slow push in, soft natural light, subtle movement",
    "image_url": "https://example.com/your-image.jpg",
    "duration": 5
  }'

View Full Documentation arrow_forward

Pricing

Wan 3.0 API pricing

Wan 3.0 is billed per video, not per second of output. See the cost calculator for your volume.

$0.20/s

per second of video at 720p ($0.40/s at 1080p) via the Wan 3.0 API

check_circle One API key for Wan 3.0 and 18 other models
check_circle No Alibaba account required
check_circle Billed per video, never per second of output

Start with the Wan 3.0 API

Comparison

Wan 3.0 API vs alternatives

How the Wan 3.0 API compares on resolution, clip length, generation speed and price. All models below share one API key.

Comparison of the Wan 3.0 API against alternative AI video generation models on VideoGenAPI
Model	Provider	Max resolution	Clip length	Avg. speed	Price / video
Wan 3.0 API This page	Alibaba	1080p	2-30s	~150s	$0.10/s
Seedance 2.5 API	ByteDance	1080p	5-30s	~150s	Included, from $0.011
FLUX 3 Max API	Black Forest Labs	1080p	5-20s	~12s	$0.25/s
Kling 3.0 API	Kuaishou	1080p	5-10s	~250s	Included, from $0.011

Switching between these models means changing the wan-3 value in your request body. The endpoint, authentication and status polling stay the same.

Limits

Wan 3.0 API limitations

Plan duration and resolution caps apply even when the model supports higher output. See pricing.
Jobs are asynchronous: poll GET /api/v1/status/{id}. Video completion webhooks are not available yet.
Rate limits and fair-use throttling are documented on /docs/rate-limits.
Prompts and images that violate the content guidelines are rejected.
This model is billed per generation on top of the monthly plan ($0.50/video).

Text-to-video API hub Image-to-video API hub Catalogue benchmark Generate endpoint docs

Reviewed by Enzo Lanne · Founder, VideoGenAPI · Updated 5 November 2026

FAQ

Wan 3.0 API questions

What is Wan 3.0? expand_more

Wan 3.0 is Alibaba's video generation model released on August 24, 2026. It generates up to 30 seconds of video with native audio from a prompt or from images. It is only available as a hosted API; no weights were published.

How do I call Wan 3.0 on VideoGenAPI? expand_more

Send POST /api/v1/generate with "model": "wan-3", a prompt, a duration from 2 to 30 seconds and an optional resolution ("480p", "720p" or "1080p"). Add "image_url" for image-to-video and "end_image_url" for a last frame.

Does Wan 3.0 generate audio? expand_more

Yes. Audio is generated with the video by default. Set "generate_audio": false to get a silent clip.

How long can a Wan 3.0 video be? expand_more

From 2 to 30 seconds per generation, at 480p, 720p or 1080p.

Are failed Wan 3.0 generations charged? expand_more

No. If a Wan 3.0 generation fails, the amount is refunded to your balance automatically.

Do I need an Alibaba Cloud account? expand_more

No. VideoGenAPI handles access to Wan 3.0; you only need your VideoGenAPI key and enough balance for the clip.

How much does one Wan 3.0 API video cost? expand_more

Wan 3.0 is billed per second of output from your VideoGenAPI balance: $0.10 per second at 480p, $0.20 at 720p and $0.40 at 1080p, so a 10-second 720p clip costs $2.00. You need a monthly plan (from $29) for API access; failed generations are refunded to your balance.

Related models

Compare with other AI video models

Explore alternative models for different quality, speed, and budget needs.

Seedance 2.5 API

ByteDance

Seedance 2.5 is a state-of-the-art AI video generation model designed to create cinematic, high-quality videos from text and image prompts with advanced motion, strong scene continuity, and professional creative control.

Seedance 2.5 API docs arrow_forward

FLUX 3 Max API

Black Forest Labs

FLUX 3 Max by Black Forest Labs: text-to-video and image-to-video with native audio, 5 to 20 seconds at 720p or 1080p. Billed per second from your balance: $0.25/s at 720p, $0.40/s at 1080p.

FLUX 3 Max API docs arrow_forward

Kling 3.0 API

Kuaishou

Kling 3: Top-tier text-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.

Kling 3.0 API docs arrow_forward