Veo 2 is Google DeepMind’s advanced text"‘to"‘video model, released December 16, 2024, and expanded in April 2025 to Gemini AI Studio & API
It generates cinematic, high"‘resolution video up to 4K (though Gemini and VideoFX tools currently output 720p, 8"‘second clips).
Veo"¯2 excels in physics"‘aware motion, natural human movement, and precise cinematographic controls—supporting prompts like “18"¯mm lens”, “tracking shot”, “shallow depth of field”.
Inputs supported: text"‘to"‘video and image"‘to"‘video. Outputs include invisible SynthID watermarks for AI"‘generated content detection.
If you'd like to access this model, you can explore the following possibilities:
Use our video cost calculator to compare prices between platforms offering Veo 2 model.
For locally hosted models, see description and additional links at the bottom for versions, repos and tutorials.