Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | PrunaAIp-videoRemove × | nvidiaNemotron-3-DiarizationRemove × | Sand.aiMAGI-2 PreviewRemove × |
|---|---|---|---|
| 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. | Nemotron 3 Diarization is an open-weight streaming Sortformer model, engineered for low-latency speaker diarization across up to 8 speakers, ordered by arrival time. It powers meeting transcription, call… | |
| Date | Feb 26, 2026Listed | Sep 25, 2026Listed | Sep 12, 2026Released |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.02/ secondDeepInfra · all routes ↗Output video second; base configuration | $0.00001/ secondDeepInfra · all routes ↗Input audio 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 | 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 | — | — | — |
| Max output | — | — | — |
| Parameters | — | — | — |