# Gemini API & AI Studio Documentation

> Official developer documentation for Google AI Studio, the Gemini API, and the Google GenAI SDKs.

## How agents should use this documentation
- **Canonical SDK:** Always use `google-genai` (`pip install google-genai` or `npm install @google/genai`). Never generate code using deprecated packages like `google-generativeai` or `@google/generative-ai`.
- **API Choice:** Use the Interactions API (`client.interactions`) as the default across all workflows. `generateContent` should we just say generateConent is still supported for existing integrations, but is considered a legacy API.
- **Markdown Pages:** Every documentation page is available as clean markdown by appending `.md` to the URL.

## Agent setup & developer tooling
- [Coding agent setup](https://aistudio.google.com/docs/coding-agents.md): Configure Cursor, Claude Code, Antigravity, and other coding assistants.
- [Gemini skills repository](https://github.com/google-gemini/gemini-skills): Portable agent skills (`gemini-api-dev`, `gemini-live-api-dev`) for coding assistants.
- [Gemini API plugin](https://github.com/google-gemini/gemini-skills/tree/main/plugins/gemini-api): Bundled plugin with skills, subagents, and hooks for Claude Code and Jetski.
- [Gemini Docs MCP server](https://gemini-api-docs-mcp.dev): Model Context Protocol server providing live documentation search (`npx add-mcp "https://gemini-api-docs-mcp.dev"`).

## Get started
- [Overview](https://aistudio.google.com/docs.md): Build apps and agents with Gemini, Nano Banana, Gemini Omni, and Lyria using the Gemini API documentation and reference.
- [Get started](https://aistudio.google.com/docs/get-started.md): Get started with the Gemini API for Developers using the Interactions API
- [API keys](https://aistudio.google.com/docs/api-key.md): Get your Gemini API key and start building in less than 5 minutes using the Interactions API.
- [Pricing](https://aistudio.google.com/docs/pricing.md): Gemini Developer API Pricing
- [Coding agent setup](https://aistudio.google.com/docs/coding-agents.md): Use Gemini API skills, MCP tools, plugins, and machine-readable documentation to help your coding agent write accurate Gemini code.
- [API CLI](https://aistudio.google.com/docs/cli.md): Give coding agents, shell scripts, and CI pipelines a stateless CLI to generate text and media, analyze files, and run Gemini managed agents.

