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 × | ByteDanceSeed-2.0-codeRemove × | alibabaAlibaba: Wan 3.0Remove × |
|---|---|---|---|
| What’s different | Accurately preserve the look and voice of people or objects from a reference video, supporting multi-reference co-creation. | A coding model optimized for real-world development environments, with reliable tool use in common IDEs such as Claude Code. It delivers strong front-end performance and supports Skills. | Can choose clip duration from the prompt; toggle generated audio, prompt expansion and extra thinking before rendering. |
| Date | Apr 27, 2026Listed | Apr 29, 2026Listed | Aug 19, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.10/ secondDeepInfra · all routes ↗780P · $ cost per second · output second | $0.50 in / $3.00 out/ 1M tokensDeepInfra · all routes ↗ | $0.05/ secondDeepInfra · all routes ↗480P · $ cost per second · output second |
| Provider endpoints | 1 endpoint → | 1 endpoint → | 2 endpoints → |
Benchmarks Each result retains its evaluation configuration | |||
| AA Video + Audio ↗2.1 | Not reported | Not reported | 1,174 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 1,159–1,189 · n=5,861 |
| AA Video Silent ↗2.1 | Not reported | Not reported | 1,135.19 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 1,116.19–1,154.19 · n=3,890 |
Specifications | |||
| Context window | — | 256K | — |
| Max output | — | — | — |
| Parameters | — | — | — |
| Structured output | Not reported | Not reported | Supported |
| Image input | Not reported | Not reported | Supported |
| Audio input | Not reported | Not reported | Supported |
| Video input | Not reported | Not reported | Supported |