tools
Google AI Studio - Free Gemini Developer Playground | AI.info
Google AI Studio provides free access to Gemini 2.5 Pro and Flash with multimodal inputs, Google Search grounding, and instant API key generation for developers.
In inglese
Google AI Studio lets developers and other builders experiment with Gemini through chat, multimodal prompts, real-time streaming, video generation, and other interfaces. It includes controls for model parameters, safety settings, structured output, function calling, code execution, and grounding.
Users can export generated code, obtain Gemini API keys, build full-stack and native Android apps, connect Google Workspace data, and deploy applications. The free tier has model and rate limits; higher limits, advanced models, and production use are usage-based and may require billing.
Features
- Test Gemini models with chat, multimodal prompts, video generation, and real-time streaming
- Adjust model parameters and safety settings
- Use structured output, function calling, code execution, and grounding
- Generate application code with the Get code function
- Create full-stack applications with Firebase integrations
- Build native Android apps with Kotlin and Jetpack Compose
- Monitor API usage, rate limits, billing, and project spending
- Access the Gemini API and create API keys
Use cases
- Prototype conversational and multimodal AI applications
- Generate starter code from prompts and export it to a development environment
- Build and test full-stack web applications
- Create native Android application prototypes
- Evaluate prompts with structured outputs and tool calls
- Monitor Gemini API usage and control project spending
Pros
Cons
Latest updates
- Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS generally available (GA)
Released two text-to-speech models and the Gemini API Voices endpoint; introduced voice design, voice replication, and Extended Voice Library.
- Gemini 2.5 models access update
Limited access to 2.5 models to users who have actively used them in the past; they will continue to be served through the API.
- Antigravity Agent 09-2026 (antigravity-preview-09-2026)
Released antigravity-preview-09-2026; local tools use PascalCase parameters and line-range file replacements.
- Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking generally available (GA)
Released two audio-to-audio models for real-time voice applications using the Live API.
- Lyria 3.5 generally available (GA) (lyria-3.5)
Released lyria-3.5; it supports text and image inputs and generates 44.1 kHz stereo audio.
Capabilities
- Choice of models — “Experiment with the latest models” source
- API — “Start building with Gemini API” source
- Official SDKs — “Official SDKs for Python, JavaScript, Go, Java, and C++” source
- Runs models for you — “Free input & output tokens” source
- Builds agents and workflows — “Build stateful, multi-turn agents with managed tool execution and history” source
Get it
Pricing
- Starting price
- Free
- Prices checked
- 2026-09-25
Free
Free
- Limited access to certain models
- Free input & output tokens
- Google AI Studio access
- Content used to improve our products
Enterprise
Price on request
- 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