Zinn® Vector Start
$12.99/month
or $129.90 a year
- NVMe storage
- 10 GB
- Database size
- 1 GB per site
Vector databases
A managed vector database that is just PostgreSQL
Store embeddings and search them by meaning, on pgvector we run and back up for you. No new datastore to learn, no cluster to size — create an index, write your vectors, and query it with the API key you already have.
Get startedPlans from $12.99 a month
- 700,000+websites hosted on our platforms worldwide
- 58languages, dashboard and support alike — five of them right to left
- 27applications you can install in one click, kept up to date for you
- 100%renewable electricity in our Finland and Germany data centres — verifiable, not offset
The database you already trust, with one extra column type
A vector database is usually a second system to run alongside the first: another cluster, another backup story, another thing to be woken up for. This is pgvector inside PostgreSQL — the same engine, the same durability, the same nightly base backup and continuous write-ahead log archiving that everything else here gets. Your index is an ordinary table with an HNSW index on it, so it is fast for approximate nearest-neighbour search and boring in every other respect, which is the property you want at three in the morning.
Your model's width, not a width we picked
Most managed vector services make you choose from a short list of dimensions. Yours does not have to be a round number: anything from 1 to 3072 is accepted and held exactly, because a narrower vector is padded into the next physical width with zeros — which changes cosine, Euclidean and inner-product distance by precisely nothing. A 1408-dimension model ranks identically to one sized natively for it, and reads give you back the 1408 values you stored, never the padding.
Included on every vector plan
- Any embedding width up to 3072, and cosine, Euclidean or inner-product distance
- Metadata stored with every vector, and filtered on at query time
- Nightly backups with 30-day retention and point-in-time recovery
- Row-level security, so one organisation's vectors are unreachable from another's
Plans and pricing
Three tiers, priced on the two things that actually cost us anything: how much you store and how much you search.
Zinn® Vector Growth
$19.99/month
or $199.90 a year
- NVMe storage
- 50 GB
- Database size
- 1 GB per site
Zinn® Vector Scale
$55.99/month
or $559.90 a year
- NVMe storage
- 250 GB
- Database size
- 1 GB per site
Support is included, and somebody is always there
Every plan comes with it. There is no support tier to buy, no per-incident charge and no ticket allowance — and the desk is open 24 hours a day.
Free on every plan
Support is part of hosting, not an upsell. It is the same support on the smallest plan as on the largest, and nothing about it is counted or capped per incident.
Open 24 hours a day
Whatever hour you are working and whatever time zone you are in, the desk is staffed. You are not writing into an inbox that opens in the morning.
Every one of our 58 languages
Write your ticket in the language you actually think in — we translate it for our team and answer you in yours, with the original always one click away. We sell in all 58.
A person, not a bot
Our assistant answers instantly from the knowledge base, but it never closes a ticket for you. A ticket is picked up and answered by somebody who can act on it.
A click-fraud shield, free with every plan
Advertising your site? Every Zinn® hosting plan includes the Zinn® Ads click shield, running on the server with nothing to install: it spots bots and repeat clickers on your ads and keeps them away. Pair it with Zinn® Ads, multi-channel PPC automation that audits your ad accounts every day and runs fully automatic or asks you first.
- Included free with every Zinn® hosting plan, nothing to install
- Zinn® Ads has a free plan, no card needed
Renewable power, where we can show it
Our servers in Finland and Germany run on renewable electricity — sourced that way, not offset after the fact. For our United States and Singapore locations we have not verified the supply, so we do not claim it.
- Renewable electricity in our Finland and Germany data centres
- Data centres running at a PUE of 1.1 to 1.2
- Sites on our shared platform pass the Green Web Foundation's checks — a third party you can verify for yourself
Where to go next
The pages people usually read after this one — the platform underneath, the rest of the range, and the help you get once you are here.
Questions people ask before they buy
Which embedding models does this work with?
Any of them. You send us the numbers your model produced, so OpenAI, Cohere, Voyage, a Sentence-Transformers model on your own machine and anything else are all the same to us. You tell us the width when you create the index — 384, 768, 1024, 1536 and 3072 are all common, and so is something in between.
Can I change an index's width or distance function later?
No, and we would rather say so plainly than let you discover it. Both decide where your vectors are physically stored and how they are ranked, so changing either would silently invalidate everything already in the index. If you switch to a different embedding model, create a second index and write into it — the same thing every vector database asks of you, and for the same reason.
Is there anything different about very wide vectors?
Yes, and it is worth knowing. Above 2,000 dimensions the values are stored at half precision, because PostgreSQL's HNSW index does not accept a full-precision column wider than that. For 3072-dimension models this is the approach pgvector itself recommends and the effect on ranking is negligible — but it is a real trade-off and you should hear it from us rather than infer it.
Do I get a database connection string?
Not today. You reach your index over HTTPS with your Zinn® API key, scoped so a key that can search cannot do anything else in your account. That is what lets us meter queries honestly and keep one tenant's rows unreachable from another's. If a direct connection is what you need, tell us — we would rather build it because someone asked than guess.
How is it metered, and can I check the numbers myself?
On two meters: how much you store and how many searches you run in a calendar month. Both are on your dashboard as they happen. Storage is a published formula rather than a physical table size — row overhead, plus the stored width, plus the length of your own ids and metadata — precisely so you can reproduce the figure we are billing you for instead of taking our word for it.
Help with this
Step-by-step guides from our knowledge base, written for exactly this.
Choosing where your site is hosted
Which data centres you can pick for each kind of hosting, where you pick it, and why the list can change.
Read the guide →The vector index
What gets indexed, what it powers, and when to rebuild it.
Read the guide →Working on a site somebody shared with you
A site's owner can hand one site to a developer by email — not their account, not their billing, not their other sites. Both halves: sharing and revoking it from the dashboard, and pulling the site down with zinnector login, clone and dev, database included — plus what each role can and cannot do.
Read the guide →