Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of Wan2.6-T2V, MAGI-2 Preview
2 modelsWan-AIWan2.6-T2VRemove ×Sand.aiMAGI-2 PreviewRemove ×
What’s differentTurn any prompt into a smooth video. Intelligent shot scheduling supports multi-shot storytelling, generating multi-shot narrative videos with consistent subjects, scenes, and atmosphere
DateFeb 5, 2026ListedSep 12, 2026Released
Listed rate$0.10/ secondDeepInfra · all routes ↗780P · $ cost per second · output secondSee provider quotes
Provider endpoints1 endpoint →0 endpoints →
AA Video + Audio ↗2.1Not reported1,044.42 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 1,028.42–1,060.42 · n=5,284
AA Video Silent ↗2.1Not reported1,012.09 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 995.09–1,029.09 · n=5,451
Context window——
Max output——
Parameters——

Add another model

Search all models →