Private LLM hosting in your own cloud account

Pick an LLM and deploy it
to your GPU provider

Set running hours,
budget caps and timers

Delete a deployment
and check its cleanup

Choose where
your model runs EU

No command line or Linux experience needed. No Terraform to write, machine images to build or inference engines to configure.

Private LLM hourly costs

Use these prices to estimate what a model costs to host per month, and what your own machine can run.

Loading…

Loading current prices…

Manage resources in your own account

The instance, storage and network are created in your account. You can inspect and manage them in your provider console, apply your own policies and retain them if you cancel your subscription.

No lock-in: resources stay after you cancel

Your provider rates, your reserved capacity, your credits

Access granted by a role you can revoke in one command

WHEN

WHAT

WHERE

08:03:08

Plan recorded: 1 instance, 1 security group

us-east-1

08:04:20

GPU instance created, billing starts

g6e.xlarge

08:19:12

Endpoint live and answering

203.0.113.10

21:44:03

Destroyed and swept, zero resources remaining

us-east-1

See every step of your deployment

You see what ran, where, when and how. Every action we take in your account is written to a timestamped log, including the plan of what will be created before it exists.

The log exports as JSON, is kept after teardown, and sits alongside spend against cap and request counts read from your own gateway.

Choose how requests reach your model

A dedicated model deployment

Model weights are downloaded to the instance in your cloud account. Your deployment has its own serving process and endpoint.

Direct requests by default

With the default gateway, requests go directly to your instance. You can also choose a private gateway in your account or a hosted gateway that proxies requests through our infrastructure.

EU-only infrastructure

EU

One checkbox pins every resource to EU member-state regions and keeps it there.

eu-central-1 eu-west-1 eu-west-3 eu-north-1 eu-south-1 eu-south-2

How this compares with EU-hosted LLM APIs →

Access you control

Create named endpoint keys with their own limits. Keys are shown once; changes take effect within seconds on an edge gateway or at the next start on the default gateway. You control the cloud credentials that let us manage your deployment.

Security: access, keys and data →

AVAILABLE CONTROLS

EU region selection

Direct request routing by default

Encryption in transit

Full audit trail

Verified deletion

Pricing

One flat subscription for the platform. GPU hours are billed to you by your cloud provider.

Lab

Evals, prototypes and side projects.

$39 /month*

Hardware1 GPU

Deployments at once2

Modelswhole catalog

ProvidersAWS, Nebius, RunPod and Verda

History after teardown30 days

Supportemail

Start 7-day free trial

7-day free trial, no credit card required.

* The subscription covers the deployment platform. GPU and hosting charges are billed by your infrastructure provider, like AWS or RunPod, directly to you.

Included on every plan, including the trial

Hard budget caps

Required on every deployment. You can raise the cap; you cannot disable it.

Weekly wake/sleep schedules

Choose running windows while deploying, with time zones, overnight runs, pre-warm and a savings preview. How scheduling works.

Self-destruct timers

Set when a deployment should be deleted, even if you are away.

Verified teardown

A sweep after every destroy, with a record of what was removed.

Full audit trail

Every action we took in your account, timestamped, including the pre-flight plan.

EU-only residencyEU

One checkbox pins a deployment to EU-member-state regions.

Delete

Delete any deployment, or your whole organization, at any time on any plan.

Frequently asked questions

How does the 7-day free trial work?

The trial runs for 7 days and no credit card is required to start it. You get the Lab feature set with one deployment at a time. Subscribe whenever you are ready; if the trial ends first, new deployments are blocked until you do. Nothing is destroyed: anything still running keeps running and keeps billing to your cloud account.

What does a stopped deployment cost?

GPU billing ends once the provider confirms the compute is off. Retained storage and an optional private gateway can still cost money. The platform subscription stays the same. Your configuration and keys are kept for the next start. See stop and start.

Do you resell GPU capacity?

No. Everything runs in your account at your provider's rates. We never see your infrastructure invoice.

What access do you need to my cloud?

On AWS, a role we can borrow for an hour at a time, scoped to resources we tagged ourselves. Delete the CloudFormation stack to remove the role; any session already issued can remain valid until it expires.

What if a deploy fails halfway?

We explain the cause in plain language, remove whatever was created, and show the sweep result. The most common first failure is an AWS GPU quota of zero, which comes with a direct link to the form that fixes it.