Google's family of multimodal AI models, and the Gemini app built on them
Gemini is Google's family of multimodal models and the assistant app built on them. In the Gemini API the lineup is tiered into Pro, Flash and Flash-Lite models: Gemini 3.1 Pro is in preview with a 1,048,576-token input limit, Gemini 3.8 Flash is the newest Flash release, and the Gemini 2.5 models remain available. The Gemini app has a free tier and paid Google AI Plus, Pro and Ultra plans.
Cody Free and Pro were discontinued in July 2025, and Copilot's billing model changed again in June 2026. A comparison of what these tools actually offer today — context handling, editor integration, and honest trade-offs.
8 min readVibe coding went from a tweet to Collins Dictionary's Word of the Year in ten months. Here's the term's real definition, where the workflow genuinely works, where it fails badly, and how to use it without wrecking your codebase.
8 min readA practical guide to the AI coding assistants developers actually use in 2025 — how completion, chat, and agentic tools differ, what each one is good at, where they reliably fail, and how to pick without switching editors.
11 min read