Google Launches Veo 3.1 AI Video Generation Model with Major Upgrades
Google has released the first major update to its AI video generation model. Veo 3 received this update less than five months after its debut. The new version, Veo 3.1, introduces big improvements in prompt accuracy, creative control, and user-guided video design.
The announcement came on X (formerly Twitter) from Google DeepMind’s official handle. The company said that since Veo 3’s launch in May, users have generated over 275 million videos. This shows massive global adoption.
According to Google, Veo 3.1 is designed to give users more artistic flexibility. It allows creators to shape videos more precisely based on their vision.
New Features in Veo 3.1
There are three key upgrades in this release.
The first is “Ingredients to Video.” This lets users upload multiple reference images to guide the AI. Veo analyses these images and integrates visual cues into the generated video. Google says this makes the output closer to the creator’s intent.
The second feature, “Frames to Video,” allows users to upload a starting and ending image. The AI then generates a smooth video connecting both frames. This gives creators narrative control and enables visually seamless transitions.
The third feature is called “Extend.” Users can upload an existing video clip, and Veo 3.1 will continue the scene beyond the original footage. This allows for the creation of longer, continuous videos that last over a minute. These are ideal for cinematic storytelling or extended establishing shots.
Availability and Pricing
Currently, Veo 3.1 is accessible through the Flow app and the Gemini API for developers. However, it is not yet available on the Gemini mobile app.
The Flow app is available to users with Google AI Pro and Google AI Ultra subscriptions. Developers can access Veo 3.1 through the Gemini API at the same pricing as before — $0.40 per second (around ₹35) for the standard model, and $0.15 per second (around ₹13) for the Veo 3.1 Fast version.
Creative Boost and Industry Impact
With these updates, Google aims to make AI-driven video creation more intuitive and powerful. The ability to merge images, frames, and clips gives creators new storytelling tools previously limited to human editors.
Veo 3.1 marks another step forward in AI video synthesis, offering deeper integration between text prompts, visual references, and motion generation.
The competition in AI video models is intensifying. Rivals include Runway, Pika Labs, and OpenAI’s Sora. Google’s latest update signals its determination to lead the creative AI frontier.
In short, Veo 3.1 is faster, smarter, and more flexible — bringing the world closer to truly customizable AI filmmaking.