LLM Hangar / EU hosting
EU-hosted LLM API providers compared (2026)
Choosing an EU region tells you where inference runs. A useful review also follows the request through gateways, logs, storage and support access. The providers below offer different ways to manage those responsibilities, from a hosted API to infrastructure in your own account.
LLM Hangar creates deployments in your cloud account. It deploys an open model onto a GPU instance inside your own AWS, Nebius, RunPod or Verda account, in an EU region if you choose, and gives you a private endpoint on that instance. Prompts and responses travel between your client and your instance. With the default node-local gateway, they do not pass through LLM Hangar. The optional hosted gateway does process request content; review its entry in the sub-processor list. The table below puts that next to the options you are probably already comparing.
The comparison
Facts are taken from each vendor's public pricing, region and security pages on the date above. "Not stated" means the vendor's pages did not say; it is not a judgement.
| Provider | Where it runs | Runs in your own cloud account? | Prompts pass through the vendor? | EU surcharge | Pricing model |
|---|---|---|---|---|---|
| LLM Hangar | Your AWS, Nebius, RunPod or Verda account; EU regions selectable, EU-only pinning available | Yes | Direct with the default gateway; the optional hosted gateway proxies content | None; EU pinning is a checkbox | Flat platform subscription; GPU hours billed by your provider |
| Scaleway Generative APIs | Scaleway infrastructure, France | No | Yes (vendor-hosted API) | Not applicable, EU-native | Per token; for example glm-5.2 at €1.80 input / €5.50 output per million tokens on its pricing page |
| OVHcloud AI Endpoints | OVHcloud infrastructure, France | No | Yes (vendor-hosted API); zero retention stated | Not applicable, EU-native | Per token |
| IONOS AI Model Hub | IONOS infrastructure, Germany | No | Yes (vendor-hosted API) | Not applicable, EU-native | Per token, $0.11 to $4.00 per million tokens depending on model |
| Mistral Studio | Mistral infrastructure, France; self-hosting of Mistral models under a commercial licence | Only via the licensed self-host option | Yes for the API; no for licensed self-hosting | Not applicable, EU-native | Per token for the API; licence for self-hosting |
| Requesty EU | Gateway in Frankfurt in front of proprietary model providers' EU endpoints | No | Yes (gateway), then the upstream model provider | Not stated | Per token; audit log on the enterprise tier |
| HostYourAI | Vendor-owned GPUs in the EU, dedicated instances | No | Yes (vendor-hosted) | Not applicable, EU-native | Prepaid credits, pay as you go |
| Apertus | Vendor-hosted, EU | No | Yes (vendor-hosted API) | Not applicable, EU-native | €20 per month base plus €0.11 to €0.95 per million tokens |
| Tessera | Vendor-hosted dedicated GPU, EU and Latin America | No | Yes (vendor-hosted) | Not stated | Flat $20 to $30 per month for a dedicated GPU |
| Northflank BYOC | Your own AWS, GCP, Azure or Kubernetes cluster | Yes | No, in BYOC mode | None; "no added cost for running in your VPC" | Pay as you go per vCPU, GB and GPU hour; setup is technical (clusters, node pools, images) |
| Modal | Modal-managed infrastructure; EU regions available | No | Yes (vendor-hosted) | Broad-region selection: 1.15x; specific-region selection: 1.75x, checked 6 September 2026. See data-residency limits as well as compute location | Usage-based compute; audit logs on the Enterprise plan |
| Fireworks AI | Fireworks-managed infrastructure | No, except large enterprise arrangements | Yes (vendor-hosted) | Region-restricted deployments billed at 1.5x per its pricing page | Per token and on-demand GPU hours |
Scroll to compare all columns. Provider names stay in view.
Choose based on the request path and operating model you need. A managed API can reduce infrastructure work; a deployment in your account gives you more direct control. Region-selection fees differ by service, and provider rates can vary between regions even when the platform adds no location surcharge.
