Google AI Studio
Web-based environment from Google for experimenting with Gemini and other generative models and building apps with the Gemini API.
At a Glance
For developers and small projects getting started with the Gemini API.
Engagement
Available On
Alternatives
Updated Oct 2026
About Google AI Studio
Google AI Studio is Google's web workspace for trying its generative models and building applications with the Gemini API. Its homepage describes going from prompt to production with Gemini, Omni, Nano Banana and other models, and it links to API key management, SDKs, an app gallery and documentation.
What It Is
Google AI Studio is a browser-based environment for experimenting with Google's latest models and starting development against the Gemini API. Users can open prompts directly with Gemini 3 for reasoning, Nano Banana for image generation, Veo for video generation, Gemini TTS for controllable speech, Gemini Live for real-time voice and video interaction, Omni for video editing and creation, and Lyria for music generation.
Building with the Gemini API
The site gives developers a place to get and manage API keys and monitor resource usage. It points to official GenAI SDKs for Python, JavaScript, Go, Java and C++. It also lists an Interactions API for stateful, multi-turn agents with managed tool execution and history, and tools for function calling plus Search and Maps grounding.
The JavaScript/TypeScript SDK (@google/genai) documents API-key initialization from Google AI Studio, streaming, function calling, experimental MCP support, file uploads, caching, chats and live sessions. The same SDK also supports the Gemini Enterprise Agent Platform.
App gallery and vibe coding
The homepage offers an app gallery of remixable starter projects, such as games, personal websites and interactive art, along with example prompts for generating apps like a language-learning partner or a background-removal tool. It also links to Live API, managed agents and vibe coding capabilities.
Community Discussions
Annotate mode: draw on UI → code
Google just showed off Annotate mode in Google AI Studio and it’s exactly the kind of vibe-coding magic we’ve been waiting for. You open your app in the Build view, hit Annotate, literally draw on the live preview. Little arrows, circles, quick notes like “make this button sticky” or “padding 24px” …
Pricing
Free
For developers and small projects getting started with the Gemini API.
- Limited access to certain models
- Free input & output tokens
- Google AI Studio access
- Content used to improve our products
Gemini 3.8 Flash
Our most intelligent Flash model, engineered for long-horizon softwareengineering, autonomous agents, and complex enterprise workflows.
- Input: $0.75 per 1M tokens through December 31, 2026; $1.50 starting January 1, 2027
- Output (including thinking tokens): $3.75 per 1M tokens through December 31, 2026; $7.50 starting January 1, 2027
- Context caching: $0.075 per 1M tokens through December 31, 2026; $0.15 starting January 1, 2027
Gemini 3.5 Flash-Lite
A cost-efficient model, optimized for high-volume agentic tasks, translation,and simple data processing.
- Input: $0.30 per 1M tokens (text / image / video / audio)
- Output (including thinking tokens): $2.50 per 1M tokens
- Context caching: $0.03 per 1M tokens
Gemini 3.1 Pro Preview
Our 3rd generation Pro model, built for multimodal understanding, agenticcapabilities, and vibe-coding.
- Input: $2.00 per 1M tokens (prompts <= 200k tokens); $4.00 (prompts > 200k tokens)
- Output (including thinking tokens): $12.00 per 1M tokens (prompts <= 200k tokens); $18.00 (prompts > 200k)
- Context caching: $0.20 per 1M tokens (<= 200k); $0.40 (> 200k)
Veo 3.1
A fast video generation model.
- Standard video with audio: $0.40 per second (720p and 1080p); $0.60 (4k)
- Fast video with audio: $0.10 per second (720p); $0.12 (1080p); $0.30 (4k)
- Lite video with audio: $0.05 per second (720p); $0.08 (1080p)
Enterprise
For enterprise deployments, powered by Gemini Enterprise Agent Platform.
- All features in Paid, plus optional access to:
- Dedicated support channels
- Advanced security & compliance
- Provisioned throughput
- Volume-based discounts (based on usage)
- ML ops, model garden and more
Capabilities
Key Features
- Prompt playground for Gemini 3, Nano Banana, Veo, Lyria, Omni and Gemini TTS
- Gemini Live real-time voice and video interactions
- Gemini API key management and usage monitoring
- Official GenAI SDKs for Python, JavaScript, Go, Java and C++
- Interactions API for stateful multi-turn agents
- Function calling and Search and Maps grounding tools
- App gallery with remixable starter projects
- Vibe coding and prompt-to-app generation
- Managed agents and Live API