GPT-5.4 vs GPT-5.4 mini: Routing Math After GPT-6
GPT-5.4 mini costs 70% less per token than GPT-5.4. October 2026 prices, worked cost math, and the same routing choice with GPT-6 and GPT-5.6 models.
Tag archive
GPT-5.4 mini costs 70% less per token than GPT-5.4. October 2026 prices, worked cost math, and the same routing choice with GPT-6 and GPT-5.6 models.
Last week I kept a running list of every concrete cost-cutting technique AI teams shared in public....

Quick Answer LLM cost control in .NET: Learn how to slash Azure OpenAI spend in .NET...
I almost skipped writing this one up as its own piece, because on the surface it looked like four...
DeepLearning.AI's LangChain courses nail the fundamentals, but stop where demos end and production begins. Drawing on two years of shipping RAG systems
Andrew Ng's LangChain courses get you to a demo, but shipping to paying customers means handling retries, multi-provider fallbacks, per-tenant cost caps
I’ve probably mentioned that I’ve been trying to stop paying Opus prices for work that does not...
I run one production codebase, three client projects, and a handful of internal tools with agentic...
I used to think picking a coding harness was mostly a taste decision. Vim bindings or not, a TUI you...
A couple of posts back I pulled a month of my own session logs to catch coding red-handed as the...
I spent last week rebuilding a small experiment I first read about in Youssef Hosni’s piece on...
Everyone read the same headline number: Claude Fable got about 25 percent cheaper, up to 45 percent...