Wan 3.0 — From 2-second loops to 30-second scenes
Wan 3.0 covers the widest duration range on MakerNice, from 2 to 30 seconds, at 480p, 720p (the default) or 1080p. It supports text-to-video, image-to-video, first and last frame, and reference-to-video with up to 10 reference images.
Highlights
2–30 s · 480p / 720p / 1080p · Text to video · Image to video · First and last frame · Reference to video
Best for
Projects that need very short or very long clips from one model, plus reference-image control.
Input
Text, first frame, last frame, up to 10 reference images
Output
Video
Checking your session…
Pricing
Prepaid in US dollars. We hold the quoted amount while it runs and charge it only on delivery — failed runs are free.
Cost of your first test
$0.1972
One 5-second clip at the lowest-cost settings.
What your top-up buys
Top up$10
≈ 50 test runs
$50
≈ 253 test runs
$100
≈ 506 test runs
| Model | Mode | Resolution | Our price | Official | You save |
|---|---|---|---|---|---|
Wan 3.0 Alibaba | Text to video | 480p | $0.0394/s | $0.05/s | -21% |
Wan 3.0 Alibaba | Text to video | 720p | $0.0789/s | $0.10/s | -21% |
Wan 3.0 Alibaba | Text to video | 1080p | $0.1578/s | $0.20/s | -21% |
Wan 3.0 Alibaba | Image to video | 480p | $0.0394/s | $0.05/s | -21% |
Wan 3.0 Alibaba | Image to video | 720p | $0.0789/s | $0.10/s | -21% |
Wan 3.0 Alibaba | Image to video | 1080p | $0.1578/s | $0.20/s | -21% |
Wan 3.0 Alibaba | First and last frame | 480p | $0.0394/s | $0.05/s | -21% |
Wan 3.0 Alibaba | First and last frame | 720p | $0.0789/s | $0.10/s | -21% |
Wan 3.0 Alibaba | First and last frame | 1080p | $0.1578/s | $0.20/s | -21% |
Wan 3.0 Alibaba | Reference to video | 480p | $0.0394/s | $0.05/s | -21% |
Wan 3.0 Alibaba | Reference to video | 720p | $0.0789/s | $0.10/s | -21% |
Wan 3.0 Alibaba | Reference to video | 1080p | $0.1578/s | $0.20/s | -21% |
What is the Wan 3.0 API?
The Wan 3.0 API provides Alibaba's Wan 3.0 video model through one MakerNice API key. Its duration range of 2 to 30 seconds is the widest on the platform, and text-to-video accepts an adaptive aspect ratio in addition to 16:9, 9:16, 1:1, 4:3 and 3:4. Wan 3.0 Prime is the higher-tier model with the same published parameters.
4 ways to generate, one endpoint
Set mode, send the inputs it needs — that's it.
Text to video
mode: "t2v" · prompt
Just a prompt — the model builds the shot from scratch.
Image to video
mode: "i2v" · image_url
Send an image in image_url and it becomes the opening frame.
First and last frame
mode: "flf" · image_url + last_image_url
Set the first and last frame; the model animates everything in between.
Reference to video
mode: "r2v" · reference_images (≤ 10)
Add up to 10 reference images to lock in characters, products and style.
What you can build with this model
Workflows this model is a good fit for.
Quick loops and micro-clips
Generate 2 or 3 second clips for UI backgrounds, stickers and animated loops.
Try it in the playgroundLong-form sequences
Produce up to 30 seconds in a single request for scenes that should not be cut.
Try it in the playgroundMulti-reference compositions
Combine up to 10 reference images for scenes with several characters or props.
Try it in the playgroundWhy run Wan 3.0 on MakerNice
Quote before you pay
Every run gets an exact quote first, locked for 12 minutes. You're charged that amount — never more.
Failed runs are free
We hold the amount while the model runs and charge only on delivery. Failures and queued cancellations cost nothing.
Switch models with one field
Same request, key, balance and console for all 16 models. Not happy with the result? Change model and run it again.
Which should you pick: Wan 3.0, Wan 3.0 Prime?
Compare modes, length, resolution and references, then run the same prompt on each.
| Wan 3.0 | Wan 3.0 Prime | |
|---|---|---|
| Modes | Text to video · Image to video · First and last frame · Reference to video | Text to video · Image to video · First and last frame · Reference to video |
| Duration | 2–30 s | 2–30 s |
| Resolution | 480p / 720p / 1080p | 480p / 720p / 1080p |
| Reference images | Up to 10 | Up to 10 |
| Audio | — | — |
| Starting price | $0.0394/s | $0.0617/s |
Integrate Wan 3.0 in three steps
Step 1
Create an API key
Sign in, top up and create a key in the console. Set a spend limit per key so nothing runs away.
OpenStep 2
Quote and create
POST the input to /v1/generations/quote with the model field set to wan-3.0, then create the generation with the quote id.
OpenStep 3
Poll the result
GET /v1/generations/{id} until the status is succeeded, then download the output.
OpenDocs/API/WAN-3-0
API reference
Copy-paste requests for this model. The full parameter reference is in the docs.
curl https://api.makernice.com/v1/generations/quote \
-H "Authorization: Bearer $MAKERNICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-3.0",
"mode": "t2v",
"prompt": "A lantern festival on a river at dusk, hundreds of glowing lanterns drifting past, camera floating above the water.",
"duration": 5,
"resolution": "720p"
}'Invalid request
400 invalid_request names each failing field. Fields the mode doesn't use are rejected too. Nothing is held.
Key or balance
401 means a missing or invalid key; 402 means the balance or the key's spend limit isn't enough.
Quote problems
A changed price-affecting field returns 422 quote_mismatch; an expired quote 410; a used one 409. Get a new quote.
Failed generation
A failed generation is never charged — the hold is released in full. Keep the generation id and retry when you're ready.
Frequently asked questions
Common questions about this model.
What is Wan 3.0?
How long can Wan 3.0 videos be?
How many reference images does Wan 3.0 support?
How much does Wan 3.0 cost per second?
Wan 3.0 vs Wan 3.0 Prime: which should I use?
Can I let the model choose the aspect ratio?
More Posts
Related models
Compare all modelsSimilar models worth comparing.
VideoWan 3.0 Prime
-9%Wan 3.0's premium tier for final renders — same 2–30 seconds, 480p–1080p and 10 references. Explore on Wan 3.0, finish here.
VideoSeedance 2.5
ByteDance's flagship for long takes: up to 30 seconds, 480p to 4K, and up to 16 reference images to keep every shot on-model.
VideoSeedance 2.0
The all-rounder for ads and social: 4–15 second clips at 720p or 1080p from text, a still, first and last frames, or up to 9 references.
VideoSeedance 2.0 Fast
-15%Seedance 2.0 tuned for speed — same modes, same 4–15 seconds, fixed 720p. Draft here, finish on 2.0 or 2.5.
● Start building
See what it does with your prompt
Test it in the playground, or grab an API key and ship it today.