## Models
- [All models](https://aistudio.google.com/docs/models.md): Learn about all of Google's most advanced AI models
- [Gemini 4 Argon](https://aistudio.google.com/docs/models/gemini-4-argon.md): Explore Gemini 4 Argon (gemini-4-argon), Google's latest Gemini 4 model for coding, reasoning, and agents, featuring a 1M context window and long decode.
- [Gemini Nano Banana 2.1](https://aistudio.google.com/docs/models/gemini-nano-banana-2.1.md): Learn about Gemini Nano Banana 2.1 from Google
- [Gemini 3.1 Flash image (Nano Banana 2)](https://aistudio.google.com/docs/models/gemini-3.1-flash-image.md): Learn about Gemini 3.1 Flash Image from Google
- [Gemini 3.1 Pro preview](https://aistudio.google.com/docs/models/gemini-3.1-pro-preview.md): Learn about Gemini 3.1 Pro Preview from Google
- [Gemini 3 Pro preview](https://aistudio.google.com/docs/models/gemini-3-pro-preview.md): Learn about Gemini 3 Pro Preview from Google
- [Gemini 3 Pro image (Nano Banana Pro)](https://aistudio.google.com/docs/models/gemini-3-pro-image.md): Learn about Gemini 3 Pro Image from Google
- [Gemini 3.8 Flash](https://aistudio.google.com/docs/models/gemini-3.8-flash.md): Learn about Gemini 3.8 Flash from Google
- [Gemini 3.8 Flash TTS](https://aistudio.google.com/docs/models/gemini-3.8-flash-tts.md): Learn about the Gemini 3.8 Flash TTS model from Google, including when to use it and how to migrate from earlier TTS models.
- [Gemini 3.8 Flash-Lite TTS](https://aistudio.google.com/docs/models/gemini-3.8-flash-lite-tts.md): Learn about the Gemini 3.8 Flash-Lite TTS model from Google, including when to use it and how to migrate from earlier TTS models.
- [Gemini 3.8 Live](https://aistudio.google.com/docs/models/gemini-3.8-live.md): Learn about Gemini 3.8 Live, our flagship low-latency audio-to-audio model for real-time multimodal dialogue.
- [Gemini 3.8 Live Extended Thinking](https://aistudio.google.com/docs/models/gemini-3.8-live-extended-thinking.md): Learn about Gemini 3.8 Live Extended Thinking, our Live API model engineered for complex reasoning and asynchronous tool orchestration.
- [Gemini 3.7 Flash](https://aistudio.google.com/docs/models/gemini-3.7-flash.md): Learn about Gemini 3.7 Flash from Google
- [Gemini 3.6 Flash](https://aistudio.google.com/docs/models/gemini-3.6-flash.md): Learn about Gemini 3.6 Flash from Google
- [Gemini 3.5 Flash](https://aistudio.google.com/docs/models/gemini-3.5-flash.md): Learn about Gemini 3.5 Flash from Google
- [Gemini 3.5 Flash-Lite](https://aistudio.google.com/docs/models/gemini-3.5-flash-lite.md): Learn about Gemini 3.5 Flash-Lite from Google
- [Gemini Omni Flash](https://aistudio.google.com/docs/models/gemini-omni-flash.md): Learn about the Gemini Omni Flash video generation and editing model
- [Gemini 3.5 Transcribe](https://aistudio.google.com/docs/models/gemini-3.5-transcribe.md): Learn about the Gemini 3.5 Transcribe model from Google
- [Gemini 3.1 Flash Lite image (Nano Banana 2 Lite)](https://aistudio.google.com/docs/models/gemini-3.1-flash-lite-image.md): Learn about Gemini 3.1 Flash Lite Image from Google
- [Gemini 3.5 Live translate](https://aistudio.google.com/docs/models/gemini-3.5-live-translate-preview.md): Learn about the Gemini 3.5 Live Translate model from Google
- [Gemini 3 Flash preview](https://aistudio.google.com/docs/models/gemini-3-flash-preview.md): Learn about Gemini 3 Flash Preview from Google
- [Gemini 3.1 Flash TTS (text-to-speech) preview](https://aistudio.google.com/docs/models/gemini-3.1-flash-tts-preview.md): Learn about Gemini 3.1 Flash TTS Preview model from Google
- [Veo 3.1 Lite preview](https://aistudio.google.com/docs/models/veo-3.1-lite-generate-preview.md): Learn about the Veo 3.1 video generation model from Google
- [Gemini 3.1 Flash live preview](https://aistudio.google.com/docs/models/gemini-3.1-flash-live-preview.md): Learn about the Gemini 3.1 Flash Live Preview model from Google
- [Gemini 3.1 Flash-Lite](https://aistudio.google.com/docs/models/gemini-3.1-flash-lite.md): Learn about Gemini 3.1 Flash-Lite from Google
- [Gemini 3.1 Flash-Lite preview](https://aistudio.google.com/docs/models/gemini-3.1-flash-lite-preview.md): Learn about Gemini 3.1 Flash-Lite preview from Google
- [Gemini 2.5 Flash](https://aistudio.google.com/docs/models/gemini-2.5-flash.md): Learn about Gemini 2.5 Flash from Google
- [Gemini 2.5 Flash preview](https://aistudio.google.com/docs/models/gemini-2.5-flash-preview-09-2025.md): Learn about Gemini 2.5 Flash Preview from Google
- [Gemini 2.5 Flash image (Nano Banana)](https://aistudio.google.com/docs/models/gemini-2.5-flash-image.md): Learn about Gemini 2.5 Flash Image from Google
- [Gemini 2.5 Flash live preview](https://aistudio.google.com/docs/models/gemini-2.5-flash-native-audio-preview-12-2025.md): Learn about Gemini 2.5 Flash Live from Google
- [Gemini 2.5 Flash text-to-speech](https://aistudio.google.com/docs/models/gemini-2.5-flash-preview-tts.md): Learn about Gemini 2.5 Flash TTS from Google
- [Gemini 2.5 Flash-Lite](https://aistudio.google.com/docs/models/gemini-2.5-flash-lite.md): Learn about Gemini 2.5 Flash-Lite from Google
- [Gemini 2.5 Flash-Lite preview](https://aistudio.google.com/docs/models/gemini-2.5-flash-lite-preview-09-2025.md): Learn about Gemini 2.5 Flash-Lite Preview from Google
- [Gemini 2.5 Pro](https://aistudio.google.com/docs/models/gemini-2.5-pro.md): Learn about Gemini 2.5 Pro from Google
- [Gemini 2.5 Pro text-to-speech](https://aistudio.google.com/docs/models/gemini-2.5-pro-preview-tts.md): Learn about Gemini 2.5 Pro TTS from Google
- [Gemini 2.5 computer use model](https://aistudio.google.com/docs/models/gemini-2.5-computer-use-preview-10-2025.md): Learn about the Gemini Computer Use model from Google
- [Gemini 2.0 Flash](https://aistudio.google.com/docs/models/gemini-2.0-flash.md): Learn about Gemini 2.0 Flash from Google
- [Gemini 2.0 Flash-Lite](https://aistudio.google.com/docs/models/gemini-2.0-flash-lite.md): Learn about Gemini 2.0 Flash-Lite from Google
- [Imagen 4](https://aistudio.google.com/docs/models/imagen.md): Learn about Imagen 4 from Google
- [Veo 3.1](https://aistudio.google.com/docs/models/veo-3.1-generate-preview.md): Learn about the Veo 3.1 video generation model from Google
- [Veo 2.0](https://aistudio.google.com/docs/models/veo-2.0-generate-001.md): Learn about the Veo 2.0 video generation model from Google
- [Gemini Embedding model](https://aistudio.google.com/docs/models/gemini-embedding-001.md): Learn about the Gemini Embedding model from Google
- [Gemini Embedding 2 model](https://aistudio.google.com/docs/models/gemini-embedding-2.md): Learn about the Gemini Embedding 2 model from Google
- [Gemini Embedding 2 preview model](https://aistudio.google.com/docs/models/gemini-embedding-2-preview.md): Learn about the Gemini Embedding 2 model from Google
- [Gemini Robotics ER 2](https://aistudio.google.com/docs/models/gemini-robotics-er-2-preview.md): Learn about Gemini Robotics ER 2 from Google
- [Gemini Robotics ER 2 streaming](https://aistudio.google.com/docs/models/gemini-robotics-er-2-streaming-preview.md): Learn about Gemini Robotics ER 2 Streaming from Google
- [Gemini Robotics-ER 1.5](https://aistudio.google.com/docs/models/gemini-robotics-er-1.5-preview.md): Learn about Gemini Robotics Preview model from Google
- [Gemini Robotics-ER 1.6](https://aistudio.google.com/docs/models/gemini-robotics-er-1.6-preview.md): Learn about Gemini Robotics Preview model from Google
- [Deep Research Pro preview](https://aistudio.google.com/docs/models/deep-research-pro-preview-12-2025.md): Learn about Gemini Deep Research Pro preview model from Google
- [Deep Research preview](https://aistudio.google.com/docs/models/deep-research-preview-04-2026.md): Learn about Gemini Deep Research preview model from Google
- [Deep Research Max preview](https://aistudio.google.com/docs/models/deep-research-max-preview-04-2026.md): Learn about Gemini Deep Research Max preview model from Google
- [Antigravity preview 05-2026](https://aistudio.google.com/docs/models/antigravity-preview-05-2026.md): Learn about Antigravity Agent preview model from Google
- [Antigravity preview 09-2026](https://aistudio.google.com/docs/models/antigravity-preview-09-2026.md): Learn about Antigravity Agent preview model from Google
- [Lyria RealTime experimental](https://aistudio.google.com/docs/models/lyria-realtime-exp.md): Learn about the Lyria RealTime experimental music generation model from Google
- [Lyria 3.5](https://aistudio.google.com/docs/models/lyria-3.5.md): Learn about Lyria 3.5 from Google DeepMind
- [Lyria 3 Clip preview](https://aistudio.google.com/docs/models/lyria-3-clip-preview.md): Learn about Lyria 3 Clip Preview from Google DeepMind
- [Lyria 3 Pro preview](https://aistudio.google.com/docs/models/lyria-3-pro-preview.md): Learn about Lyria 3 Pro Preview from Google DeepMind
- [Latest Gemini models](https://aistudio.google.com/docs/latest-model.md): Learn what's new in Gemini 4 Argon (gemini-4-argon), Google's new Gemini 4 model with a 1M shared context window, long decode, pricing, and API migration guide.
- [What's new in Gemini 3.8 Flash](https://aistudio.google.com/docs/whats-new-gemini-3.8.md): Learn about what's new in Gemini 3.8 Flash, including model capabilities, API changes, and migration guidance.
- [What's new in Gemini 3.7 Flash](https://aistudio.google.com/docs/whats-new-gemini-3.7.md): Learn about what's new in Gemini 3.7 Flash, including model capabilities, API changes, and migration guidance.
- [What's new in Gemini 3.6 Flash and 3.5 Flash-Lite](https://aistudio.google.com/docs/whats-new-gemini-3.6.md): Learn about what's new in Gemini 3.6 Flash and Gemini 3.5 Flash-Lite, including model capabilities, API changes, and migration guidance.
- [What's new in Gemini 3.5 Flash](https://aistudio.google.com/docs/whats-new-gemini-3.5.md): Learn about the new features and migration guidance for Gemini 3.5 Flash.
- [Nano Banana](https://aistudio.google.com/docs/image-generation.md): Get started generating images with the Gemini API using Nano Banana and Nano Banana Pro
- [Veo](https://aistudio.google.com/docs/veo.md): Generate high-fidelity videos with native audio using Google's Veo 3.1 API.
- [Gemini Omni Flash](https://aistudio.google.com/docs/omni.md): Get started with Gemini Omni Flash for fast, conversational video generation and editing using the Interactions API.
- [Lyria 3.5 — Lyria 3.5 & Lyria Clip](https://aistudio.google.com/docs/music-generation.md): Generate music with the Gemini API using Lyria 3 Clip and Lyria 3.5.
- [Lyria 3.5 — Lyria RealTime](https://aistudio.google.com/docs/realtime-music-generation.md): Get started building with Lyria RealTime's real-time, streaming music generation in the Gemini API
- [Lyria 3.5 — Lyria prompt guide](https://aistudio.google.com/docs/lyria-prompt-guide.md): Guide to prompt engineering for music generation with Lyria 3.5 and Lyria RealTime in the Gemini API.
- [Imagen](https://aistudio.google.com/docs/imagen.md): Imagen models are shut down; migrate to Nano Banana for image generation.
- [Text-to-speech — Overview](https://aistudio.google.com/docs/speech-generation.md): Generate high-fidelity speech and multi-speaker audio with the Gemini API using gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts.
- [Text-to-speech — Voice design](https://aistudio.google.com/docs/voice-design.md): Create persistent custom vocal personas from natural-language descriptions with Gemini 3.8 TTS.
- [Text-to-speech — Voice replication](https://aistudio.google.com/docs/voice-replication.md): Replicate a speaker's voice with persistent voice IDs or stateless client keys in the Gemini API.
- [Transcribe](https://aistudio.google.com/docs/transcribe.md): Get started transcribing audio with the Gemini 3.5 Transcribe model in the Gemini API
- [Live](https://aistudio.google.com/docs/live-api.md): Enable low-latency, real-time voice and video interactions with the Live API.
- [Live translate](https://aistudio.google.com/docs/live-api/live-translate.md): Perform low-latency, real-time speech-to-speech translation with Live API.
- [Embeddings](https://aistudio.google.com/docs/embeddings.md): Generate vector embeddings for semantic search and classification using Gemini.
- [Robotics — Overview](https://aistudio.google.com/docs/robotics-overview.md): Overview of Gemini Robotics ER models and capabilities for building robotics applications.
- [Robotics — Spatial reasoning](https://aistudio.google.com/docs/robotics-spatial.md): Use Gemini Robotics ER for spatial reasoning tasks including object detection, tracking, and trajectory planning.
- [Robotics — Agentic vision](https://aistudio.google.com/docs/robotics-agentic.md): Use Gemini Robotics ER agentic capabilities including code execution, instrument reading, and image annotation.
- [Robotics — Task orchestration](https://aistudio.google.com/docs/robotics-orchestration.md): Orchestrate long-horizon robotics tasks by combining spatial reasoning with custom robot APIs.
- [Robotics — With streaming](https://aistudio.google.com/docs/robotics-streaming.md): Use the Gemini Live API with Gemini Robotics ER 2 Streaming preview for real-time, bidirectional robot orchestration.
- [Robotics — Video understanding](https://aistudio.google.com/docs/robotics-video-progress.md): Use Gemini Robotics ER 2 to track task progress and identify key moments in robot task videos.

