Before You Swap in gemini-4-argon, Search Your Own Code for What to Remove
Four habits can break or silently change when you move to gemini-4-argon: explicit caches, sampling parameters, small max_output_tokens and short timeouts. A stdlib-only script finds them in your repository, with what to check after the swap and when to stay on Flash.
Gemini 3.8 Flash Costs the Same Per Token and Can Still Raise Your Bill
Gemini 3.8 Flash carries the same per-token price as 3.7 Flash, but it is designed to work harder, so output tokens can grow and your bill with them. Here is what to measure before you switch, and how to price it across the January boundary.
Spend Deep Reasoning Only Where It's Needed: Per-Request thinking_level Routing in Gemini
Running every request at high thinking_level bloats latency and cost; forcing low drops accuracy on hard questions. This walks through a router that picks Gemini 3.x thinking_level per request from an inexpensive difficulty estimate, keeping p95 latency inside a mobile budget while reserving deep reasoning for the questions that need it — with measured numbers and working code.