AI Stack The $0 AI Stack: 500+ Articles on Free-Tier APIs in 2026
I replaced $744/year of AI subscriptions with $0 — Gemini free tier, GLM-5.1, OpenRouter routing. 500+ published articles later, here's the exact stack.
Soya Shintani
AI Stack AI Tools Renoise AI Review: 8 Hours of Video Editing Became 40 Minutes
Renoise AI uses the Seedance 2.0 model to remove the timeline from video editing completely. Learn how this autonomous agent generates 100 ad-ready video variations from a single prompt, fully integrating with Claude Code.
AI Models Qwen 3.6 Plus Review: A Free 1M-Token Model That Actually Works
Alibaba's Qwen 3.6 Plus: 1M token context, free preview, real coding and multilingual chops. Where it replaces Claude and GPT — and where it clearly doesn't.
AI Models Claude vs GPT vs Gemini: 90 Days of Real Work in 2026
90 days running Claude, GPT, and Gemini side-by-side on production tasks. Benchmarks lie, real workflows don't. Here's which model wins which job in 2026.
AI Models MiniMax M2.7 Review: Claude Opus Performance at 1/17 the Price
MiniMax M2.7 hits frontier coding benchmarks at $0.30 per million tokens — 17× cheaper than Claude Opus. The self-evolving training trick and where it wins.
AI Stack GLM-5.1 Routing: Cut Claude Code API Costs by 60% in 2026
GLM-5.1 costs $0.07/M tokens vs Claude Opus at $5.00. Route 70% of traffic to GLM and your Claude Code bill drops 60% — here's the exact config and quality check.
AI Models Gemma 4 on a MacBook: The Local LLM That Ships Real Code
Gemma 4 runs on 4GB, fits on a MacBook, and writes production code. Open weights, the exact setup, the benchmarks, and the honest limits — after two weeks of use.
Workflow How I Delegate 70% of My Content Work to AI — and Keep Quality
15 hours per week back, same output quality. The exact delegation matrix between me and the AI — which 70% to hand off, and which 30% you must never give up.
Workflow Single-Model Content Pipeline: 3 Months Running Claude-Only
What happens when you run research, drafting, editing, and publishing through one model for 90 days? The time savings, the failure modes, the full Claude workflow.
Claude Claude Mythos: The Anthropic Model That Was Too Dangerous to Ship
Anthropic built Claude Mythos, decided not to release it, and told the world why. Inside Project Glasswing — and what withholding a frontier model actually signals.