## Core capabilities
- [Text](https://aistudio.google.com/docs/text-generation.md): Get started building text generation and multi-turn interaction apps with the Gemini API
- [Image — Image understanding](https://aistudio.google.com/docs/image-understanding.md): Get started building with Gemini's multimodal capabilities in the Gemini API
- [Video — Video overview](https://aistudio.google.com/docs/video.md): Generate and edit videos in the Gemini API using Gemini Omni Flash.
- [Video — Video understanding](https://aistudio.google.com/docs/video-understanding.md): Get started building with Gemini's multimodal capabilities in the Gemini API
- [Documents](https://aistudio.google.com/docs/document-processing.md): Learn how to use the Gemini API to process documents like PDFs
- [Speech and audio — Audio understanding](https://aistudio.google.com/docs/audio.md): Learn how to analyze audio input and generate text responses using the Gemini API.
- [Thinking — Thinking](https://aistudio.google.com/docs/thinking.md): Use thinking capabilities with the Gemini API
- [Thinking — Thought signatures](https://aistudio.google.com/docs/thought-signatures.md): Learn how the Interactions API handles thought signatures and model reasoning.
- [Structured outputs](https://aistudio.google.com/docs/structured-output.md): Learn how to generate structured JSON output with the Gemini API.
- [Function calling](https://aistudio.google.com/docs/function-calling.md): Get started using Function Calling with the Gemini API
- [Long context](https://aistudio.google.com/docs/long-context.md): Learn about how to get started building with long context (1 million context window) on Gemini.
- [Long decode](https://aistudio.google.com/docs/long-decode.md): Use long decode with Gemini 4 Argon on the Interactions API to generate past 64K tokens up to the 1M-token context window with background execution.

