Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | bytedanceByteDance: Seedance 2.5Remove × | Sapiens AIAgnes-Video-2.5Remove × |
|---|---|---|
| What’s different | Seedance 2.5 is a video generation model from ByteDance. It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension. It supports first-frame and… | |
| Date | Jul 31, 2026Released | Aug 22, 2026Released |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.1028/ second Listed rate Replicate · model variant=non_video_in · target resolution=480p · output video second · Conditional | See provider quotes |
| Provider endpoints | 1 endpoint → | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | ||
| AA Video + Audio ↗2.1 | 1,157.61 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 1,142.61–1,172.61 · n=6,477 | 1,065.86 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 1,049.86–1,081.86 · n=4,263 |
| AA Video Silent ↗2.1 | 1,103.61 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 1,085.61–1,121.61 · n=4,115 | 1,052.2 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 1,034.2–1,070.2 · n=3,194 |
Specifications | ||
| Context window | — | — |
| Max output | — | — |
| Parameters | — | — |
| Image input | Supported | Not reported |
| Audio input | Supported | Not reported |
| Video input | Supported | Not reported |