Open-source products
Build on a model whose weights are public, without running the inference yourself.
Also known as Alibaba Wan 2.5, Wan AI video
Alibaba Wan 2.5 - open-weights AI video with realistic motion and built-in audio, through a simple REST API.
Best for Open-source enthusiasts, audio-inclusive videos, and cost-effective realistic generation.
Access the Wan 2.5 video model via REST API on VideoGenAPI, with endpoints, a live playground and developer docs.
Explore the interface and see how easy it is to generate videos with Wan 2.5. Sign up for free to start creating!
Discover what's possible with Wan 2.5 AI video generation
Generated with the Wan 2.5 API at up to 1080p. Results vary with prompt detail and requested duration.
The Wan 2.5 API is a REST interface that lets developers generate AI videos programmatically using Alibaba's Wan 2.5 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 2.5 API.
Integrate the Wan 2.5 API in your app in under 5 minutes with these four steps.
Sign up free at VideoGenAPI.com and generate your API key from the dashboard. No Alibaba account needed.
POST to https://videogenapi.com/api/v1/generate with your API key, model "wan-25", and a text prompt describing your video.
Use the returned generation_id to poll GET /api/v1/status/{id} until the job completes. Video completion webhooks are not available yet.
Once status is "completed", retrieve the video URL from the response and embed it in your app, website, or workflow.
Wan 2.5 is Alibaba's open-weights video model, part of the Tongyi family. Because the weights are published, it is one of the few frontier-adjacent models you could in principle run yourself, which is why it has a following among teams that dislike depending on closed APIs. In practice, self-hosting means GPU capacity, queueing and upkeep. VideoGenAPI runs it for you and charges per generation, so you get the openness of Wan 2.5 without the infrastructure. It produces 5-10 second clips at up to 1080p with synchronized audio, averaging around 50 seconds.
Build on a model whose weights are public, without running the inference yourself.
Generate scenes that arrive with matching audio for music and mood content.
Add video generation to a product without committing to GPU spend up front.
Quick start guide to integrate Wan 2.5 in your application
| Parameter | Type | Required | Wan 2.5 values |
|---|---|---|---|
| model | string | Yes | "wan-25" |
| 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 | 5 to 10 seconds. Plan caps: 5s Basic, 10s Starter, 15s Unlimited. |
| resolution | string | No | 480p, 720p, 1080p. Plan caps: 480p Basic, 720p Starter, 1080p Unlimited. |
| 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 2.5 generates native audio with the video. |
Average generation time: ~50s. Poll GET /api/v1/status/{id} with the returned generation_id. Full reference: /docs/generate.
{
"model": "wan-25",
"prompt": "Street musician playing guitar in a rainy alley, reflections on wet pavement, acoustic guitar audio",
"duration": 10,
"resolution": "480p"
}
{
"success": true,
"generation_id": "gen_abc123xyz",
"status": "in_progress",
"estimated_time": 50}
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-25',
prompt: 'Street musician playing guitar in a rainy alley, reflections on wet pavement, acoustic guitar audio',
duration: 10 })
});
const data = await response.json();
console.log(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-25",
"prompt": "Slow push in, soft natural light, subtle movement",
"image_url": "https://example.com/your-image.jpg",
"duration": 5
}'
Wan 2.5 is billed per video, not per second of output. See the cost calculator for your volume.
per Wan 2.5 video on the Starter plan
| Plan | Monthly | Videos | Cost / video | Max output |
|---|---|---|---|---|
| Basic | $29 | 1,500 | $0.019 | 480p, 5s |
| Starter | $49 | 4,500 | $0.011 | 720p, 10s |
| Unlimited | $199 | No cap | Flat | 1080p, 15s |
How the Wan 2.5 API compares on resolution, clip length, generation speed and price. All models below share one API key.
| Model | Provider | Max resolution | Clip length | Avg. speed | Price / video |
|---|---|---|---|---|---|
| Wan 2.5 API This page | Alibaba | 1080p | 5-10s | ~50s | Included, from $0.011 |
| LTX-2 API | Lightricks | 4K | 6-10s | ~30s | Included, from $0.011 |
| Veo 2 API | Google DeepMind | 1080p | 10s | ~110s | Included, from $0.011 |
| MiniMax H3 API | MiniMax | 1080p | 5-15s | ~88s | Included, from $0.011 |
Switching between these models means changing the wan-25
value in your request body. The endpoint, authentication and status polling stay the same.
Create a key and call the Wan 2.5 API in minutes, plus 15 other models on the same endpoint.
Free account · Plans from $29/mo · Cancel anytime