Wan 3.0 Text-to-Video
Cinematic text-to-video generation with synchronized audio, optional prompt expansion, 2–30 second duration, and 480p, 720p, or 1080p output.
Added Aug 10, 2026
Details
- Starting Price
- From $0.100 per video
- Model type
- text-to-video
Final price depends on the selected settings and is shown before generation.
Settings
Generation controls available for this model.
Output Format
Default Duration
5
Aspect Ratio
Default
16:9
Options (5)
16:9 (Landscape), 9:16 (Portrait), 1:1 (Square), 4:3 +1 more
Output aspect ratio
Duration
Default
5
Output duration in seconds
Generate Audio
Default
Yes
Include synchronized audio in the output
Prompt Expansion
Default
No
Let the model expand and interpret the prompt before generating; useful for complex scenes
Resolution
Default
720p
Options (3)
480p, 720p, 1080p
Output resolution
Seed
Default
-1
Use -1 for a random seed or set 0 to 2147483647 to reuse one. The seed sent is returned with each video
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#4 / 36
ELO
1133.0
Appearances
4,515
95% CI
-17/17
Release Date 2026-08 · Matched as Wan 3.0
Artificial Analysis APIExamples
Loading examples…