226 posts tagged with "Cost Optimization"
Cloud vs owned-hardware cost breakdowns and bill analysis
Railway Killed Its Free Tier for a One-Time $5 Credit: What a Real Hobby App Costs on Railway vs a Hetzner Box
Railway's free tier died in 2023 and never came back. Here's the line-by-line recompute of what a real web+worker+Postgres hobby app costs on Railway's metered Hobby plan versus a flat €5.49/month Hetzner box.
Render's April 23, 2026 Repricing: Flat Fees Land, but Included Egress Drops From 100GB to 5GB
Render's April 2026 repricing swapped per-seat fees for flat ones but slashed included egress 95% on Hobby and Pro. Here's the line-by-line bill recompute at real traffic levels, plus what the same stack costs on a Hetzner box.
The Self-Hosted GPU Breakeven Point: Why ~50M Tokens/Day Is Where Owning H100s Beats Renting Inference APIs
A dedicated H100 breaks even against typical hosted LLM API pricing at roughly 50 million tokens a day of sustained use, but the real number depends entirely on which API tier you're comparing against and how well a platform can bin-pack tenant traffic to keep the GPU busy.
Vercel's Active CPU Billing Saves 93% on a Real AI Agent — Here's the Exact Math
Vercel claims Active CPU pricing cuts costs up to 95% across 45 billion weekly requests. A worked example on a realistic AI-agent function gets 93% — and shows the exact invocation volume where the discounted bill catches back up to a flat-rate box you already own.
Vercel's Spending Cap Doesn't Cap Your Spending: The Bandwidth Math Behind $23K Bills
Vercel's Spend Management feature can pause a runaway bill, but it's opt-in, checks usage every few minutes instead of continuously, and shuts down all of production instead of capping the overage — here's the real per-GB, per-CPU-hour math and what a fixed-cost server costs instead.
Coolify vs Dokploy vs Kamal in 2026: Idle CPU, Multi-Server, and Why a Cluster-API PaaS Is a Different Bet
Coolify, Dokploy, and Kamal charge wildly different resource rent to run your self-hosted PaaS. Here's the real idle CPU/RAM cost of each architecture, and why a Cluster-API-based platform is a different bet entirely, not a fourth entry in the list.
Heroku Fir: The Kubernetes-Native Successor Nobody Outside Enterprise Can Use
Heroku's Kubernetes-native runtime, Fir, has been enterprise-only since its April 2025 GA, with a four-figure monthly price floor before you deploy anything. Here's what that architecture actually costs to run yourself, on Hetzner, with Cluster API.
Fly.io Quietly Metered Three More Things in 2026 — Here's What It Actually Costs Your Indie SaaS
In a single quarter, Fly.io started billing for volume snapshots, app-scoped egress IPs, and inter-region private networking. None of the three is large alone. Here's the line-by-line before/after for a real two-region indie stack, and what the same topology costs self-hosted.
Heroku Enters Sustaining-Engineering Mode: The Buildpack Survives, Here's What It Costs to Leave
Heroku's February 2026 shift to bug-fixes-only maintenance doesn't kill the buildpack workflow it invented — here's what actually stops, and a real dollar-for-dollar comparison of running the same dyno formation on self-hosted hardware instead.