Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | Unknownperceptron-mk1Remove × | fal-aiVidu Q4 Reference to VideoRemove × |
|---|---|---|
| What’s different | 32.8K context · 8.2K max output · Structured output · Reasoning | Uses up to 12 image references and three voice clips for consistent subjects and voices in 3–16 second videos, up to 4K. |
| Date | Oct 16, 2026Discovered | Oct 5, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.15 in / $1.50 out/ 1M tokensExperiential · all routes ↗Standard list rate | See provider quotes |
| Provider endpoints | 1 endpoint → | 0 endpoints → |
Specifications | ||
| Context window | 32.8K | — |
| Max output | 8.2K | — |
| Parameters | — | — |
| Structured output | Supported | Not reported |
| Reasoning | Supported | Not reported |