Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | fal-aiFramepack F1Remove × | alibabaAlibaba: Wan 3.0Remove × | Sand.aiMAGI-2 PreviewRemove × |
|---|---|---|---|
| What’s different | Framepack is an efficient Image-to-video model that autoregressively generates videos. | Can choose clip duration from the prompt; toggle generated audio, prompt expansion and extra thinking before rendering. | |
| Date | May 13, 2025Listed | Aug 19, 2026Released | Sep 12, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.0333/ secondfal · all routes ↗ | $0.05/ secondDeepInfra · all routes ↗480P · $ cost per second · output second | See provider quotes |
| Provider endpoints | 1 endpoint → | 2 endpoints → | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Video + Audio ↗2.1 | Not reported | 1,174.59 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 1,159.59–1,189.59 · n=6,372 | 1,042.07 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 1,028.07–1,056.07 · n=6,015 |
| AA Video Silent ↗2.1 | Not reported | 1,134.11 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 1,116.11–1,152.11 · n=4,042 | 1,012.09 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 995.09–1,029.09 · n=5,451 |
Specifications | |||
| Context window | — | — | — |
| Max output | — | — | — |
| Parameters | — | — | — |
| Structured output | Not reported | Supported | Not reported |
| Image input | Not reported | Supported | Not reported |
| Audio input | Not reported | Supported | Not reported |
| Video input | Not reported | Supported | Not reported |