Building on Free Tiers: Practical Guides
What you can build with no budget, and where the free tiers end: limits measured, workarounds that held up, and the trade-offs.
7 articles
How to Reduce LLM Token Usage Without Worse Answers
Practical ways to cut LLM token usage — skip the model when rules suffice, send less context, route to smaller models, cache repeated answers, use provider prompt caching and cap output — with measured numbers from a production assistant.
A Free AI Gateway: Gemini + Groq Failover That Stays Fast
How to put several free AI providers behind one function — per-use-case model chains, cooldowns on 429s and timeouts, no interactive retries, and the measurements that showed why each rule exists.
Free Help Desk Software: What You Actually Get
What free help desk plans typically include and leave out — seats, SLAs, automation, AI, reporting, data export — the hidden costs, and a checklist to evaluate any free plan before your team depends on it.
SaaS on Free Tiers: An Architecture That Actually Holds
How to run a real SaaS on free tiers — Supabase, free AI APIs, free email — with the actual limits, what breaks first, the commercial-use rules people miss, and the design choices that keep it inside the budget.
The Case for AI That Degrades Gracefully
AI features fail — rate limits, timeouts, outages, wrong answers. Design so the product still works when they do: save first, suggest don't decide, fall back to rules and cached answers, and tell users plainly.
Rate Limiting API Routes Without Redis (Using Postgres)
A per-user rate limiter built in Postgres — a hits table, a sliding window, an advisory lock against races, and a cleanup job — plus per-IP limits for login, and when you really do need Redis.
Free Transactional Email with Resend (Next.js Guide)
Send invites, password resets and notifications from a Next.js app on Resend's free tier — one fetch call, a verified domain, SPF/DKIM/DMARC, a graceful no-op when unconfigured, and what the limits mean in practice.