Notes from the Clodei team
Deep dives on EU GPU infrastructure, pricing, performance and the platform we ship.
- April 25, 2026 · 5 min read
Zero egress fees explained: what hyperscaler bandwidth really costs
Egress is the line item nobody quotes you up front, and the one most likely to make your invoice 2x what you expected. A guide to where the bytes get charged and how to avoid the worst of it.
- April 22, 2026 · 4 min read
From signup to running model in 60 seconds: a Clodei walkthrough
What happens between clicking 'Launch a GPU' and your first inference. A literal click-by-click of Clodei, with timings.
- April 18, 2026 · 4 min read
A100 vs H100 vs H200 vs L40: which GPU for your workload
A practical comparison of the four datacenter GPUs available on Clodei. VRAM, compute, memory bandwidth, and the actual workloads each one handles best.
- April 15, 2026 · 4 min read
Per-minute vs reserved GPU pricing: when each model wins
Reserved instances are cheap when utilisation is high. Per-minute is cheap when utilisation is anything else. The break-even point is messier than vendor calculators suggest.
- April 12, 2026 · 4 min read
Why EU-based GPUs matter: GDPR, latency and data sovereignty
Where your GPU is physically plugged in changes who can subpoena the data, how fast users see results, and what you pay to move bytes around. A practical look for EU teams.