Image model for prompt-driven generation, editing, and visual design workflows
Select one official tariff and enter its direct billable quantity. Resolution, audio and input conditions are not inferred.
| Billed media | Conditions | Official price |
|---|---|---|
| Output | HDText to video · Fast draft | $0.06 / second |
| Output | HDImage to video · Fast draft | $0.06 / second |
| Output | HDVideo continuation · Fast draft | $0.12 / second |
| Output | HDText to video · Full render | $0.17 / second |
| Output | HDImage to video · Full render | $0.17 / second |
| Output | FHDText to video · Full render | $0.29 / second |
| Output | FHDImage to video · Full render | $0.29 / second |
| Output | QHDText to video · Full render | $0.40 / second |
| Output | QHDImage to video · Full render | $0.40 / second |
| Output | HDVideo continuation · Full render | $0.41 / second |
| Output | FHDVideo continuation · Full render | $0.53 / second |
| Output | QHDVideo continuation · Full render | $0.65 / second |
| Output | UHDText to video · Full render | $0.80 / second |
| Output | UHDImage to video · Full render | $0.80 / second |
| Output | UHDVideo continuation · Full render | $0.95 / second |
Prices use each vendor's billing unit. The billed media and listed conditions determine the charge; these values do not enter text-token price comparisons.
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 |
|---|---|---|---|
| Vercel AI Gateway | Cloud | bfl/flux-3-video | GA |
Availability comes from models.dev. Text-token prices and context limits are omitted because they do not describe video generation billing.