Cloud: a dedicated environment, your keys
A single-tenant deployment in your own cloud account, in a region you choose, with open-weight or private model endpoints behind your controls. We build it and hand it over; we can operate it on a schedule if you would rather not.
When it fits
- Regulated data that must stay in a named region, without buying hardware
- Variable or growing volume
- No infrastructure team, or one that would rather not own GPUs
- A first deployment you control, which may move on-premise later
The reference architecture
The named parts. Sizes and figures come from the assessment, not from this page.
Compute
Containers on your cloud account's compute, single tenant, under your billing.
Models
Open-weight models on rented GPUs, or a provider's private endpoint inside your cloud, chosen by measurement.
Vector store and database
Qdrant or Postgres with pgvector, in the same region, encrypted at rest.
Application services
A FastAPI service for ingestion, retrieval and the workflow; a small web front end where needed.
Delivery
Slack, email or a document store you own.
Who holds what
Keys
Yours. Encryption keys and provider credentials live in your account's secret store.
Data
Stays in the region you choose. Nothing is copied to a shared service.
Uptime and updates
Your cloud provider's terms for the infrastructure; we schedule model and dependency updates with you, or under an optional run agreement.
Backups
Automated snapshots in region, with a restore tested at handover.
What you give up
- A network hop to your cloud region; latency is good, not local.
- Monthly infrastructure spend continues for as long as it runs.
- Provider endpoints, where used, carry that provider's terms.
When another option is the better answer
On-premise
You run it
Choose on-premise when data may not leave your network at all, when volume is high and steady enough that owned hardware pays off, or when an air-gapped environment is a requirement.
On-premiseManaged agents
We run it
Choose a managed agent when you want the output without owning an environment at all. We host it, monitor it and send the report; it can move into your account later.
Managed agentsWhat this is not
The TurnkeyGTM platform runs as a cloud service we operate. We do not offer an on-premise or private-hosted edition of the platform today. On-premise and cloud deployments are designed and built on open-weight models and self-hostable components — containerised services, a vector store such as Qdrant or Postgres, and a model server such as Ollama or vLLM — and handed over with documentation. Managed agents run on infrastructure we operate, under a data-handling rule set agreed before the first run. Capacity, latency and cost figures are given per engagement, never on this page.
Questions we get asked
The capabilities behind it
Custom hosted and on-premise AI
AI deployments designed for where your data has to live — a dedicated hosted environment or your own hardware — on open-weight models and self-hostable components.
See the deliverablesModel selection and cost optimization
Which model, at which size, for which step — chosen by measured quality and cost on your own tasks rather than by the leaderboard.
See the deliverablesPII protection and data handling
Redaction, minimisation and handling rules for personal data in transcripts, tickets and documents before any model sees them, with residency where your obligations require it.
See the deliverablesTell us where your data has to live.
The assessment is short and fixed price. It ends with a written recommendation and a reference architecture.