# Google AI Docs

> 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.

- Skill: `wenerme/google-ai-docs` (Agent Skill, multi-file: 102 files)
- Install (CLI): `npx skillmds@latest add wenerme/google-ai-docs`
- Raw SKILL.md: https://api.skillmd.com/api/skills/wenerme/google-ai-docs/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: wenerme (https://skillmd.com/u/wenerme)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/wenerme/google-ai-docs

---


# Google AI (Gemini) Developer Guides

Official Gemini developer guides (sourced from [ai.google.dev/gemini-api/docs](https://ai.google.dev/gemini-api/docs)).

CRITICAL: grep `references/` for keywords before answering.

## Topic Index

- `quickstart.md` — Getting started
- `text-generation.md` — Text generation
- `thinking.md` — Thinking/reasoning mode
- `image-understanding.md` — Vision
- `audio.md` — Audio understanding
- `video.md` — Video understanding
- `structured-output.md` — JSON schema output
- `function-calling.md` — Function/tool calling
- `code-execution.md` — Code execution
- `grounding.md` — Grounding with Google Search
- `caching.md` — Context caching
- `context-window.md` — Context window management
- `long-context.md` — Long context
- `embeddings.md` — Embeddings
- `files.md` — File uploads
- `live.md` — Live/real-time API
- `safety.md` — Safety settings
- `pricing.md` — Pricing
- `openai.md` — OpenAI SDK compatibility