Stories from the gateway
Models
Model Selection for Cost Ceilings: Working Backwards From a Budget
When the budget is fixed before the model is chosen, selection inverts. How to derive a per-request token allowance and pick what fits inside it.
· 9 min read
Fundamentals
Model Size vs Capability: Why Bigger Stopped Meaning Better
Parameter counts once tracked capability closely and no longer do. What size still predicts, what it never predicted, and what to check instead.
· 9 min read
Models
Models That Fit on One GPU: What You Can Actually Run
· 9 min read
Fundamentals
Multi-Head Latent Attention Explained
· 9 min read
Models
Multi-Model Strategies: Splitting Work Across Two or Three Models
· 9 min read
Fundamentals
Needle-in-a-Haystack Tests: What They Prove and What They Miss
· 9 min read
Cost & Pricing
Negotiating AI Contracts: What Is Actually on the Table
· 9 min read
Guides
Neovim LLM Setup: Adapters, Keys and Custom Endpoints
· 8 min read
Models
Open Model Pricing Compared: What the Per-Token Rate Hides
· 9 min readModels
Open-Weight Model Licences Compared: What You Can Ship
· 9 min readModels
Open-Weight vs Closed Models: What the Gap Costs You Now
· 9 min read
Guides
OpenAI Node SDK Setup Against a Custom Base URL
· 9 min readGuides
OpenAI Python SDK Setup for Any Compatible Endpoint
· 9 min readGuides
opencode Setup Guide: Custom Providers in the Terminal
· 8 min readReady to start?
Every model, one key. Start free and upgrade when you are ready.