Español – América Latina Português – Brasil The Gemini API is the fastest path from prompt to production with Gemini, Veo, Nano Banana, and more. It lets you integrate these generative models into your applications to generate text and images, analyze multimodal inputs, and build conversational agents. Follow our getting started guide to get an API key and make your first API call in minutes. Meet the models auto_awesome Gemini 3.1 Pro New Our most intelligent model, the best in the world for multimodal understanding, all built on state-of-the-art reasoning. spark Gemini 3.7 Flash New Our latest and most capable Flash model, built for complex coding, agentic workflows, and reliable multi-step execution. spark Gemini 3.6 Flash Our previous-generation Flash model, balancing speed and multimodal capabilities across general agentic and everyday tasks. spark Gemini 3.5 Flash Our legacy Flash model, providing baseline speed and foundational performance for routine, high-throughput workloads. spark Gemini 3.5 Flash-Lite New High-volume, cost-sensitive model optimized for low-latency high throughput subagent tasks. spark Gemini 3.1 Flash-Lite High-volume, cost-sensitive model with the performance and quality of the Gemini 3 series. spark Gemini 3 Flash Frontier-class performance rivaling larger models at a fraction of the cost. 🍌 Nano Banana 2 and Nano Banana Pro State-of-the-art image generation and editing models. video_library Veo 3.1 Our state-of-the-art video generation model, with native audio. spark Gemini Robotics A vision-language model (VLM) that brings Gemini's agentic capabilities to robotics and enables advanced reasoning in the physical world. Explore Capabilities Native Image Generation (Nano Banana)

Generate and edit highly contextual images natively with Gemini 2.5 Flash Image. Input millions of tokens to Gemini models and derive understanding from unstructured images, videos, and documents. Structured Outputs Constrain Gemini to respond with JSON, a structured data format suitable for automated processing. Function Calling Build agentic workflows by connecting Gemini to external APIs and tools. Video Generation with Veo 3.1 Create high-quality video content from text or image prompts with our state-of-the-art model. Voice Agents with Live API Build real-time voice applications and agents with the Live API. Connect Gemini to the world through built-in tools like Google Search, URL Context, Google Maps, Code Execution and Computer Use. Document Understanding Process up to 1000 pages of PDF files with full multimodal understanding or other text-based file types. Explore how thinking capabilities improve reasoning for complex tasks and agents. Interactions API The Interactions API has become our default interface as of June 2026 and is the best way to build with Gemini models and agents going forward. If you're starting a new project, you should use the Interactions API. While it remains supported, the generateContent API is now considered legacy. Interactions Overview Learn how the Interactions API manages conversation state, messages, and output formats. Migration Guide Step-by-step guide to transition your code from generateContent to the Interactions API. Stream real-time tokens, incremental thoughts, and tool call events. Test prompts, manage your API keys, monitor usage, and build prototypes. Ask questions and find solutions from other developers and Google engineers. Find detailed information about the Gemini API in the official reference documentation. Check the status of Gemini API, Google AI Studio, and our model services. Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License , and code samples are licensed under the Apache 2.0 License . For details, see the Google Developers Site Policies . Java is a registered trademark of Oracle and/or its affiliates. Last updated 2026-08-24 UTC.