Google's agent-first IDE at antigravity.google. Public preview remains free. Do not treat a Windsurf acquisition as a first-party fact.

Google's agent SDK in Python, Java, Go, and TypeScript. Docs now live at google.github.io/adk-docs. A2A is a separate protocol repo.

OpenAI-compatible AI API gateway: one base URL and key for 60+ models from GPT, Claude, Gemini, DeepSeek, Sora, and VEO, with routing, failover, and unified.

Previous Gemini 2.0 Flash Thinking snapshot. Not a 2026 o1-mini alternative.

Previous Gemini 2.0 Flash snapshot. Live Flash is Gemini 3.7 Flash.

Previous Gemini 3 Pro Preview snapshot. Not a 2026 vision crown.

Chrome built-in Gemini. Auto browse preview is U.S. AI Pro/Ultra, not free-for-all.

Image generation and editing skill built on the OpenRouter Image API, reaching Gemini, FLUX, Seedream, Recraft, and GPT-Image from one script.

Diagram skill that generates scientific figures with Nano Banana 2 and regenerates only when a Gemini 3.6 Flash review scores below your document type's bar.

Google Labs' Gemini-powered UI design tool that generates app screens and exports an agent-readable DESIGN.md design system file.

Google Gemini 3.1 Flash-Lite: leftover cheap Flash-Lite sibling on the live models page.

Google Gemini 3.1 Flash Live: leftover live/audio sibling on the Gemini models page. Not the 2026 Flash default.

Google Gemini 3.1 Flash TTS: leftover TTS sibling on the live Gemini models page. Not the 2026 Flash default.

Google Gemini 3.1 Pro: leftover Pro sibling on the live models page. Not a 2026 Pro default.

Google Gemini 3.5 Flash-Lite: leftover cheap Flash-Lite row on the live Gemini models page.

Google's agent-first frontier model: long-horizon agentic tasks, coding, and a 1M-token context at Flash-tier speed and cost.

Google Gemini 3.5 Live Translate: leftover live-translate sibling on the live Gemini models page. Not the 2026 Flash default. No invent.

Google Gemini 3.6 Flash: previous-generation Flash after 3.5, before live 3.7 Flash.

Google's most capable Flash model for agentic workflows and multimodal reasoning, with 1M-token context, 65k output tokens, and Computer Use preview.

Gemini 3.8 Flash TTS designs custom voices from a prompt, replicates a voice from 30 seconds of audio, and leads Hume's voice design benchmark at 71.4.

Google's new frontier model for long-horizon coding, enterprise knowledge work, and cyber defense, with a 1M output-token limit and phased Fairwind access.

Google Gemini Nano Banana 2 Lite: leftover cheaper Nano Banana 2 sibling on the live Gemini image page.

Google Gemini Omni Flash: leftover Omni Flash sibling on the live Gemini models page. Not the 2026 Flash default.