How
routes work, cuts inference cost, and reviews its own diffs
Engineering notes on routing, model cost, and coding agents, written by the people building ML.ai.
21 articles
October 28, 2026 · Engineering
VS Code AI Extension Cost Control: 9 Things to Check Before You Install
How to pick a VS Code AI extension that controls token spend: routing, caching, context limits, plan mode and team budgets, with real numbers.
15 min read
October 28, 2026 · Engineering
How to Evaluate an AI Code Review Tool: A Buyer's Checklist
How to evaluate an AI code review tool on your own PRs: act-on rate, catch rate, noise, security, and cost per useful comment, with real team results.
17 min read
October 28, 2026 · Engineering
OpenAI API Pricing Explained: What You're Really Paying For
OpenAI API pricing for GPT-6 Astra, Sol, and Luna, plus the cache-write, reasoning, tool, and Fast mode costs that set your real bill, with savings math.
18 min read
October 28, 2026 · Engineering
Claude API Pricing Explained: Cost Breakdown by Model (October 2026)
Claude API pricing for every model in October 2026: Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1 rates, caching, batch, tool fees, and how to cut your bill.
21 min read
October 12, 2026 · Engineering
14 Best Token optimization techniques for production AI workloads
14 token optimization techniques for production AI workloads, each with a measured saving, the quality cost, and the provider thresholds that make caching fail.
27 min read
October 12, 2026 · Engineering
Five Ways Engineering Teams Are Cutting AI Spend in 2026 (and What Each One Returned)
Five ways engineering teams reduce AI spend in 2026, each with the team that did it, the exact steps they took, and what it returned.
23 min read
Try today, or talk to us about what is next
Install the editor agent on your own machine, or book a call to talk through your team’s workloads