Veo 3.1

Google DeepMind
class A live

Google DeepMind's text/image-to-video model with native synchronized audio; up to 8s at 1080p/4K, closed weights, paid API from $0.40/s.

Layer 1 — factual axes

API & price public · $0.40/s (Fast $0.10-0.30/s, Lite $0.05-0.08/s) official source ↗ 2026-07-04
Max output 8s · 1080p (4K available; ~148s via extension) official source ↗ 2026-07-04
Native audio yes official source ↗ 2026-07-04
Weights closed official source ↗ 2026-07-04
Free tier limited (watermarked generation via Gemini app; no free API) official source ↗ 2026-07-04

Layer 2 — output quality

1094 / 1600
Eligible for Best freeBest for APINative audio

Google DeepMind’s text/image-to-video model with native synchronized audio; up to 8s at 1080p/4K, closed weights, paid API from $0.40/s.

Data as of 2026-07-04 · verified 2026-07-04. One ruler for all tools. How we measure ↗