Veo 3.1

Published

Oct 15, 2025

Veo 3.1 is an AI model developed by Google DeepMind (United States), first published in October 2025. It works in the video and vision domain, on tasks such as image-to-video, video generation, text-to-video and audio generation.

Epoch AI has no training-compute estimate for this model.

Access: API access. Its weights are not openly released.

Full record

Organization: Google DeepMind
Country of organization: United States
Domain: Video, Vision
Task: Image-to-video, Video generation, Text-to-video, Audio generation
Model accessibility: API access
Open weights: No