## Agents
- [Overview](https://aistudio.google.com/docs/agents.md): Build agents that reason, write code, manage files, and browse the web with the Gemini API.
- [Quickstart](https://aistudio.google.com/docs/managed-agents-quickstart.md): Quickstart guide for making your first call to the manage agents API.
- [Antigravity agent](https://aistudio.google.com/docs/antigravity-agent.md): Use the Antigravity managed agent to perform multi-step tasks that require reasoning, file operations, and tool use.
- [Building managed agents](https://aistudio.google.com/docs/custom-agents.md): How to create and use custom agents with managed agents in the Gemini API.
- [Environments](https://aistudio.google.com/docs/agent-environment.md): Learn how to provision, configure, and manage remote sandbox environments in Gemini Managed Agents.
- [Credentials](https://aistudio.google.com/docs/agent-credentials.md): Learn how to store and manage server-side credentials for managed agents, including bearer tokens, OAuth2 configurations, and environment variable secrets.
- [Hooks](https://aistudio.google.com/docs/agent-hooks.md): Configure synchronous hooks inside remote sandboxes to intercept tool calls for security, formatting, and auditing.
- [Deep Research agent](https://aistudio.google.com/docs/deep-research.md): Deep Research is an agent designed to perform complex, long-running context gathering and synthesis tasks.

## Tools
- [Overview](https://aistudio.google.com/docs/tools.md): Use tools with the Gemini API to extend the capabilities of Gemini models, enabling them to access real-time information and perform complex computational tasks.
- [Google Search](https://aistudio.google.com/docs/google-search.md): Ground your model's responses in real-time information from Google Search to improve factual accuracy and provide citations.
- [Google Maps](https://aistudio.google.com/docs/maps-grounding.md): Ground your model's responses in rich, real-world data from Google Maps to provide factually accurate, location-aware answers
- [Code execution](https://aistudio.google.com/docs/code-execution.md): Learn how to use the Gemini API code execution feature.
- [URL context](https://aistudio.google.com/docs/url-context.md): Ground your model's responses in real-time information by providing URLs as context for more accurate and citation-backed answers.
- [Computer use](https://aistudio.google.com/docs/computer-use.md): Learn how to use the Gemini API computer use feature.
- [File search](https://aistudio.google.com/docs/file-search.md): Get started building RAG solutions with the File Search tool in the Gemini API
- [Combine tools and function calling](https://aistudio.google.com/docs/tool-combination.md): Learn how to maintain context and enable built-in and custom tool combinations in the Gemini API.

## Live API
- [Get started — Using GenAI SDK](https://aistudio.google.com/docs/live-api/get-started-sdk.md): Build real-time Live API applications using the Google GenAI SDK.
- [Get started — Using WebSockets](https://aistudio.google.com/docs/live-api/get-started-websocket.md): Build bidirectional Live API applications directly using raw WebSockets.
- [Capabilities](https://aistudio.google.com/docs/live-api/capabilities.md): Explore the capabilities and configuration options of the Gemini Live API.
- [Thinking](https://aistudio.google.com/docs/live-api/thinking.md): Learn about Thinking in the Gemini Live API, including architectural differences, interaction status tracking, and non-blocking tools.
- [Live transcription](https://aistudio.google.com/docs/live-api/live-transcribe.md): Low-latency, real-time speech-to-text transcription using the gemini-3.5-transcribe-live model.
- [Tool use](https://aistudio.google.com/docs/live-api/tools.md): Use tools with the Gemini Live API to enable external actions in real time.
- [Session management](https://aistudio.google.com/docs/live-api/session-management.md): Manage real-time persistent sessions and connection states in the Live API.
- [Ephemeral tokens](https://aistudio.google.com/docs/live-api/ephemeral-tokens.md): Learn how to generate short-lived ephemeral tokens for client-side authentication in the Live API.
- [Best practices](https://aistudio.google.com/docs/live-api/best-practices.md): Learn best practices to optimize your use of the Gemini Live API.

