Models — Google DeepMindSkip to main content
Google DeepMind
Build with Gemini<br>Try Gemini
Slide 1 of 7
Models<br>Explore our next generation AI systems
View model cards
Your browser does not support the video tag. Your browser does not support the video tag.
Gemini Robotics 2<br>The intelligence layer to power any kind of robot
Learn more
Try
Your browser does not support the video tag. Your browser does not support the video tag.
Lyria 3.5<br>Compose music with improved vocals and acoustic details
Learn more<br>Try
Nano Banana 2 Lite 🍌<br>Our fastest, most efficient Gemini Image model
Learn more
Try
Your browser does not support the video tag. Your browser does not support the video tag.
Gemini 3.5<br>Our latest family of models combining frontier intelligence with action
Learn more
Try
Your browser does not support the video tag. Your browser does not support the video tag.
Gemini Omni<br>Create anything from anything – with a leap in world understanding, multimodality, and editing
Learn more
Try
Your browser does not support the video tag. Your browser does not support the video tag.
Gemma 4<br>Our most intelligent open models, built to maximize intelligence-per-parameter
Learn more
Try
New
Gemini<br>Frontier intelligence with action
Try it in
Gemini app
Google AI Studio
Google Antigravity
Gemini Enterprise Agent Platform
Learn more
Gemini Omni<br>Create anything from anything, starting with video
Try it in
Gemini app
Google Flow
Learn more
Nano Banana 🍌<br>Create and edit images with Gemini Image
Try it in
Gemini app
Google AI Studio
Gemini Enterprise Agent Platform
Learn more
New
Lyria<br>Our most advanced music generation model
Try it in
Gemini app
Google Flow Music
Google AI Studio
Gemini Enterprise Agent Platform
Learn more
Gemini Audio<br>Advanced real-time audio models, built on Gemini
Try it in
Google AI Studio
Gemini Enterprise Agent Platform
Learn more
Veo<br>Our leading video generation model
Try it in
Gemini app
Google Flow
Google AI Studio
Gemini Enterprise Agent Platform
Learn more
Imagen<br>Our leading text-to-image model
Try it in
Google AI Studio
Gemini Enterprise Agent Platform
Learn more
Gemma<br>Our most capable open models
Build with Gemma
Google AI Studio
Run Gemma
Developer docs
Learn more
Gemini Embedding<br>State-of-the-art multimodal embedding model
Build with Gemini Embedding
Gemini API docs
Google Cloud docs
Learn more
World models & physical AI<br>Systems that simulate environments and reason in the physical world
Your browser does not support the video tag. Your browser does not support the video tag.
Genie 3<br>A new frontier for world models
Learn more
Your browser does not support the video tag. Your browser does not support the video tag.
Gemini Robotics 2<br>The intelligence layer to power any kind of robot
Learn more
Try
How to write effective prompts<br>Browse our guides for the perfect ingredients to bring your next video, image, track or world to life
Slide 1 of 5
Your browser does not support the video tag. Your browser does not support the video tag.
Create video from anything with Gemini Omni
View guide
Create and edit images with Nano Banana
View guide
Your browser does not support the video tag. Your browser does not support the video tag.
Create music with Lyria
View guide
Your browser does not support the video tag. Your browser does not support the video tag.
Create worlds with Genie
View guide
Your browser does not support the video tag. Your browser does not support the video tag.
Create cinematic video with Veo
View guide
SynthIDEmbedding watermarks to identify content generated through AI
Learn more
Start building
Google AI Studio<br>Start building something new, with cutting-edge AI models and tools
Try Google AI Studio
Google Antigravity<br>Our AI-first development platform that allows anyone to be a builder
Try Google Antigravity
Gemini Enterprise Agent Platform<br>Build, scale, and govern agents
Try Gemini Enterprise Agent Platform
Latest news
View news
Putting sign language AI into users’ hands<br>August 2026Models<br>Learn more
Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration<br>July 2026Models<br>Learn more
Gemini Robotics 2 brings whole body intelligence to robots<br>July 2026Models<br>Learn more
We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control<br>July 2026Models<br>Learn more
Introducing Gemini 3.5 Flash Cyber<br>July 2026Models<br>Learn more
Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber<br>July 2026Models<br>Learn more