Google releases Veo 3.1 Lite, a cost-effective video generation model available on the Gemini API with 50% lower cost than Veo 3.1 Fast while maintaining the same speed. The model supports text-to-video and image-to-video generation with flexible resolutions and aspect ratios.
<img src="https://storage.googleapis.com/gweb-uniblog-publish-prod/images/veo31lite.max-600x600.format-webp.webp">Veo 3.1 Lite is now available in paid preview through the Gemini API and for testing in Google AI Studio.
# Build with Veo 3.1 Lite, our most cost-effective video generation model
Source: https://blog.google/innovation-and-ai/technology/ai/veo-3-1-lite/
Our most cost-effective video generation model is now available to developers via the Gemini API.
Guillaume Vernade
Gemini Developer Advocate, Google DeepMind
Build with Veo 3.1 Lite
Your browser does not support the audio element.
Listen to article
This content is generated by Google AI. Generative AI is experimental
[[duration]] minutes
We are introducing Veo 3.1 Lite (https://ai.google.dev/gemini-api/docs/models/veo-3.1-lite-generate-preview), Google’s most cost-effective video model. This model empowers developers to build high-volume video applications for less than 50% of the cost of Veo 3.1 Fast, while delivering the same speed. This completes the Veo 3.1 model family, providing developers with flexibility tailored to their specific needs.
On April 7, we’ll also be reducing prices for Veo 3.1 Fast, enabling even more developers to integrate video generation into their products.
latest pricing
## Efficiency for builders
Veo 3.1 Lite balances practical utility with professional capabilities, supporting Text-to-Video and Image-to-Video. It supports flexible framing for landscape (16:9) and portrait (9:16) aspect ratios, along with 720p and 1080p video resolutions.
A demo app showcasing how Veo 3.1 Lite can be used to iterate as you craft the perfect video.
Developers can also customize duration at 4s, 6s, or 8s, with costs adjusting accordingly.
Our commitment to making video generation more accessible to developers doesn’t stop with the release of Veo 3.1 Lite. Stay tuned for more updates soon!
## Get started
Rolling out today, you can access the model via a paid tier on the Gemini API (https://ai.google.dev/gemini-api/docs/models/veo-3.1-lite-generate-preview) and Google AI Studio (https://aistudio.google.com/prompts/new_video?model=veo-3.1-lite-generate-preview).
Check out the developer documentation (https://ai.google.dev/gemini-api/docs/models/veo-3.1-lite-generate-preview) for all specifications for the new Veo 3.1 Lite and the updated pricing for Veo 3.1 Fast.
### Related stories
Google launches Veo 2 video generation capabilities in Gemini Advanced and Whisk, enabling users to create high-resolution 8-second videos from text prompts or animate images, available to Google One AI Premium subscribers.
Google introduces Veo 3.1, an upgraded video generation model with richer audio, improved narrative control, and enhanced realism, alongside significant updates to Flow with new editing capabilities including Insert and Remove features, plus audio support across all existing tools.
Google announced Veo 2 and Imagen 3, state-of-the-art video and image generation models now available in VideoFX, ImageFX, and a new tool called Whisk. Veo 2 generates high-quality 4K videos with improved physics understanding and cinematography knowledge, while Imagen 3 produces brighter, better-composed images with diverse art styles.
Google Vids introduces free high-quality video generation using Veo 3.1 for all users, alongside new custom music creation via Lyria 3 and AI avatar features for premium subscribers.
Google updates Veo 3.1 with improved consistency for characters and objects, support for vertical video generation, and upscaling to 1080p/4K resolution.