ZMIME
Google · video model · Released Oct 13, 2025

Veo 3 Fast

Veo 3 Fast is a video model from Google, released Oct 13, 2025. It handles text to video.

  • Video model
  • Proprietary
  • Text to video
Arena score
1,347#18 of 50 · text to video
Starting price
—Not published
Longest clip
—Not published
Resolution
—Audio unconfirmed
Quality & price

How it rates and what it costs

Text to video arena
1,347 ±11#18 of 50 · 25,277 votes
Image to video arena
1,327 ±9#23 of 50 · 41,228 votes

Arena scores come from blind, side-by-side human votes on the same prompts (higher is better; ± is the 95% range). Boards updated Nov 9, 2026.

Specifications

The details

Lab
Google
Type
Video model
Released
Oct 13, 2025
Inputs
Text prompts
Output
Video
Can do
Text to video
Weights
Proprietary
Availability
1 API host
Same lab

More video models from Google

Questions

About Veo 3 Fast

How good is Veo 3 Fast?

In blind side-by-side votes, Veo 3 Fast scores 1,347 for text to video (#18 of 50) and 1,327 for image to video (#23 of 50). Higher is better; scores within about 22 points of each other are effectively tied.

Who makes Veo 3 Fast?

Veo 3 Fast is a video model from Google, released Oct 13, 2025.

What can Veo 3 Fast do?

Veo 3 Fast accepts text prompts and produces video. In practice: text to video.

Is Veo 3 Fast open source?

No. Veo 3 Fast is proprietary; you use it through an API or partner apps.

Where can I use Veo 3 Fast?

It is listed by 1 API host we track.

What are the alternatives to Veo 3 Fast?

The closest video models from other labs, by release date, are Cosmos-Transfer2.5-2B (NVIDIA, Oct 6, 2025), Sora 2 (OpenAI, Oct 6, 2025), Kling v2.6 (Kling AI, Dec 3, 2025) and Seedance v1.0 Pro Fast (ByteDance Seed, Oct 24, 2025).