Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | Wan-AIWan2.7-R2VRemove × | cloudflareCloudflare: Clef FlashRemove × | Sand.aiMAGI-2 PreviewRemove × |
|---|---|---|---|
| What’s different | Accurately preserve the look and voice of people or objects from a reference video, supporting multi-reference co-creation. | Small decision model for routing and scoring; the Workers AI route currently reads only roughly the first 2K text-state tokens. | |
| Date | Apr 27, 2026Listed | Oct 1, 2026Listed | Sep 12, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.10/ secondDeepInfra · all routes ↗780P · $ cost per second · output second | $0.038 in / $0.00 out/ 1M tokensDeepInfra · all routes ↗ | 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 | Not reported | 1,044.42 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 1,028.42–1,060.42 · n=5,284 |
| AA Video Silent ↗2.1 | Not reported | Not reported | 1,012.49 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 995.49–1,029.49 · n=5,306 |
Specifications | |||
| Context window | — | 24.6K | — |
| Max output | — | 22.1K | — |
| Parameters | — | — | — |
| Image input | Not reported | Supported | Not reported |
| Open weights | Not reported | Supported | Not reported |