Real Numbers From Sites We Run: Hostinger, AWS, Cloudflare

9 of our own production sites measured3 PageSpeed Insights runs + 5 curl runs per siteNo Cloudways numbers (none of the measured sites runs there)Raw CSVs published below, not just averages

We measured response time, Largest Contentful Paint, and Cumulative Layout Shift on 9 sites we personally operate, using Google's PageSpeed Insights API (mobile, 3 runs each) and local curl TTFB from Pakistan (5 runs each), on September 28, 2026. Five sites run on a Hostinger VPS behind Cloudflare, one on Hostinger shared hosting, one on AWS (S3 + CloudFront), and two on Cloudflare Workers. We also use Cloudways, but none of these nine public sites runs on it, so this page has no Cloudways numbers. This page is a snapshot of our own infrastructure, not a lab benchmark controlling for stack, traffic, or geography. Read "What this does and doesn't prove" below before drawing conclusions from it.

Key takeaways

  • Fastest PSI performance score in our sample: the two Cloudflare Workers sites (animalrandomizer.com 0.92, formassets.com 0.81) and the Hostinger VPS Next.js sites behind Cloudflare (aitoolranked.com 0.86, chattoanyone.com 0.84). These run different stacks, so this isn't a controlled comparison.
  • Local curl TTFB from Pakistan was lowest for the Hostinger VPS Next.js sites (chattoanyone.com 0.11s, primetimeanime.com 0.12s) and highest for AWS's race-planner.com (1.01s avg, with one run spiking to 4.3s) and the Hostinger shared WordPress site (0.72s). Geography and CDN presence explain most of this gap, not host quality alone (see caveats).
  • A CDN sits in front of 6 of our 9 measured sites: Cloudflare proxies the 5 Hostinger VPS sites, and Amazon CloudFront fronts race-planner.com separately, so most of these numbers include CDN edge behavior, not pure origin-server performance. CloudFront and Cloudflare are different, unrelated CDNs; we're not conflating them.
  • The Hostinger shared site (timeandhalfcalc.com) is measured direct, with no CDN in front, so its numbers are closer to raw origin performance.
  • No Cloudways numbers here. We use Cloudways, but none of the public sites measured on this page runs there. Our Cloudways comparisons use its published specs and pricing, and we don't publish Cloudways benchmark figures we haven't measured.

Why we're publishing this

Most "which host is faster" content on the web is either a paid comparison, a single cherry-picked screenshot, or a synthetic benchmark run once on a trial account. We wanted to publish something different: what our own sites actually measure like, today, with the raw numbers attached, including the runs that don't flatter any particular host. We're not claiming this proves Host A beats Host B; see the caveats section for exactly what a 9-site, mixed-stack, single-day sample can and can't tell you.

The sites we measured

SiteHostCDN in frontStack
webhostingguide.net Hostinger (Cloud VPS) Cloudflare proxy Astro static
hostingdiscounts.org Hostinger (Cloud VPS) Cloudflare proxy Astro static
primetimeanime.com Hostinger (Cloud VPS) Cloudflare proxy Next.js (Docker)
aitoolranked.com Hostinger (Cloud VPS) Cloudflare proxy Next.js (PM2)
chattoanyone.com Hostinger (Cloud VPS) Cloudflare proxy Next.js
timeandhalfcalc.com Hostinger (shared) none (direct) WordPress / LiteSpeed
race-planner.com AWS (S3 + CloudFront) CloudFront Static S3
animalrandomizer.com Cloudflare Workers n/a (native edge) Vinext
formassets.com Cloudflare Workers n/a (native edge) Vinext

On Cloudways specifically

We use Cloudways, but none of the nine public sites measured on this page runs there, so there are no Cloudways numbers here. Our Cloudways recommendations (see Cloudways vs Hostinger and managed WordPress) rest on its published specs, pricing and architecture; we don't quote Cloudways benchmark figures we haven't measured. Earlier pages quoted specific Cloudways setups and numbers we couldn't back with published data; we removed them on 2026-09-28 (see the disclosure page). When a measurable public site of ours runs on Cloudways, its numbers go here.

Methodology

Dates: All measurements taken September 28, 2026, with the PageSpeed Insights runs inside about five minutes (08:40–08:46 UTC) plus a separate curl pass, to keep conditions comparable across sites.

