It supports text-to-video, image-to-video, and reference-to-video. All three modes offer 480p, 720p, and 1080p output.
Wan 3.0 Video
Wan 3.0 Video supports text-to-video, image-to-video, and reference-to-video generation with the broadest reference toolkit in this API lineup: images, videos, audio, files, and links. Choose 480p, 720p, or 1080p output, or let smart duration determine the clip length.
Modes
Text / Image / Reference
APIXO Price
From $0.05 / second
Duration
Smart or 2–30 Seconds
Reference Types
Image / Video / Audio / File / Link
Resolution
480p / 720p / 1080p
Create with Wan 3.0 Video
Loading workspace...
A reference toolkit built for complex creative briefs
Five Reference Channels
Guide a reference-to-video request with images, videos, audio, one file, or one link instead of compressing every instruction into the prompt alone.
First-and-Last-Frame Images
Use one image as the starting frame or add a second image as the ending frame in image-to-video mode. Reference mode accepts up to ten images.
Video Reference Guidance
Attach up to five reference videos of 1–15 seconds each, with at most 15 seconds of reference video in total. Reference-video duration is added to output duration and billed at the same resolution-based per-second rate.
Audio References Without a Surcharge
Use up to five public reference audio URLs through the audio_urls parameter to guide timing, tone, rhythm, or voice cues. Each file must be 1–15 seconds, with 15 seconds maximum in total. Reference audio adds no separate input charge.
File or Link Context
Supply one file URL or one link URL as extra reference context. The two fields are mutually exclusive, keeping each request’s external context unambiguous.
Smart Duration
Turn on smart duration when the model should determine the output length, or choose any whole number from 2 through 30 seconds for an explicit clip duration.
Choose text, image, or reference-to-video generation
Text-to-Video
Generate a video from a written prompt, with no reference media required.
Image-to-Video & Reference-to-Video
Animate one or two images, or add videos, audio, a file, or a link as reference context.
Published Wan 3.0 Video API parameters
Key generation modes, reference limits, sound behavior, and output options exposed by the APIXO route.
3 Generation Modes
Modes
480p / 720p / 1080p
Resolution
Smart or 2–30 Seconds
Duration
Up to 10 Images
Image References
Up to 5 Videos
Video References
Enabled by Default
Sound
When richer reference context improves the production brief
Reference-Guided Scene Development
Combine image references with short video clips to communicate subjects, visual direction, and motion cues within one reference-to-video request.
First-to-Last-Frame Motion
Provide a starting image and an optional ending image when the desired clip needs to move between two known visual states.
Audio, File, and Link Context
Extend a visual brief with audio references and either a file or a link when the prompt alone cannot carry all of the supporting context.
Smart-Length Creative Exploration
Use smart duration when the appropriate clip length should follow the generated result, then switch to a fixed 2–30 second duration for controlled production passes.
Wan 3.0 Video input and billing guidance
Notes
Wan 3.0 Video is available in the APIXO browser workspace and through the API today. Create directly in your browser, or use the API for automation and product integrations.
Smart duration uses -1. The backend initially reserves the cost of 30 seconds, then settles against the actual duration of the successful video and refunds the difference.
Reference-video seconds are billed at the same mode and resolution rate as output seconds. Reference audio has no separate input charge.
For a fixed positive duration, output seconds plus total reference-video seconds cannot exceed 30 seconds.
Sound defaults to true, while watermark defaults to false. Set either field explicitly when the request should use different behavior.
file_urls and link_urls are mutually exclusive in reference-to-video mode; submit at most one file or one link, not both.
Frequently Asked Questions
All three generation modes cost $0.05, $0.1125, or $0.20 per second at 480p, 720p, or 1080p. Reference-to-video additionally bills the actual seconds of any reference videos.
When duration is -1, the backend reserves 30 seconds of cost because the final duration is not known yet. After a successful result, billing is settled using the actual duration and the difference is refunded.
Yes. In reference-to-video mode, pass up to five public audio URLs through the audio_urls parameter. Each file must be 1–15 seconds, with 15 seconds maximum in total. Reference audio can guide timing, tone, rhythm, or voice cues without a separate input charge.
No. Reference audio adds no separate input charge. Reference-video duration is added to the generated output duration and billed at the same resolution-based per-second rate.
Explore Other Models
Discover more AI models for your next creative workflow