Video model for prompt-guided generation, editing, and motion workflows
Elo from human preference matchups run by Artificial Analysis. Each arena is anchored separately, so Elo is only comparable within one arena, against the other models on that board, and the 95% confidence interval (shown as ±) indicates how much of a gap is noise. Rank is over the whole arena, including models not listed here.
| Provider | Tier | Provider model ID | Status |
|---|---|---|---|
| FastRouter | Gateway | wanx/wan-v2-6 | GA |
Availability comes from models.dev. Text-token prices and context limits are omitted because they do not describe video generation billing.