A private LLM for your enterprise,hosted in Europe.Your data stays with you.
A private LLM, instantly available via API: performance on par with the top US models, at a fraction of the cost.
Operated in our own data centres in Berlin, Frankfurt, Vienna, Zurich and Bolzano. No CLOUD Act, no kill switch, no data leaving your control.
What a private LLM means for your enterprise
A private LLM is a language model running on your own hardware or in a dedicated European data centre instead of at a US provider. No business data leaves the controlled perimeter, no outside vendor can switch off your access, and the operator decides which model runs in which version.
Private does not necessarily mean your own server room
What matters is control, not where the metal sits. A model in a dedicated data centre under European law serves the same purpose as one in your basement, without you having to buy hardware and hire people to run it. Both count as a private LLM; the difference is effort and capital outlay.
Why an EU endpoint alone is not a private LLM
Many providers advertise a European access point. If the company behind it is subject to US law, the CLOUD Act still applies, and cutting off access remains a decision outside your influence. The sovereignty section below sets out the four levels and shows exactly where that line runs.
What enterprises actually run on a private LLM
Document analysis on confidential contracts, knowledge search across internal repositories, minutes and summaries from meetings, code assistance on your own source, triage of customer enquiries. The common denominator is always the same: data a company will not, or may not, hand to someone else’s cloud.
Performance in Action
A short look at sovereign operation: from prompt to answer — entirely on our infrastructure across five European sites.
Open frontier-class models — available now, transparent pricing
All models are already running and usable via API immediately — billed by usage, per million tokens, no base fee, no minimum spend; GLM 5.3 and the new DeepSeek V4 Pro follow on 1 September. On request we also run the same models dedicated or on-premise at a fixed price.
| Model | Class | Context | Locations | Input€ / 1M tokens | Output€ / 1M tokens |
|---|---|---|---|---|---|
| GLM 5.3from 1 Sep | All-round | 1M | from 1 Sep | tba | tba |
| DeepSeek V4 Pro 0813from 1 Sep | All-round | 1M | from 1 Sep | tba | tba |
| Kimi K3★ Best seller | All-round | 1M | Berlin · Zurich | 3.00 € | 15.00 € |
| DeepSeek V4 Pro | All-round | 1M | All 5 locations | 1.75 € | 3.50 € |
| Qwen3.5 397B | All-round | 256K | All 5 locations | 0.60 € | 3.60 € |
| Kimi K2.6 | All-round | 256K | Berlin · Zurich | 0.95 € | 4.00 € |
| GLM 5.2 | All-round | 1M | All 5 locations | 1.40 € | 4.40 € |
| GLM 5.1 | All-round | 200K | Frankfurt · Vienna | 1.40 € | 4.40 € |
| MiniMax M3 | All-round | 1M | Vienna · Zurich · Bolzano | 0.30 € | 1.20 € |
| Mistral Large | All-round | 256K | Berlin · Frankfurt · Zurich | 0.50 € | 1.50 € |
| DeepSeek V4 Flash | Efficiency | 1M | All 5 locations | 0.29 € | 0.35 € |
| gpt-oss-120b | Efficiency | 128K | Berlin · Vienna | 0.15 € | 0.60 € |
| Qwen3.6 27B | Efficiency | 256K | All 5 locations | 0.40 € | 2.70 € |
| Qwen3 Coder 480B | Code | 256K | All 5 locations | 0.40 € | 1.60 € |
| Kimi K2.7 Code | Code | 256K | Berlin · Zurich · Bolzano | 1.44 € | 5.18 € |
| Devstral Small | Code | 128K | Vienna · Bolzano | 0.10 € | 0.30 € |
Prices net, as of August 2026; billed by actual usage. More models on request — the catalogue grows continuously.
Dedicated or on-premise operation: fixed price based on sizing instead of token billing — talk to us.
Many models. One conductor.
Fugi is our orchestration layer on top of the model pool: a small coordinator model receives every request and decides for itself what to do — answer directly, or assemble a team of specialists, hand out sub-tasks, cross-check results and condense them into one answer.
Learned, not hard-wired
Classic routers follow hand-maintained if-then rules. Fugi’s coordinator is itself a trained model: its strategies — who takes what, when to verify, when one answer suffices — emerge from experience and improve with every training run.
