Black Forest Labs Flux 3 Video vs Google Veo 3.1
Specs, pricing, and capabilities side by side, plus outputs generated from identical prompts, so the only variable between the columns is the model.
Black Forest Labs' multimodal video model: text, image, or video in, with synchronized audio, lip-sync, and a cheap draft mode.
Learn more about Flux 3 Video →Google's high-quality video model with native audio, reference-image support, and frame-to-frame control.
Learn more about Veo 3.1 →Every sample is the model’s first result for the shared scene prompt (no cherry-picking), generated via Runware or Replicate. Hover a copy icon to read the full prompt.
LMArena ranks come from the arena.ai leaderboard (dataset, CC BY 4.0), board of Sep 22, 2026.