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 × | minimaxH3 Max RelightRemove × | x-aiSpaceXAI: Grok Imagine Video 1.5 LiteRemove × |
|---|---|---|---|
| What’s different | Accurately preserve the look and voice of people or objects from a reference video, supporting multi-reference co-creation. | Relight any video with H3 Max from a lighting sphere image, while preserving the source subjects, motion, camera and audio. | Lite text-to-video endpoint with 480p, 720p or 1080p output, adjustable duration and seven landscape-to-portrait aspect ratios. |
| Date | Apr 27, 2026Listed | Oct 7, 2026Listed | Aug 26, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.10/ secondDeepInfra · all routes ↗780P · $ cost per second · output second | $0.05/ secondfal · all routes ↗480p · generated output second | See provider quotes |
| Provider endpoints | 1 endpoint → | 1 endpoint → | 0 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Video + Audio ↗2.1 | Not reported | Not reported | 998.36 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 983.36–1,013.36 · n=5,957 |
| AA Video Silent ↗2.1 | Not reported | Not reported | 980.72 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 962.72–998.72 · n=3,488 |
Specifications | |||
| Context window | — | — | — |
| Max output | — | — | — |
| Parameters | — | — | — |
| Structured output | Not reported | Not reported | Supported |
| Image input | Not reported | Not reported | Supported |