The team beats the star
Complex tasks are decomposed and assigned to the strongest specialists — with a verification step before the answer. A federation of open models reaches frontier-level results without needing one giant model.
The pool is yours
New models dock on without retraining, deprecated ones drop out, and your rules apply at system level — such as “only models at DACH locations”. The whole federation runs on our infrastructure across five European sites.
Fugi orchestrates the model pool across all five sites — access comes via the waitlist.
Pick your model — and see the difference
Choose a model, set your monthly volume: the chart plots your monthly output cost against Claude Fable 5 at market API pricing — and how the savings grow with every token.
Kimi K3 is, per output token, 3.3× cheaper
Comparison basis: Claude Fable 5 at the verified market API price ($10 input / $50 output per 1M tokens, July 2026 — the most expensive Anthropic model ever listed). Calculated over output tokens, because that is where the cost lives: Fable 5 always thinks, and thinking tokens are billed as output. User equivalence: around 0.3M output tokens per employee and month — a typical mix of assistant requests, knowledge-base queries (RAG) and agentic software development. Prices net.
On par. Proven.
Open frontier-class models are no longer a compromise. The head-to-head: GLM-5.2 (open, in our catalogue) versus Claude Opus 4.8 (US frontier) — measured, not claimed. And the gap keeps closing: Kimi K3, ranked #3 worldwide, is now openly available and running in our catalogue.
| GLM-5.2 · open | Opus 4.8 · US | |
|---|---|---|
| Terminal-Bench 2.1agentic | 82.7 | 78.9 |
| AIME 2026mathematics | 99.2 | 95.7 |
| Composite scoreoverall | 91 | 93 |
| Cost / 1M outputAPI price | $4.40 | $25.00 |
| Licence & access | MIT · open | proprietary · API |
| Operable in the EU | ✓ | — |
5.7× cheaper per output token. On agentic terminal tasks and mathematics it already beats Opus 4.8 today — both with 1M-token context. The narrow composite-score gap costs one fifth of the price.
benchlm.ai · llm-stats.com · as of June 2026
GLM 5.2 is in the price table above — available via API right away →
Swap the base URL. Done.
Our endpoint is OpenAI-compatible: existing code keeps running unchanged — you only change the base URL and the model. No SDK switch, no migration project.
from openai import OpenAI
client = OpenAI(
base_url="https://api.advisori.de/v1",
api_key="IHR_ADVISORI_KEY",
)
antwort = client.chat.completions.create(
model="glm-5.2",
messages=[{"role": "user", "content": "Hallo!"}],
)
print(antwort.choices[0].message.content)You receive your API key with your capacity release from the waitlist.
Your models live in Berlin, Frankfurt, Vienna, Zurich and Bolzano — Hamburg is next.
Our inference servers are located in Berlin, Frankfurt, Vienna, Zurich and Bolzano — running on NVIDIA B200, the current GPU generation. Hamburg is in build-out. High performance, high quality, short distances. And entirely in Europe: operations, data and jurisdiction stay where you are.
Built by security people — not bolted on
ADVISORI is a security company. Model operations follow the same standards we apply when advising banks and insurers.
Zero data retention
Prompts and responses are not stored — they are processed and discarded. Your data feeds no training and reaches no third party.
Encrypted, end to end
TLS 1.3 in transit, AES-256 for everything at rest. Hardened and monitored by the ADVISORI FTC security team.
DPA included
A data processing agreement under Art. 28 GDPR is part of the contract — with processing exclusively at our European sites (DE, AT, CH, IT). EU AI Act evidence included.
Control for your IT
Dedicated API keys per team, budget limits and an audit trail across all requests — your IT keeps track of who uses what.
Multimodal guardrails — your policies, enforced at the endpoint
PII protection, multimodal
Personal data is detected and masked in text, images and documents before it reaches the model — and, on request, in the responses as well.
Prompt-injection defence
Attacks via manipulated inputs, documents or web content are detected and blocked at the endpoint — before they can steer the model.
Company-own policies
Your guidelines as enforceable guardrails: topic blocklists, compliance requirements, department-specific approvals — centrally maintained, effective per team and API key.
Every decision in the audit log
What was checked, masked or blocked is documented traceably — per request, per rule, audit-proof for your compliance.