## Optimization
- [Overview](https://aistudio.google.com/docs/optimization.md): Learn about the different inference and optimization options from the Gemini API.
- [Batch API](https://aistudio.google.com/docs/batch-api.md): Get started building with the Batch API
- [Webhooks](https://aistudio.google.com/docs/webhooks.md): Learn how to use webhooks in the Gemini API.
- [Flex inference](https://aistudio.google.com/docs/flex-inference.md): Learn how to optimize costs with the Flex inference tier in the Interactions API
- [Priority inference](https://aistudio.google.com/docs/priority-inference.md): Learn how to use Gemini Priority inference for business-critical workloads requiring lower latency.
- [Context caching](https://aistudio.google.com/docs/caching.md): Learn how to use Context Caching in the Interactions API

## Guides
- [Interactions API](https://aistudio.google.com/docs/interactions-overview.md): The Interactions API is the simplest and recommended way to build with Gemini models and agents.
- [Streaming](https://aistudio.google.com/docs/streaming.md): Learn how to stream responses, tool calls, thinking, and images in real time with the Interactions API.
- [Background execution](https://aistudio.google.com/docs/background-execution.md): Run long-running background tasks and agents using background=true in the Interactions API.
- [File input — Input methods](https://aistudio.google.com/docs/file-input-methods.md): Get started building with Gemini's multimodal capabilities in the Gemini API
- [File input — Files API](https://aistudio.google.com/docs/files.md): Learn how to upload, manage, and process media files using the Gemini Interactions API.
- [OpenAI compatibility](https://aistudio.google.com/docs/openai.md): Call Gemini models directly using standard OpenAI SDKs and REST endpoints.
- [Media resolution](https://aistudio.google.com/docs/media-resolution.md): Learn about how to use media resolutions with multimodal inputs in the Interactions API.
- [Token counting](https://aistudio.google.com/docs/tokens.md): Understand and count tokens with the Gemini API
- [Prompt engineering](https://aistudio.google.com/docs/prompting-strategies.md): Get started designing prompts for Gemini AI models.
- [Logs and datasets — Get started with logs](https://aistudio.google.com/docs/logs-datasets.md): Learn how to configure project logging, view logs in AI Studio, and create shared datasets.
- [Logs and datasets — Data logs and sharing](https://aistudio.google.com/docs/logs-policy.md): The policy for sharing your data logs for Gemini improvements.
- [Safety — Safety settings](https://aistudio.google.com/docs/safety-settings.md): Configure content moderation filters and safety thresholds in the Gemini API.
- [Safety — Safety guidance](https://aistudio.google.com/docs/safety-guidance.md): Apply best practices for safety, fairness, and factuality in Gemini apps.
- [Frameworks — LangChain & LangGraph](https://aistudio.google.com/docs/langgraph-example.md): Building LangGraph Agents with Gemini
- [Frameworks — CrewAI](https://aistudio.google.com/docs/crewai-example.md): Building CrewAI Agents with Gemini
- [Frameworks — LlamaIndex](https://aistudio.google.com/docs/llama-index.md): Building Research Agents with Gemini
- [Frameworks — Vercel AI SDK](https://aistudio.google.com/docs/vercel-ai-sdk-example.md): Building apps with Gemini and the AI SDK by Vercel
- [Frameworks — Temporal](https://aistudio.google.com/docs/temporal-example.md): Building durable AI agents with Gemini and Temporal

## Resources
- [Release notes](https://aistudio.google.com/docs/changelog.md): Keep track of updates to the Gemini API
- [Deprecations](https://aistudio.google.com/docs/deprecations.md): Keep track of deprecation schedules for Gemini models and features
- [Libraries](https://aistudio.google.com/docs/libraries.md): Download and get started with the Gemini API Libraries + SDKs
- [Migration — To GenAI SDK](https://aistudio.google.com/docs/migrate.md): Migrate existing applications to the unified Google Gen AI SDK.
- [Migration — To Interactions API](https://aistudio.google.com/docs/migrate-to-interactions.md): Guide for migrating from generateContent to the Interactions API.
- [Migration — Interactions breaking changes (May 2026)](https://aistudio.google.com/docs/interactions-breaking-changes-may-2026.md): Guide for migrating to upcoming breaking changes in the Interactions API, including the steps schema and response format changes.
- [Rate limits](https://aistudio.google.com/docs/rate-limits.md): Understand request quotas, token limits, and rate limits for the Gemini API.
- [Billing info](https://aistudio.google.com/docs/billing.md): Understand Gemini API billing tiers, pricing structures, and usage charges.
- [API troubleshooting](https://aistudio.google.com/docs/troubleshooting.md): Diagnose and resolve common errors and API exceptions when using Gemini.
- [API errors](https://aistudio.google.com/docs/api-errors.md): Reference for Interactions API error codes and response format
- [Partner and library integrations](https://aistudio.google.com/docs/partner-integration.md): Provide the Gemini API as an integration into your platform or library.
- [Google AI Studio — Quickstart](https://aistudio.google.com/docs/ai-studio-quickstart.md): Get started with prompt engineering and prototyping in Google AI Studio.
- [Google AI Studio — Google AI plans](https://aistudio.google.com/docs/google-ai-plans.md)
- [Google AI Studio — Vibe code in Build](https://aistudio.google.com/docs/aistudio-build-mode.md): Learn how to build full-stack applications using the vibe coding experience in Google AI Studio.
- [Google AI Studio — Full-stack apps](https://aistudio.google.com/docs/aistudio-fullstack.md): Learn how to develop full-stack applications with server-side logic in Google AI Studio.
- [Google AI Studio — Build Android apps](https://aistudio.google.com/docs/aistudio-android.md): Learn how to build native Android apps with Kotlin and Jetpack Compose in Google AI Studio.
- [Google AI Studio — Deploying your app](https://aistudio.google.com/docs/aistudio-deploying.md): Deploy full-stack generative AI applications directly from Google AI Studio.
- [Google AI Studio — Agents in AI Studio](https://aistudio.google.com/docs/aistudio-agents.md): Learn how to use Agents in AI Studio
- [Google AI Studio — Try out LearnLM](https://aistudio.google.com/docs/learnlm.md): Use pedagogical learning capabilities with standard Gemini models in AI Studio.
- [Google AI Studio — Troubleshooting](https://aistudio.google.com/docs/troubleshoot-ai-studio.md): This page provides suggestions for troubleshooting Google AI Studio if you encounter issues.
- [Google AI Studio — Google Workspace access](https://aistudio.google.com/docs/workspace.md): Access Google AI Studio and manage settings with a Workspace account.
- [Google Cloud Platform — Gemini Enterprise Agent Platform Gemini API](https://aistudio.google.com/docs/migrate-to-cloud.md): When developing generative AI solutions with Gemini, Google offers two API products: the Gemini Developer API and the Gemini platform API.
- [Google Cloud Platform — OAuth authentication](https://aistudio.google.com/docs/oauth.md): Authenticate to the Gemini API securely using OAuth client credentials.

