Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | PrunaAIp-videoRemove × | togethercomputerTogether: Tev1 4B ExperimentalRemove × | minimaxMiniMax H3 Max Text to VideoRemove × |
|---|---|---|---|
| What’s different | Real-time AI video generation from text, images, and audio. Supports up to 1080p at 48 FPS with built-in audio generation, draft mode for 4x faster previews, and prompt upsampling. | Tev1 4B Experimental is an experimental decision model from Together AI, a supervised fine-tune of Qwen3.5-4B trained to choose one option from a structured state, question, and list of 2-24... | Uses native 480P/768P generation or 1080P latent refinement; supports supplied soundtracks and selectable prompt expansion. |
| Date | Feb 26, 2026Listed | Sep 30, 2026Listed | Aug 26, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.02/ secondDeepInfra · all routes ↗Output video second; base configuration | $0.042 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | 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 | 1,155.56 ↗Text-to-video · audio evaluated · all categoriesIndependent result95% CI 1,139.56–1,171.56 · n=5,440 |
| AA Video Silent ↗2.1 | Not reported | Not reported | 1,118.75 ↗Text-to-video · silent evaluation · all categoriesIndependent result95% CI 1,101.75–1,135.75 · n=5,734 |
Specifications | |||
| Context window | — | 32.8K | — |
| Max output | — | 8 | — |
| Parameters | — | 4B | — |
| Open weights | Not reported | Supported | Not reported |