Tool 1: Google PageSpeed Insights API (pagespeedonline/v5/runPagespeed), mobile strategy, performance category, 3 runs per site with a short pause between runs. This is a lab metric under Lighthouse's simulated mid-tier mobile device and throttled network. It is not the same as a real visitor's experience, and it is not Chrome UX Report (CrUX) field data. PSI returned real CrUX field data (28-day rolling Chrome telemetry) for 2 of our 9 sites (primetimeanime.com overall "Average" and chattoanyone.com overall "Fast") and no field data for the other 7, which don't have enough real-world Chrome traffic for Google to report a percentile. Where field data exists, we've noted it; every number in the tables below is still the lab measurement, not the field data, since only 2 sites have both.

Tool 2: local curl from this machine, located in Pakistan, 5 runs per site, recording time_starttransfer (a practical proxy for TTFB) plus DNS, connect, and TLS handshake timing. This is a second, independent vantage point, not a replacement for PSI's mobile-emulated numbers, and it reflects the specific network path from Pakistan to each site's CDN edge or origin, which varies by host region (Hostinger Boston MA is far from Pakistan; a Cloudflare-fronted site instead reflects the distance to the nearest Cloudflare edge, which is much closer).

Metrics recorded: server response time / TTFB, Largest Contentful Paint (LCP), Cumulative Layout Shift (CLS), First Contentful Paint (FCP), and the overall Lighthouse performance score (PSI); DNS/connect/TLS/TTFB/total time (curl).

Raw data: PSI raw runs (CSV) and curl raw runs (CSV).

PageSpeed Insights results (mobile, lab, average of 3 runs)

SiteHostTTFB (ms)LCP (ms)CLSFCP (ms)Perf score
webhostingguide.net Hostinger (Cloud VPS) 2 4,575 0 2,539 0.77
hostingdiscounts.org Hostinger (Cloud VPS) 1 4,590 0 2,653 0.74
primetimeanime.com Hostinger (Cloud VPS) 143 4,604 0 933 0.82
aitoolranked.com Hostinger (Cloud VPS) 3 3,826 0 1,686 0.86
chattoanyone.com Hostinger (Cloud VPS) 51 4,174 0 1,836 0.84
timeandhalfcalc.com Hostinger (shared) 134 3,908 0.0003 3,458 0.79
race-planner.com AWS (S3 + CloudFront) 1 4,868 0.1061 3,093 0.71
animalrandomizer.com Cloudflare Workers 7 3,303 0 1,521 0.92
formassets.com Cloudflare Workers 5 4,578 0 1,651 0.81

Local curl TTFB from Pakistan (average of 5 runs, seconds)

SiteAvg TTFB (s)MinMax
webhostingguide.net 0.283 0.280 0.289
hostingdiscounts.org 0.395 0.287 0.781
primetimeanime.com 0.115 0.090 0.162
aitoolranked.com 0.283 0.098 0.983
chattoanyone.com 0.110 0.094 0.145
timeandhalfcalc.com 0.715 0.350 0.904
race-planner.com 1.012 0.150 4.344
animalrandomizer.com 0.146 0.133 0.168
formassets.com 0.145 0.128 0.173

A month of uptime on the Hostinger VPS

Speed on one morning says little about whether a host stays up, so here is the month after it. The five Hostinger sites in the tables share one KVM 8 VPS. From September 22 to October 21, 2026, Cloudflare passed 141,309 requests to it. On October 17, 2026 the host machine shut the server down at 21:02 UTC (the server's log reads "hypervisor initiated shutdown"; we didn't trigger it), and it booted again at 21:40. Those 38 minutes produced 91 failed requests. The other 43 failures were spread over 18 days, never more than 10 in a day.

0 30 60 90 Oct 17: down 38 min Sep 22Oct 2Oct 12Oct 21
Requests Cloudflare could not get from our Hostinger KVM 8 VPS (8 vCPU, 32 GB RAM), per day, September 22, 2026 to October 21, 2026: 134 of 141,309. Source: our Cloudflare analytics and the server's own log.

That is 99.91% uptime for the 30 days. A 99.9% guarantee allows about 43 minutes of downtime in the same period, so a month like this one earns no credit. The lesson for us: this site's HTML wasn't cached at Cloudflare, so visitors saw an error page instead of a slightly stale copy.

What this does and doesn't prove

What it doesn't prove:

What it does show:

For a beginner site or small WordPress project, Hostinger is the host we run the most production sites on and the one we recommend most often on this site. See our full best web hosting comparison. If you've outgrown shared hosting, Cloudways is compared in depth on our Cloudways vs Hostinger page from its published specs and architecture, clearly labeled as such (no measured Cloudways numbers).