Sluis is a drop-in OpenAI endpoint. Change one line, and it strips every name and secret before the model sees them, puts them back in the response, and seals every call in a ledger you can't fake. GDPR compliant, EU-sovereign by default.
No seat fees and no minimum spend. Nothing leaves your residency policy.
Sluis Workspace is where your team works. Sluis Gateway governs the apps and agents you already run. Both sides share one policy and one audit trail.
The European alternative to Copilot: chat, agents, skills and company knowledge in one place.
One endpoint, compatible with the OpenAI and Anthropic APIs, in front of everything you already run.
Sluis Workspace, shown with sample data
A lock holds back the sea while it moves the boat. Sluis works the same way: nothing skips a gate, and nothing leaves without a record.
60+ detectors scan every prompt before it leaves. PII, PHI and secrets are reversibly pseudonymised before a single token moves on.
Your policy picks the provider. An EU-sovereign model first, an EU-region cloud as backup, a hard stop if nothing fits.
Every request gets a hash-chained entry: verifiable offline, exportable, erasable per data subject (GDPR Art. 17). Break one link and the whole chain shows it.
Sluis swaps every name, ID and secret for a stable token before the prompt ever leaves your network. Suddenly any model is safe to call, direct US and Chinese providers included, on opt-in. The real values come back in the response, and the token map is never stored.
Refund customer Jan de Vries, IBAN NL91ABNA0417164300.Refund customer [PERSON_1], IBAN [IBAN_1].Map your data classes to the regions and providers you trust. Sluis checks it on every request. No exceptions, no data quietly slipping out.
Every entry is hashed with the one before it. Change a single field anywhere in the history and every link after it breaks. Export the chain and anyone can re-check it offline.
Sluis shows you what other gateways hide: who owns each model and where it runs. EU-owned first. Frontier models like Claude and Gemini run today in EU regions. Direct US and Chinese providers are available too, on opt-in, each flagged for CLOUD Act exposure and only ever used when your policy says so.
A stateless hot path, with an in-process cache and a streaming tee that never buffers your response. Latency, throughput and uptime are observed per model, next to context window and price.
The fee is for the lock, not the tokens. No seats, no minimums, no markup games. Below roughly 26 euro of model spend per person per month, that lands under a paid Copilot licence.
See pricingCompliance shouldn't mean giving up the best models. That's a false dilemma. You're just missing a lock.
No seat fees and no minimum spend. Nothing leaves your residency policy.
Read the quickstart