Series
Choosing Your AI Stack
A six-part series on picking models, pricing models, and building workflows that aren't locked to any single provider.
6 parts · first published
- 01
Token vs Subscription: Which AI Pricing Model Is Right for You
The break-even math is simpler than you think. Light users overpay on tokens. Heavy users overpay on subscriptions. Here's how to figure out which side you're on.
· 5 min read - 02
Claude Models Explained: Opus, Sonnet, Haiku for Coding
Opus for architecture, Sonnet for execution, Haiku for the fast repetitive stuff. And prompt caching that makes the pricing math work in your favour.
· 6 min read - 03
DeepSeek for Developers: Capable, Cheap, and Worth Knowing
DeepSeek-V3 matches Claude Sonnet on many coding benchmarks at roughly 10x lower API cost. Here's what it's actually good at, where it falls short, and what you need to know about data residency.
· 6 min read - 04
GLM Models: The Open-Source Alternative from Zhipu AI
GLM-4 and CodeGeeX aren't widely discussed in Western developer circles. They should be. Open weights, strong multilingual coding, and a dedicated IDE extension that's genuinely good.
· 5 min read - 05
Local Models: When You Run the Weights Yourself
Your code never leaves your machine. No API costs. No rate limits. The tradeoffs are real, but for the right use case, running local models is the right call.
· 6 min read - 06
Building Model-Agnostic Workflows
The model you use today will not be the best model in 12 months. Write your workflow so that switching costs hours, not weeks.
· 7 min read