Real Numbers From Sites We Run: Hostinger, AWS, Cloudflare
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
| Site | Host | CDN in front | Stack |
|---|---|---|---|
| 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)
| Site | Host | TTFB (ms) | LCP (ms) | CLS | FCP (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)
| Site | Avg TTFB (s) | Min | Max |
|---|---|---|---|
| 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.
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:
- It isn't a controlled host benchmark. The sites are different stacks: Astro static, Next.js in Docker, Next.js under PM2, WordPress on LiteSpeed, static S3, and Vinext on Workers. A stack difference can swing these numbers more than a host difference.
- Most of the Hostinger numbers include Cloudflare, not pure origin performance. Only one Hostinger site (timeandhalfcalc.com, shared hosting) was measured with no CDN in front.
- The AWS example is S3 + CloudFront static hosting, not an EC2 compute instance. That is a different product category from a Hostinger VPS, included because it's the only AWS-hosted site we run.
- One data point for AWS means we can't say whether the numbers are typical of the provider or specific to that one site's configuration and region.
- Single-day, single geographic curl vantage point (Pakistan). A visitor in the US, Europe, or elsewhere in Asia would see different relative numbers, especially for the direct (non-CDN) Hostinger shared origin.
- CrUX field data exists for only 2 of the 9 sites (primetimeanime.com, chattoanyone.com); the rest don't have enough real-world Chrome traffic for Google to report it, so most of this page is lab measurement, not real-visitor telemetry.
- It says nothing about Cloudways, because none of the measured sites runs there. Don't read this page as an argument against Cloudways; it's a gap in this dataset, not a verdict.
What it does show:
- These are real, current production sites, measured on a stated date, with the raw per-run data published rather than a single flattering screenshot.
- Hostinger and AWS are both hosts we actually operate infrastructure on today, and that's the basis for anything on this site described as first-hand hosting experience with them.
- Where Cloudflare fronts a Hostinger origin, the measured experience is a combination of the two. That is a common real-world setup for a budget-to-mid VPS host, not a flaw in the test.
- A visible gap in this dataset (no Cloudways numbers) is disclosed rather than papered over with a comparison we can't back.
If you're choosing a host from this
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).