AI video models
Ranked coverage: 3 of 5 at 10s / 720p / t2v / no audio
| Model | Creator | Cheapest | Providers |
|---|---|---|---|
| t2v 路 i2v 路 ref2v 馃幀 Long takes: 30 seconds in one generation, where nothing else here passes 15. | ByteDance | $2.16 derived per clip 路 10s / 720p / t2v / no audio | 13 of 13 tracked |
| t2v 路 i2v 路 ref2v 馃攣 Volume work: drafts, variants and prompt tests, with 720p as the ceiling. | ByteDance | $0.2288 derived per clip 路 10s / 720p / t2v / no audio | 11 of 13 tracked |
| t2v 路 i2v 路 ref2v 馃摵 Resolution: the only Seedance that outputs 4K, at up to fifteen seconds. | ByteDance | $1.216 derived per clip 路 10s / 720p / t2v / no audio | 12 of 13 tracked |
| t2v 路 i2v 路 ref2v 馃攰 Talking clips: native audio in five named languages, from 3 seconds up. | Kuaishou | $0.90 derived own unit per clip 路 10s / pro / t2v / no audio | 6 of 6 tracked |
| t2v 路 i2v 路 ref2v 馃敆 Stitched scenes: Extend chains generations to about 148 seconds, though one clip caps at 8. | $2.56 derived own unit per clip 路 8s / 1080p / t2v / audio | 9 of 11 tracked |
This column ranks at one shared unit: 10s / 720p / t2v / no audio. A row marked "own unit" sells nothing at it, so its figure buys what the line under it says and is not comparable with the rest of the table.
This compares only the models we currently track; it is not a market-wide ranking.