AI Models
Explore available models and their capabilities
Google
Released December 2025
Veo 3.1 Fast (Text)
Fast text-to-video with audio, up to 4K, 4-8s
Video Generation
About this model
Google DeepMind Veo 3.1 Fast via Fal is an accelerated variant for rapid text-to-video generation with audio. Produces high-quality videos at up to 4K with realistic motion and synchronized audio.
Input Cost
$0.10-0.35/s
Output Cost
$0.10-0.35/s
Input Types
Text