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 × | tripo3dTripo3D SegmentRemove × | lightricksLtx 2.5 Text to Video FastRemove × |
|---|---|---|---|
| What’s different | Accurately preserve the look and voice of people or objects from a reference video, supporting multi-reference co-creation. | Automatically splits a 3D model into semantic parts for editing, texturing, and rigging. | Up to 20s at 1080p/25fps; 4K or 50fps clips cap at 10s. Includes camera-motion controls and optional generated audio. |
| Date | Apr 27, 2026Listed | Aug 6, 2026Listed | Aug 11, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.10/ secondDeepInfra · all routes ↗780P · $ cost per second · output second | See provider quotes | See provider quotes |
| Provider endpoints | 1 endpoint → | 0 endpoints → | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Video + Audio ↗2.1 | Not reported | Not reported | 950.79 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 932.79–968.79 · n=2,763 |
| AA Video Silent ↗2.1 | Not reported | Not reported | 932.71 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 914.71–950.71 · n=2,971 |
Specifications | |||
| Context window | — | — | — |
| Max output | — | — | — |
| Parameters | — | — | — |
| Open weights | Not reported | Not reported | Supported |