The guardrails apply before and after every model call — regardless of which model Fugi selects. Also available as a standalone service in front of any model: Fugi Guardrails →
The same certifications ADVISORI holds when advising regulated companies — no “in preparation”, no “expected”.
What sovereign operation looks like
When Washington pulls the plug
What was long a hypothetical risk has been documented reality since June 2026 — shutdown, access lists, overnight price changes.
The off switch has been used
No longer hypothetical: in June 2026, Claude Fable 5 was switched off worldwide for 19 days by US government directive — for all customers. No contract, no SLA protected against it.
Access is granted politically
GPT-5.6 launched exclusively for around 20 partners individually approved by Washington. Who gets to use frontier AI is increasingly decided by the US government — European companies are not at the table.
Price changes overnight
The same model that was just included in the subscription costs $10 / $50 per million tokens from July 8 — no grandfathering. Local models flip the equation: fixed infrastructure, plannable costs. The price calculator above shows the difference.
CLOUD Act & structural dependency
US authorities can access data held by US providers — regardless of which data centre it sits in. And according to the first UN AI report, 75% of the world’s AI computing power is located in the US.
GDPR & EU AI Act
Documentation duties, data minimisation, transparency. Easiest to satisfy when the model runs where your data already lives: with you.
- 12 Jun 2026US government orders the shutdown of Claude Fable 5 & Mythos 5 — worldwide, for all users. Source →
- 26 Jun 2026OpenAI launches GPT-5.6 for only ~20 government-vetted partners — access approved customer by customer. Source →
- 01 Jul 2026First UN AI report: 75% of global AI computing power is located in the US, 15% in China. Source →
- 08 Jul 2026Fable 5 back online after 19 days — throttled, and from July 8 only via usage credits ($10 / $50 per million tokens). Source →
- 16 Jul 2026The open world catches up: Moonshot unveils Kimi K3 — ranked #3 worldwide, ahead of Opus 4.8. The weights were released on 27 Jul. Source →
Digital sovereignty: what the term actually demands
Digital sovereignty is usually debated as a stance and rarely written down as a checklist. For running a private LLM, digital sovereignty can be pinned down precisely: four questions, each with a verifiable answer. Who can switch off your access? Whose law governs your data? Who decides on model changes and pricing? And could you take over operations yourself if you had to?
EU data residency
The data physically sits in Europe, but the provider remains subject to US law. That satisfies storage-location requirements and nothing else, and has nothing to do with digital sovereignty yet: the CLOUD Act still applies, and shutdown remains someone else’s decision. Most offerings advertising European data centres stop here.
Location settled, control notEuropean operator
Operations and contract sit with a European company, while the model still comes from a US provider on that provider’s terms. A clear step up for digital sovereignty; technically the dependency remains. If the model is switched off or repriced, it hits you just the same.
Law settled, model notOpen weights in a European data centre
The model is open source or available with open weights and runs at a European operator. Now nobody can switch it off: you hold the weights, and the version stays frozen until you change it. This is where a private LLM genuinely begins, where most enterprises should land, and what ADVISORI delivers by default.
Shutdown risk eliminatedFull self-operation
Hardware, model and operations entirely in house. Maximum digital sovereignty, and the only route for classified environments or strict network separation. The price is capital expenditure on hardware, your own specialists, and responsibility for availability and updates.
Fully sovereign, at a costThe decisive line runs between levels two and three: only with open weights does dependency on someone else’s release decision end. Everything below that is data protection, not digital sovereignty. Why a purely European access point does not cross that line is covered in the next section.
An “EU endpoint” is not sovereignty
Many providers advertise “EU data residency” — meaning a gateway in Europe that receives your requests and forwards them to US model providers. What matters is not where the request arrives, but where the model computes.
| US cloud APIOpenAI, Anthropic & co. directly | AI gateway“EU data residency” / EU endpoint | Local modelsADVISORI | |
|---|---|---|---|
| Where does the model compute? | In the US cloud | Still at the US model provider | On your premises or in our data centres (DE/AT/CH/IT) |
| Who sees your prompts? | The model provider | Gateway and model provider | Only you |
| CLOUD Act access possible? | Yes | Yes — at the model operator | No |
| Cost model | API price per token | API price + markup | Fixed infrastructure, unlimited usage |
| Can third parties switch it off? | Yes | Yes | No — you run it |
Private LLM and the GDPR: what self-operation changes
Running a private LLM in your own legal jurisdiction does not turn the GDPR into a formality, but it moves the question from a hard-to-evidence level to an easily evidenced one. Three things change concretely.
