1 / 3
Swipe to compare

Veo 3.1 is Google's state-of-the-art video generation model, producing high-fidelity 8-second clips at up to 4K resolution with natively generated audio — dialogue, sound effects, and background music synchronized to the visuals. It supports text-to-video, image-to-video with up to three reference images, portrait and landscape framing (9:16, 16:9), frame-specific generation, and scene extension for creating longer videos exceeding one minute. The model offers greater narrative control with improved understanding of cinematic styles and richer native audio.

Author
GoogleGoogle
Release Date
2026-01-01
Knowledge Cutoff
2026-01-01
License
Proprietary
I/O Format
Context Length
API I/O (1M)
$0.4~$0.6/second
How to Use
Google AI Ultra or above / API Access
Output Speed
Arena Overall
Intelligence Index
Coding Index
Math Index
LiveBench
ForecastBench
GPQA Diamond
HLE
MMLU-Pro
AIME 2025
MATH-500
LB Reasoning
LB Math
LB Data Analysis
LiveCodeBench
LB Coding
LB Agentic
TAU2
TerminalBench
SciCode
IFBench
AA-LCR
Hallucination (HHEM)
Factual Consistency (HHEM)
LB Language
LB Instruction Following