name: google-ai-docs description: "Use when learning about Gemini model capabilities, guides, and concepts: text generation, thinking/reasoning, vision, audio, video, structured output, function calling, code execution, grounding, prompt caching, context windows, safety, embeddings, pricing, or OpenAI compatibility."
Google AI (Gemini) Developer Guides
Official Gemini developer guides (sourced from ai.google.dev/gemini-api/docs).
CRITICAL: grep references/ for keywords before answering.
Topic Index
quickstart.md— Getting startedtext-generation.md— Text generationthinking.md— Thinking/reasoning modeimage-understanding.md— Visionaudio.md— Audio understandingvideo.md— Video understandingstructured-output.md— JSON schema outputfunction-calling.md— Function/tool callingcode-execution.md— Code executiongrounding.md— Grounding with Google Searchcaching.md— Context cachingcontext-window.md— Context window managementlong-context.md— Long contextembeddings.md— Embeddingsfiles.md— File uploadslive.md— Live/real-time APIsafety.md— Safety settingspricing.md— Pricingopenai.md— OpenAI SDK compatibility