The transfer disappears instead of being justified
Calling a US model means justifying a third-country transfer under the GDPR and safeguarding it continuously. If the model runs in a European data centre, the transfer simply does not happen. That is the cleaner route: processing that does not take place needs no justification.
Article 32 asks for effectiveness, not intent
Article 32 GDPR requires technical and organisational measures reflecting the state of the art that ensure confidentiality, integrity, availability and resilience, plus a process for regularly testing their effectiveness. Under self-operation the logs, access records and configuration are yours, and so is the evidence. With an external service you hold the provider’s certificate and little else.
The allocation of roles becomes unambiguous
With us, ADVISORI remains a processor under Article 28 GDPR, with a data processing agreement, a named data centre and no training on your data. Under full self-operation the processor disappears entirely. Either way the chain is short and documented in writing, rather than running through several sub-processors across shifting jurisdictions.
How to set up and document such an operation in detail, from role allocation to deletion policy, is covered in our guide on GDPR-compliant AI. It does not replace an assessment of your specific use case, which is exactly what we have advised on for years.
Open frontier-class models — three operating paths, one accountable partner
We select the right open model for your use cases, build the operation and take responsibility for it — including hardening, updates and monitoring.
On-premise with you
Operation on your own hardware, in your own building. Maximum control — the right choice for classified material, R&D and strictly regulated data.
European data centre
Dedicated operation on NVIDIA B200 infrastructure at one of our five European sites — no hardware investment of your own, under the law of the respective location (DE/AT/CH/IT), with a clear SLA.
Hybrid with failover
Local models as the default, defined fallback paths for peak load — orchestrated via Synthara AI Studio, with rules you define.
Your model speaks your industry
Beyond the catalogue, we fine-tune open frontier-class models on your industry and your documents: domain language, forms, processes, regulation. Training runs on our B200 clusters across five European sites — the fine-tuned model belongs exclusively to you and runs as its own endpoint.
Banks & financial services
Credit files, MaRisk, regulator language — a model that knows your rulebook.
→ Join the waitlistInsurance
Policies, claim files, terms and conditions — trained on your vocabulary.
→ Join the waitlistHealthcare
Doctor’s letters, coding, study protocols — with full data sovereignty.
→ Join the waitlistLegal & compliance
Contracts, briefs, deadlines — precise in legal language.
→ Join the waitlistIndustry & manufacturing
Maintenance reports, standards, bills of materials — your operational knowledge in the model.
→ Join the waitlistPublic sector
Notices, procurement documents, administrative language — sovereign and on the record.
→ Join the waitlistClicking your industry adds it straight to your waitlist request — we follow up with a concrete proposal.
The API is complete. Synthara takes it to your business teams.
Your endpoint works on its own — your developers integrate directly via the API, no extra software needed. If you also want to bring AI to teams without developers, you can optionally put Synthara AI Studio on top of the same sovereign models: AI assistant, no-code studio, workflows and reporting — with automatic failover between your models.
Discover Synthara AI Studio →Three steps to your sovereign endpoint
Sign up
Join the waitlist — a business email is all it takes. We release capacity in waves and reach out in the order of sign-ups.
today · 2 minutesReceive access & DPA
You get your API key, your site assignment and the data processing agreement — everything your IT and privacy teams need for approval.
after 3–5 daysSwap the base URL, go
The endpoint is OpenAI-compatible: one line of configuration and your applications, Claude Code or OpenCode run on sovereignly hosted models. You pay only for what you use — industry models and an on-premise path are always available as a next step.
day 1What decision-makers ask us most often
What is local AI?
Are open models really good enough for enterprise use?
What sets you apart from providers advertising “EU data residency”?
Do we need our own GPU hardware?
What does it cost compared to our current API usage?
How quickly are we productive?
Who operates and maintains the models long term?
Is a data processing agreement (DPA) available?
Can we enforce our own policies (guardrails)?
What availability do you commit to?
Secure the next available slot
Current capacity is allocated — we are expanding continuously. Join the waitlist: we reach out in the order of sign-ups as soon as your access is ready.
Join the waitlistQuestions first? Write to us: info@advisori.de · ADVISORI FTC GmbH