## Policies
- [Terms of service](https://aistudio.google.com/docs/terms.md)
- [Additional Terms of Service archive](https://aistudio.google.com/docs/terms-archive/index.md)
- [Available regions](https://aistudio.google.com/docs/available-regions.md): Check the supported regions and access rules for AI Studio and Gemini API.
- [Abuse monitoring](https://aistudio.google.com/docs/usage-policies.md): Review Gemini API terms of service, usage policies, and abuse monitoring.
- [Feedback information](https://aistudio.google.com/docs/feedback-policies.md): Review AI Studio feedback workflows, data usage, and evaluation policies.

## API reference
- [Overview](https://aistudio.google.com/api-reference.md): Unary REST, streaming, and WebSocket API reference for Gemini models and managed agents.
- [API versions](https://aistudio.google.com/api-reference/api-versions.md): Understand the differences between the v1 and v1beta API versions of the Gemini API.

## API reference — Core APIs
- [Interactions API — Overview](https://aistudio.google.com/api-reference/interactions-api.md): The Gemini Interactions API allows developers to build generative AI applications using Gemini models.
- [Interactions API — create](https://aistudio.google.com/api-reference/interactions-api/create-interaction.md): Creates a new interaction.
- [Interactions API — cancel](https://aistudio.google.com/api-reference/interactions-api/cancel-interaction-by-id.md): Cancels an interaction by id.
- [Interactions API — get](https://aistudio.google.com/api-reference/interactions-api/get-interaction-by-id.md): Retrieves the full details of a single interaction based on its `Interaction.id`.
- [Interactions API — delete](https://aistudio.google.com/api-reference/interactions-api/delete-interaction.md): Deletes the interaction by id.
- [GenerateContent — Overview](https://aistudio.google.com/api-reference/generate-content.md): The Gemini API supports content generation with images, audio, code, tools, and more.
- [GenerateContent — generateContent](https://aistudio.google.com/api-reference/generate-content/generate-content.md): Generates a model response given an input `GenerateContentRequest`.
- [GenerateContent — streamGenerateContent](https://aistudio.google.com/api-reference/generate-content/stream-generate-content.md): Generates a [streamed response](/docs/text-generation#streaming-responses) from the model given an input `GenerateContentRequest`.
- [GenerateContent — createToken](https://aistudio.google.com/api-reference/generate-content/create-token.md): Creates a token that can be used to constrain the behavior of a BidiGenerateContent session.

## API reference — Real-time APIs
- [Live API — Overview](https://aistudio.google.com/api-reference/live.md): Reference for the stateful, WebSockets-based Live API, including session configuration and the client and server messages it exchanges.
- [Live API — Starting a Live session](https://aistudio.google.com/api-reference/live/bidi-generate-content.md): Opens a stateful WebSocket session for exchanging text, audio, and video with the model.
- [Live Music API — Overview](https://aistudio.google.com/api-reference/live-music.md): Reference for the WebSockets-based Live Music API used for real-time music generation with Lyria RealTime.
- [Live Music API — Starting a Live Music session](https://aistudio.google.com/api-reference/live-music/bidi-generate-music.md): Opens a WebSocket session that streams music generated in real time from your prompts and playback controls.