Residency is not sovereignty
A useful checklist for EU hosting claims comes from Mate iT: five points that a region name alone does not answer. The table maps each one to what LLM Hangar does.
| Checklist point | What to ask | LLM Hangar |
|---|---|---|
| Processing region | Where does inference run, as opposed to where the company is registered? | On a GPU instance in the region you picked. The EU-only option pins every resource of the deployment to EU member-state regions and keeps it there. |
| Backups and copies | Where do snapshots, caches and prepared images live? | In your account. A prepared stage kept after a destroy, so the next boot is fast, is storage in your account, listed with its own cost and deletable at any time. |
| Sub-processors | Who else touches the content? | With the default or private gateway, request content stays on your infrastructure. The hosted gateway introduces a sub-processor for that content. The dated list is at /sub-processors. |
| Maintenance access | Can vendor staff reach the machine, and how is that bounded? | On AWS, access is a cross-account role assumed for an hour at a time and scoped to resources we tagged; delete the CloudFormation stack and it ends. Nebius uses a project-scoped service account, RunPod an API key you can revoke, Verda client credentials you can delete. Details in security. |
| Deletion timeline | When you delete, what proves it happened? | Teardown is verified against your provider until the resources are confirmed gone, and the sweep is written to the audit log, which you can export as JSON. |
Scroll to read all columns. Checklist labels stay in view.
What an EU region does not change
AWS and RunPod are US companies. Nebius is headquartered in the Netherlands and operates EU regions. Verda is a Finnish company whose three locations are all in Finland. An EU region of a US-headquartered provider is still run by that provider, and whether that places data outside the reach of US law is a live debate; the discussion around AWS's European Sovereign Cloud is a good summary of both sides. LLM Hangar does not claim to settle it.
The request path depends on gateway placement. The default and private gateways run in your account; the hosted gateway proxies requests on infrastructure we operate. The control plane that creates and destroys your instances runs in Germany and never sees prompt content. Your account data, deployment metadata and audit log are hosted in Germany. The inference itself happens in your own account, under your own provider agreement, in the region you chose.
The EU AI Act and self-hosting
Self-hosting alone does not determine your role or obligations under the AI Act. The model, your modifications and the application matter. An infrastructure audit log helps document deployment actions, but it does not establish compliance or replace any application records you need.
Check the AI Act together with its 2026 amendment for the provisions and dates that apply to your use.
How to deploy EU-only
- Connect your cloud account: AWS, Nebius, RunPod or Verda.
- Pick a model from the catalog and a shape that fits it.
- Tick EU-only. The wizard then offers EU regions only, and every resource, including storage, is created there.
- Set a budget cap, confirm the estimate, and copy the endpoint URL and key into your code.
The whole flow is a few clicks; there is no command line, Terraform or Kubernetes involved. The deploy-on-AWS guide walks through it with instance shapes and observed prices.
Questions we get asked
Is EU data residency the same as GDPR compliance?
No. Residency says where data is processed and stored. GDPR compliance also depends on who processes it, under what agreement, how long it is kept, who can reach it for maintenance, and how it is deleted. A vendor can host in the EU and still be a processor of your prompts.
Does hosting in an EU region remove CLOUD Act risk?
Not on its own. An EU region of a US-headquartered provider is still operated by that provider, and LLM Hangar does not claim otherwise. With the default gateway, prompts travel directly to your instance. Choosing the hosted gateway adds a managed proxy, so include that choice in your review.
Which EU regions can I pin a deployment to?
On AWS the EU-only option covers eu-central-1, eu-west-1, eu-west-3, eu-north-1, eu-south-1 and eu-south-2. Nebius, RunPod and Verda EU regions are offered where the provider has GPU capacity in them. The option pins every resource of the deployment, including storage, to EU member-state regions.
Do you sign a DPA?
Yes. A signed data processing agreement is available on request; the processing facts it records are summarised at /dpa.
Who are your sub-processors?
The hosted gateway uses Hetzner in Germany for request content. With the default or private gateway, content is handled in your own account. Platform services include Hetzner, Cloudflare, Scaleway and Paddle, whose roles are listed separately. The dated list is at /sub-processors.