WAN 3.0 AI Generator
Generated on PixelDojo with WAN 3.0. Produced by PixelDojo's generation pipeline.
WAN 3.0 charges by the second and by resolution: 1.5 credits a second at 480p, 2 at 720p, 5 at 1080p or 2K and 6 at 4K on the standard tier. A default 5 second 720p clip is 10 credits. Every clip comes with native audio, runs 2 to 30 seconds, and can start from reference images or a first and last frame. This page covers the full rate card, what a request needs, and when the Fast tier or a sibling model fits.
Made with WAN 3.0
Every example below was produced on PixelDojo. Hover to see the prompt.
Slow cinematic camera orbit around the earbuds case, soft studio lighting shifts, the lid opens gently to reveal the earbuds, product commercial style
WAN 3.0
The full WAN 3.0 rate card
Standard speed: 1.5 to 6 credits per second
480p is 1.5 credits a second, 720p is 2, 1080p and 2K are 5, and 4K is 6. The default request is 720p for 5 seconds: 10 credits.
Fast tier: the same output, a shorter queue
The Fast setting runs the same model at 2 credits a second at 480p, 3 at 720p and 6 at 1080p.
Two ways to feed it a starting image
Reference images (up to 10) or a first and last frame pair. The two modes cannot be combined in one request; sending both gets rejected before anything is charged.
Duration runs 2 to 30 seconds, or let the model choose
Set duration to -1 and the model picks its own length, billed at the full 30 second ceiling since the final length is not known at submit time.
Native audio is on by default
Turning it off does not change the price. It is a quality setting, not a cost lever.
Six aspect ratios
16:9, 4:3, 1:1, 3:4 and 9:16, plus adaptive, which matches the shape of the media you feed in.
Rate card read straight from the model's own credit formula, on one Pixel Dojo credit balance with 60+ other video models.
Why Choose Pixel Dojo for WAN 3.0
Professional-quality results with cutting-edge AI technology
Priced per second, not per clip
1.5 to 6 credits a second depending on resolution, so a short test costs a fraction of a full length generation.
From 480p drafts to 4K finals
One model covers every stage: test at 480p, then render the keeper at 1080p, 2K or 4K.
Up to 30 seconds with native audio
Longer and with sound than most video models in the catalog, at a per-second rate that scales with what you actually generate.
How It Works
Make a WAN 3.0 clip:
Pick resolution before duration
Resolution sets the per-second rate. Draft at 480p, finish at 1080p or above.
Feed it a starting image the right way
Pass reference images, or a first and last frame pair. The two modes cannot be mixed in one request.
Generate in the app or over the API
From the tool page, or POST to /api/v1/models/wan-3-0-video/run with the same key as every other model.
Loved by creators on PixelDojo
Real feedback from people using PixelDojo, pulled from our in-product surveys.
This is the best image generator I've used so far. Well done!
es facil de comprender asi uno no sea programador
amazing web site
phenomenal site. would highly recommend
Amazing features, easy to use, privacy
the number of options, and especially the quick response to questions on Discord
Explore more AI tools on PixelDojo
Popular AI Models
AI Tools
Compare & Switch
- All AI Tool Alternatives
- Pollo AI Alternative
- PixelDojo vs Pollo AI
- Pollo AI Review
- MotionMuse AI Alternative
- MioCreate Alternative
- Dessi AI Alternative
- Runway Alternatives
- CapCut Alternatives
- Leonardo Alternatives
- OpenArt Alternatives
- Midjourney Alternatives
- Canva AI Alternatives
- Pika Alternatives
- InVideo Alternatives
- Higgsfield Alternatives
- Krea Alternatives
- Luma Alternatives
- Magic Hour Alternatives
- HeyGen Alternatives
- PixAI Alternatives
- Vidu Alternatives
- Seedream Alternatives
- Tensor.Art Alternatives
Common Questions
Everything you need to know about WAN 3.0
How much does WAN 3.0 cost?
It bills per second of output at a rate set by resolution: 1.5 credits a second at 480p, 2 at 720p, 5 at 1080p and 6 at 4K on the standard tier. A default 5 second 720p clip is 10 credits.
Does image-to-video cost more than text-to-video?
No. The per-second rate is the same either way. What changes is how you feed it a starting image: up to 10 reference images, or a first and last frame pair, never both in the same request.
What does the Fast tier change?
Only the queue. Fast runs the same model and returns the same output quality, at 3 credits a second at 720p instead of 2.
How does WAN 3.0 compare with WAN 2.1 Video and WAN 2.2 Plus?
WAN 3.0 is cheaper per second than WAN 2.1 Video at both 480p and 720p, and adds native audio and clips up to 30 seconds. WAN 2.2 Plus is a flat 3 credits at 480p or 11 at 1080p for short silent clips.
Can I automate it?
Yes. POST to /api/v1/models/wan-3-0-video/run with your API key and a prompt plus optional resolution, duration and fast fields. Every model is also in the MCP server at https://pixeldojo.ai/mcp, so Claude, ChatGPT and Cursor can make videos for you.
Is it free?
Yes, to start. A free account gets 3 free video effects every day, no card needed. Plans from $10/mo unlock every model, with Unlimited on every plan and credits that roll over every month while you are subscribed.