## API reference — Agent APIs
- [Agents — Overview](https://aistudio.google.com/api-reference/agents.md): Agents are systems that leverage Gemini models, a set of tools, and reasoning capabilities to perform complex, multi-step tasks and achieve specific goals.
- [Agents — create](https://aistudio.google.com/api-reference/agents/create-agent.md): Creates a new Agent (Typed version for SDK).
- [Agents — list](https://aistudio.google.com/api-reference/agents/list-agents.md): Lists all Agents.
- [Agents — get](https://aistudio.google.com/api-reference/agents/get-agent.md): Gets a specific Agent.
- [Agents — delete](https://aistudio.google.com/api-reference/agents/delete-agent.md): Deletes an Agent.
- [Environments — Overview](https://aistudio.google.com/api-reference/environments.md): Environments provide isolated execution contexts for running agent code, tools, and services securely.
- [Environments — create](https://aistudio.google.com/api-reference/environments/create-environment.md): Creates an environment.
- [Environments — list](https://aistudio.google.com/api-reference/environments/list-environments.md): Lists environments.
- [Environments — getEnvironmentFiles](https://aistudio.google.com/api-reference/environments/get-environment-files.md): Retrieves file metadata or directory contents from an environment's snapshot.
- [Environments — get](https://aistudio.google.com/api-reference/environments/get-environment.md): Gets an environment.
- [Environments — startEnvironmentFileUpload](https://aistudio.google.com/api-reference/environments/start-environment-file-upload.md): Starts a resumable upload session for a file in an environment workspace.
- [Environments — delete](https://aistudio.google.com/api-reference/environments/delete-environment.md): Deletes an environment.
- [Triggers — Overview](https://aistudio.google.com/api-reference/triggers.md): Triggers allow you to schedule agent executions on a cron schedule, enabling automated and recurring tasks.
- [Triggers — create](https://aistudio.google.com/api-reference/triggers/create-trigger.md): Creates a new trigger that will invoke the specified agent on the given cron schedule.
- [Triggers — runTrigger](https://aistudio.google.com/api-reference/triggers/run-trigger.md): Runs a trigger immediately.
- [Triggers — list](https://aistudio.google.com/api-reference/triggers/list-triggers.md): Lists triggers for a project.
- [Triggers — get](https://aistudio.google.com/api-reference/triggers/get-trigger.md): Gets details of a single trigger.
- [Triggers — listTriggerExecutions](https://aistudio.google.com/api-reference/triggers/list-trigger-executions.md): Lists executions for a trigger.
- [Triggers — update](https://aistudio.google.com/api-reference/triggers/update-trigger.md): Updates a trigger.
- [Triggers — delete](https://aistudio.google.com/api-reference/triggers/delete-trigger.md): Deletes a trigger.
- [Webhooks — Overview](https://aistudio.google.com/api-reference/webhooks.md): Webhooks allow the Gemini API to push real-time notifications to your server when asynchronous or Long-Running Operations (LROs) complete.
- [Webhooks — create](https://aistudio.google.com/api-reference/webhooks/create-webhook.md): Creates a new Webhook.
- [Webhooks — pingWebhook](https://aistudio.google.com/api-reference/webhooks/ping-webhook.md): Sends a ping event to a Webhook.
- [Webhooks — rotateSigningSecret](https://aistudio.google.com/api-reference/webhooks/rotate-signing-secret.md): Generates a new signing secret for a Webhook.
- [Webhooks — list](https://aistudio.google.com/api-reference/webhooks/list-webhooks.md): Lists all Webhooks.
- [Webhooks — get](https://aistudio.google.com/api-reference/webhooks/get-webhook.md): Gets a specific Webhook.
- [Webhooks — update](https://aistudio.google.com/api-reference/webhooks/update-webhook.md): Updates an existing Webhook.
- [Webhooks — delete](https://aistudio.google.com/api-reference/webhooks/delete-webhook.md): Deletes a Webhook.
- [Credentials — Overview](https://aistudio.google.com/api-reference/credentials.md): The Credentials API allows you to create, retrieve, update, list, and delete server-managed credentials (such as API keys, OAuth2 tokens, HTTP Bearer tokens, and environment variables) to authenticate tool calls and MCP servers.
- [Credentials — create](https://aistudio.google.com/api-reference/credentials/create-credential.md): Creates a new credential.
- [Credentials — list](https://aistudio.google.com/api-reference/credentials/list-credentials.md): Lists credentials.
- [Credentials — get](https://aistudio.google.com/api-reference/credentials/get-credential.md): Gets a credential by ID.
- [Credentials — update](https://aistudio.google.com/api-reference/credentials/update-credential.md): Updates a credential.
- [Credentials — delete](https://aistudio.google.com/api-reference/credentials/delete-credential.md): Deletes a credential.

