Guarrix — questions developers ask

Nowhere persistent. Prompts and responses are processed in RAM and discarded immediately after validation. Only metadata — timestamps, token counts, and PII type labels — reaches our audit log.

No. We never access your content beyond the moment of validation. Content is discarded after each request. We do not use your prompts or responses to train or fine-tune any model.

OpenAI, Anthropic, Mistral, and any provider with an OpenAI-compatible API endpoint. You supply your own API key; Guarrix never shares keys between tenants.

Encrypted with AES-256-GCM at rest. The encryption key lives in a separate environment variable that never touches the database. The plaintext key is only held in RAM during a request and is never logged.

Names, email addresses, phone numbers, IBAN and credit card numbers, IP addresses, passport and national ID numbers, dates of birth, and more. Entity types are configurable per tenant.

Yes. Data is processed in the EU on Hetzner infrastructure. Dot-0 is the data controller under Dutch law. You retain all rights under GDPR Articles 15–22, including the right to access, correct, and delete your data.

The request is blocked with HTTP 400 before it reaches the LLM. An audit record is written with injection_detected: true but no content. Your application receives a clear blocked response.

Yes. Every LLM response is scanned for PII and checked against your outbound policy rules before being returned to your application. Content that violates policy is blocked or scrubbed, not forwarded.

All infrastructure runs on Hetzner in the EU with no US parent company involvement and no CLOUD Act exposure. We do not use AWS, Azure, or GCP.

Create a free account, add your LLM API key in the dashboard, point your application at https://api.guarrix.com/v1/chat/completions, and use your Guarrix key instead of your LLM provider key. The free tier includes 500 requests per month.

Guarrix offers five plans: Free (500 requests/month), Starter (€49/month, 5,000 requests), Pro (€149/month, 25,000 requests), Business (€349/month, 100,000 requests), and Enterprise (custom volume with dedicated infrastructure, pricing on request). Overages are charged per request above your plan's included volume.

Yes. The free tier includes 500 requests per month with no time limit and no credit card required. You can upgrade to a paid plan at any time from your dashboard.

Yes. You can cancel from your dashboard settings at any time. Your subscription continues until the end of the current billing period. Consumer customers in the EU have a 14-day withdrawal right on new subscriptions under Dutch consumer law.

Requests above your plan's included volume are charged at the overage rate shown on the pricing page. You can set a monthly spend cap in your dashboard to prevent unexpected charges.

Yes. Beyond the built-in entity types, you can create custom rules using regex patterns or keyword lists. Custom rules can block, scrub, or flag content that matches your criteria. Rules are configured per tenant from the dashboard.

Yes. Prompt injection detection is enabled on all plans. When an injection pattern is found in an inbound prompt, the request is blocked before it reaches the LLM. No injection content is forwarded or logged.

Yes, as long as your model exposes an OpenAI-compatible API endpoint. Point Guarrix at your endpoint URL instead of a cloud provider. Your model endpoint must be reachable from Guarrix's infrastructure over HTTPS.

Business and Enterprise plans include a 99.9% uptime SLA. Free and Starter plans target the same infrastructure but without a contractual SLA. Service status is published at status.guarrix.com.

Email hello@guarrix.com. Business and Enterprise customers have access to a priority support queue with a 4-hour response guarantee during EU business hours.

From your dashboard you can export your audit log as CSV or JSON for any date range up to 90 days. Exported data includes request metadata — timestamps, token counts, PII labels — but never prompt or response content.