Models
Explore our next generation AI systems
Slide 1 of 6
Gemini 3.5
Our latest family of models combining frontier intelligence with action
Gemini Omni
Create anything from anything – with a leap in world understanding, multimodality, and editing
Gemma 4
Our most intelligent open models, built to maximize intelligence-per-parameter
Nano Banana 2 🍌
Pro-level image generation and editing, Flash-level speed
Lyria 3
Compose music with vocals, and experiment with acoustic details
Gemini
Frontier intelligence with action
Gemini Omni
Create anything from anything, starting with video
Nano Banana 🍌
Create and edit images with Gemini Image
Lyria
Our most advanced music generation model yet
Gemini Audio
Advanced real-time audio models, built on Gemini
Veo
Our leading video generation model
Imagen
Our leading text-to-image model
Gemma
Our most capable open models
Gemini Embedding
State-of-the-art multimodal embedding model
World models & embodied AI
Systems that simulate environments and reason in the physical world
Genie 3
A new frontier for world models
Gemini Robotics
Our most advanced vision-language-action model
How to write effective prompts
Browse our guides for the perfect ingredients to bring your next video, image, track or world to life
Slide 1 of 5
Create video from anything with Gemini Omni
Create and edit images with Nano Banana
Create music with Lyria
Create worlds with Genie
Create cinematic video with Veo
SynthID
Embedding watermarks to identify content generated through AI
Start building
Google AI Studio
Start building something new, with cutting-edge AI models and tools
Google Antigravity
Our AI-first development platform that allows anyone to be a builder
Gemini Enterprise Agent Platform
Build, scale, and govern agents
Latest news
Gemini 3.5: frontier intelligence with action
Introducing Gemini Omni
Introducing Google Antigravity 2.0
Simulate real-world places with Project Genie and Street View
Gemini 3.1 Flash TTS: the next generation of expressive AI speech
Gemini Robotics-ER 1.6: Powering real-world robotics tasks through enhanced embodied reasoning