## API reference — Platform APIs
- [Files API — Overview](https://aistudio.google.com/api-reference/files.md): The Gemini API supports uploading media files separately from the prompt input, allowing your media to be reused across multiple requests and multiple prompts.
- [Files API — get](https://aistudio.google.com/api-reference/files/get-file.md): Gets the metadata for the given `File`.
- [Files API — list](https://aistudio.google.com/api-reference/files/list-files.md): Lists the metadata for `File`s owned by the requesting project.
- [Files API — delete](https://aistudio.google.com/api-reference/files/delete-file.md): Deletes the `File`.
- [Files API — registerFiles](https://aistudio.google.com/api-reference/files/register-files.md): Registers a Google Cloud Storage files with FileService.
- [Files API — create](https://aistudio.google.com/api-reference/files/create-file.md): Creates a `File`.
- [File Search stores — Overview](https://aistudio.google.com/api-reference/file-search/file-search-stores.md): The File Search API provides a hosted question answering service for building Retrieval Augmented Generation (RAG) systems using Google's infrastructure.
- [File Search stores — create](https://aistudio.google.com/api-reference/file-search/file-search-stores/create-file-search-store.md): Creates an empty `FileSearchStore`.
- [File Search stores — delete](https://aistudio.google.com/api-reference/file-search/file-search-stores/delete-file-search-store.md): Deletes a `FileSearchStore`.
- [File Search stores — get](https://aistudio.google.com/api-reference/file-search/file-search-stores/get-file-search-store.md): Gets information about a specific `FileSearchStore`.
- [File Search stores — list](https://aistudio.google.com/api-reference/file-search/file-search-stores/list-file-search-stores.md): Lists all `FileSearchStores` owned by the user.
- [File Search stores — importFile](https://aistudio.google.com/api-reference/file-search/file-search-stores/import-file.md): Imports a `File` from File Service to a `FileSearchStore`.
- [File Search stores — getFileSearchStoreOperation](https://aistudio.google.com/api-reference/file-search/file-search-stores/get-file-search-store-operation.md): Gets the latest state of a long-running operation.
- [File Search stores — getFileSearchStoreUploadOperation](https://aistudio.google.com/api-reference/file-search/file-search-stores/get-file-search-store-upload-operation.md): Gets the latest state of a long-running operation.
- [File Search stores — uploadToFileSearchStore](https://aistudio.google.com/api-reference/file-search/file-search-stores/upload-to-file-search-store.md): Uploads data to a FileSearchStore, preprocesses and chunks before storing it in a FileSearchStore Document.
- [File Search documents — Overview](https://aistudio.google.com/api-reference/file-search/documents.md): The File Search API references your raw source files, or documents, as temporary File objects.
- [File Search documents — delete](https://aistudio.google.com/api-reference/file-search/documents/delete-document.md): Deletes a `Document`.
- [File Search documents — get](https://aistudio.google.com/api-reference/file-search/documents/get-document.md): Gets information about a specific `Document`.
- [File Search documents — list](https://aistudio.google.com/api-reference/file-search/documents/list-documents.md): Lists all `Document`s in a `Corpus`.
- [Caching — Overview](https://aistudio.google.com/api-reference/caching.md): Context caching allows you to save and reuse precomputed input tokens that you wish to use repeatedly, for example when asking different questions about the same media file.
- [Caching — create](https://aistudio.google.com/api-reference/caching/create-cached-content.md): Creates CachedContent resource.
- [Caching — list](https://aistudio.google.com/api-reference/caching/list-cached-contents.md): Lists CachedContents.
- [Caching — get](https://aistudio.google.com/api-reference/caching/get-cached-content.md): Reads CachedContent resource.
- [Caching — update](https://aistudio.google.com/api-reference/caching/update-cached-content.md): Updates CachedContent resource (only expiration is updatable).
- [Caching — delete](https://aistudio.google.com/api-reference/caching/delete-cached-content.md): Deletes CachedContent resource.
- [Embeddings — Overview](https://aistudio.google.com/api-reference/embeddings.md): Embeddings are a numerical representation of text input that open up a number of unique use cases, such as clustering, similarity measurement and information retrieval.
- [Embeddings — embedContent](https://aistudio.google.com/api-reference/embeddings/embed-content.md): Generates a text embedding vector from the input `Content` using the specified [Gemini Embedding model](/docs/models#specialized-task-models).
- [Embeddings — batchEmbedContents](https://aistudio.google.com/api-reference/embeddings/batch-embed-contents.md): Generates multiple embedding vectors from the input `Content` which consists of a batch of strings represented as `EmbedContentRequest` objects.
- [Embeddings — asyncBatchEmbedContent](https://aistudio.google.com/api-reference/embeddings/async-batch-embed-content.md): Enqueues a batch of `EmbedContent` requests for batch processing.
- [Batch API — Overview](https://aistudio.google.com/api-reference/batch-api.md): The Gemini API supports batch APIs, which let you process multiple requests in a single call.
- [Batch API — batchGenerateContent](https://aistudio.google.com/api-reference/batch-api/batch-generate-content.md): Enqueues a batch of `GenerateContent` requests for batch processing.
- [Batch API — asyncBatchEmbedContent](https://aistudio.google.com/api-reference/batch-api/async-batch-embed-content.md): Enqueues a batch of `EmbedContent` requests for batch processing.
- [Batch API — get](https://aistudio.google.com/api-reference/batch-api/get-batch.md): Gets the latest state of a long-running operation.
- [Batch API — list](https://aistudio.google.com/api-reference/batch-api/list-batches.md): Lists operations that match the specified filter in the request.
- [Batch API — cancel](https://aistudio.google.com/api-reference/batch-api/cancel-batch.md): Starts asynchronous cancellation on a long-running operation.
- [Batch API — delete](https://aistudio.google.com/api-reference/batch-api/delete-batch.md): Deletes a long-running operation.
- [Batch API — update](https://aistudio.google.com/api-reference/batch-api/update-generate-content-batch.md): Updates a batch of GenerateContent requests for batch processing.
- [Batch API — updateEmbedContentBatch](https://aistudio.google.com/api-reference/batch-api/update-embed-content-batch.md): Updates a batch of EmbedContent requests for batch processing.
- [Tokens — Overview](https://aistudio.google.com/api-reference/tokens.md): For a detailed guide on counting tokens using the Gemini API, including how images, audio and video are counted, see the [Token counting guide](/docs/tokens) and accompanying [Cookbook recipe](https://colab.research.google.com/github/google-gemini/cookbook/blob/main/quickstarts/Counting_Tokens.ipynb).
- [Tokens — countTokens](https://aistudio.google.com/api-reference/tokens/count-tokens.md): Runs a model's tokenizer on input `Content` and returns the token count.
- [Voices — Overview](https://aistudio.google.com/api-reference/voices.md): The Voices API allows you to create custom voices from natural language prompts (Voice Design) or from reference audio and speaker consent recordings (Voice Replication), as well as list, retrieve, and manage custom and prebuilt voices for Text-to-Speech (TTS) synthesis.
- [Voices — create](https://aistudio.google.com/api-reference/voices/create-voice.md): Creates a custom voice from a natural-language prompt (`VOICE_TYPE_PROMPTED`) or from reference and consent audio recordings (`VOICE_TYPE_REPLICATED`).
- [Voices — list](https://aistudio.google.com/api-reference/voices/list-voices.md): Lists custom stored voices owned by the caller (ordered newest first) followed by prebuilt system voices from Google's voice catalog.
- [Voices — get](https://aistudio.google.com/api-reference/voices/get-voice.md): Gets a custom stored voice (`store = true`) by resource name.
- [Voices — delete](https://aistudio.google.com/api-reference/voices/delete-voice.md): Deletes a custom stored voice (`store = true`) by resource name.
- [Model API — Overview](https://aistudio.google.com/api-reference/models.md): The models endpoint provides a way for you to programmatically list the available models, and retrieve extended metadata such as supported functionality and context window sizing.
- [Model API — get](https://aistudio.google.com/api-reference/models/get-model.md): Gets information about a specific `Model` such as its version number, token limits, [parameters](/docs/prompting-strategies#model-parameters) and other metadata.
- [Model API — list](https://aistudio.google.com/api-reference/models/list-models.md): Lists the [`Model`s](/docs/models) available through the Gemini API.
- [All methods](https://aistudio.google.com/api-reference/all-methods.md): Every REST method in the Gemini API, grouped by reference page.

## Optional
- [Full documentation corpus (llms-full.txt)](https://aistudio.google.com/llms-full.txt): Complete concatenated documentation for context caching.