Region status
You cannot deploy here. Hostim runs exactly one region today, in Falkenstein, Germany. This page exists so North American teams can tell us whether a New Jersey region is worth building.
Everything Hostim does — long-lived Docker containers, managed PostgreSQL, MySQL and Redis, persistent volumes, custom domains with automatic HTTPS, a flat monthly bill that does not move with traffic — works today. The part that does not work for you, if your users are in North America, is that all of it is on the wrong side of the Atlantic. A round-trip from Toronto or New York to Falkenstein is roughly 95 to 100 ms, and that shows up on every request.
No hardware is ordered and no date is set. Hostim is a small, self-funded company, and a second region is a real monthly cost that has to be paid by people who actually want it. So we are asking first instead of building first.
The waitlist decides whether this happens. We wrote down a demand threshold before this page went live, and we review it eight weeks after launch. Above the threshold we build — small at first, one node, not a copy of the EU region. Below it we do not build, and we update this page to say so rather than leaving it up forever. The list also tells us how much capacity to buy, which managed databases to have ready, and whether Canadian data residency is a real requirement for enough people to justify a separate region later. Signups from customers who already pay us count for more than anonymous ones, which is why the form asks what you would move.
If US East never reaches enough demand, we will say so on this page rather than leaving it up indefinitely.
Typical figures for that metro, based on Secaucus as the expected site. Not measurements from our hardware — there is none there yet, and the exact facility is not fixed.
| City | Country | Expected RTT |
|---|---|---|
| New York | United States | ~2 ms |
| Washington DC | United States | ~6 ms |
| Boston | United States | ~8 ms |
| Chicago | United States | ~20 ms |
| Atlanta | United States | ~20 ms |
| Dallas | United States | ~35 ms |
| Denver | United States | ~45 ms |
| Seattle | United States | ~65 ms |
| San Francisco | United States | ~70 ms |
| Montreal | Canada | ~12 ms |
| Toronto | Canada | ~15 ms |
| Ottawa | Canada | ~16 ms |
| Halifax | Canada | ~25 ms |
| Winnipeg | Canada | ~40 ms |
| Calgary | Canada | ~55 ms |
| Vancouver | Canada | ~70 ms |
US hardware costs differently than German hardware, so US East will have its own prices. We are not publishing a number before we have one. We also bill in EUR today, and whether USD or CAD invoicing is needed is a genuine open question — tell us if it decides it for you.
New Jersey is close to Toronto and Montreal but it is not Canada. Private-sector use under PIPEDA is usually workable with the right contract; Quebec Law 25 adds an assessment; Nova Scotia's PIIDPA requires Canadian storage outright. BC repealed its statutory residency rule in 2021, but many BC public bodies still apply one by policy. We count that demand separately.
Hostim is HOSTIM.DEV UG, a German company. US East would be US-located servers run by a German operator. For most teams that is irrelevant; for a few it is a contract clause. Ask us before assuming it either helps or hurts you.
Not available in any region today, and not part of the US East plan. CPU inference covers embeddings, classical ML and smaller models. If GPU is what you actually need, saying so is still useful signal.
The same platform as the EU region. These pages describe each stack in a North American context.
No. It does not exist. Hostim runs one live region, in Falkenstein, Germany. This page describes a region we are considering building and collects interest from people who would use it.
There is no date, because there is no decision yet. We review this page eight weeks after it goes up. If enough North American teams sign up, we set a build date then and email everyone on the list. If not enough do, there is no date at all.
Yes — that is the whole point of it. We set a demand threshold before this page went live so the result could not be argued away afterwards. Below it, we do not build, and we say so here. Signups from existing paying customers weigh most.
Northern New Jersey — the same metro as the main East Coast peering points, around 2 ms from New York City. Secaucus is the site we expect to use, because that is where our likely hardware supplier has capacity. Nothing is contracted, so the exact facility could change, and any site in that metro gives figures close to the ones below. No hardware is installed anywhere yet, so every latency number here is typical for the location rather than a measurement of ours.
No. New Jersey is 12 to 15 ms from Montreal and Toronto, which is good enough for latency but does not satisfy any rule that requires data stored inside Canada. If you need Canadian storage, say so on the waitlist form — we count that separately, because it is a different build.
No. Projects stay in the region you chose. Nothing is migrated for you. If US East launches and you want to move a project, that is a migration you decide to run.
Probably not. Hardware in New Jersey costs differently than hardware in Falkenstein, so US East pricing will be set for that region and published before launch. The structure stays the same: flat monthly cost for reserved CPU, RAM and storage, not per request.
HOSTIM.DEV UG, a German company. A US region would mean US-located servers operated by a German company. That is an unusual combination, and if a customer contract of yours has a clause about foreign processors it is worth checking before you plan anything.
Email plus one line about what you would move. That is the entire input we are using to size this.
Platform figures from the published price list, docs and our own benchmark.
€2.50/month
Hostim entry app plan
Plan sa-1-1: 1 vCPU, 1 GB RAM. Flat price, billed hourly, no usage meter.
€0
Managed database free tier
PostgreSQL 256 MB, MySQL 256 MB, Redis 128 MB, volume 1 GB. No cap on how many free instances you create.
Included on every plan
Database high availability
PostgreSQL and MySQL run as a primary plus hot standby with automatic failover, shared plans included.
2,708 TPS
Managed PostgreSQL write throughput
pgbench, 4 clients, 300 s, plan drp-50 (2 vCPU / 4 GB). AWS RDS db.t4g.medium scored 1,080 TPS on the same test.
€0/GB
Traffic charges
No ingress fees and no per-GB egress line on app plans.
1 today (Falkenstein, Germany)
Regions
Bare metal, EU only, with more regions planned. No AWS, GCP or Azure underneath.
“Managed PostgreSQL runs as a replicated cluster with automatic failover on every plan, shared and dedicated alike.”
— Hostim.dev docs, managed PostgreSQL