MiniMax-H3 turns text or visual references into video for motion design, editing, and production workflows.
from $0.08 / second
View model detailsFind the model for your next video
Explore video generation models for text and image inputs. Compare each model’s supported duration, resolution, audio options, and pricing to find a fit for your production workflow.
Featured models include MiniMax-H3, seedance-2.0, and seedance-2.0-fast, ranked by real token usage over the last 7 days when available.
Video Generation Models
seedance-2.0 turns text or visual references into video for motion design, editing, and production workflows.
from $0.035115 / second
View model detailsseedance-2.0-fast turns text or visual references into video for motion design, editing, and production workflows.
from $0.022194 / second
View model detailsseedance-2.0-mini turns text or visual references into video for motion design, editing, and production workflows.
from $0.014123 / second
View model detailsseedance-2.5 turns text or visual references into video for motion design, editing, and production workflows.
from $0.061488 / second
View model details