Frequently asked questions

Direct answers for business and technical decision-makers evaluating TechVera.

What is TechVera?

TechVera is a managed LLM platform: one OpenAI-compatible endpoint that connects every relevant LLM provider — global hyperscalers, EU-hosted and EU-sovereign — under a single contract, with cost tracking, latency optimisation, governance and per-request jurisdiction policy. The gateway itself is EU-operated and EU-contracted, run by TechVera GmbH in Wels, Austria.

Is TechVera an AI gateway?

Yes — TechVera is an AI gateway in the technical sense (a single endpoint in front of multiple LLM providers). The difference from typical gateways is the four-pillar scope:
  • Cost transparency — per-request EUR cost across providers, attributable per team and application.
  • Latency optimisation — per-route, on measured behaviour rather than nominal SKU.
  • Governance — scoped API keys, budget enforcement, exportable per-request audit log.
  • Sovereignty — EU-operated gateway, EU-contracted entity, per-request jurisdiction policy.

It is not just aggregation; it is the management layer above the providers.

How does TechVera compare to OpenRouter, LiteLLM, Portkey, Helicone or Together AI?

All of those are US-headquartered. TechVera differs structurally on three layers:
  1. Gateway operation — TechVera runs the gateway on EU-sovereign cloud (OVHcloud Paris); the US alternatives run on US cloud, so a customer's clear-text prompt traverses a CLOUD-Act / FISA-702 / Patriot-Act exposed surface even when the inference endpoint sits in the EU.
  2. Contractual jurisdiction — TechVera contracts via an Austrian GmbH under EU law; the US alternatives contract via Delaware Corps, where a DPA cannot cure CLOUD-Act exposure (Schrems II precedent).
  3. Inference routing — like the others, TechVera routes per request across global, EU-hosted and EU-sovereign providers. This layer alone is replicable; the first two are not.

Beyond the sovereignty structure, TechVera adds cost transparency (per-request EUR across providers), latency optimisation (measured per-route) and governance (scoped keys, audit log, policy enforcement) as first-class management features. The API is OpenAI-compatible, so migration is a base URL change.

Is TechVera GDPR-compliant?

Yes. TechVera GmbH is an EU company, the control plane is operated from EU infrastructure, and a jurisdiction-aware routing policy ensures that requests flagged as sensitive never leave EU-sovereign providers. Customer request and response content is not retained and is not used for model training. A Data Processing Agreement is available on request. See Regulation (EU) 2016/679 (GDPR).

How does TechVera address the EU AI Act and NIS2?

The EU AI Act imposes obligations on providers and deployers of AI systems — including transparency, risk classification, and record-keeping. NIS2 requires adequate cybersecurity and supply-chain controls for essential and important entities. TechVera supports both by logging provider, country and model for every request, giving you an auditable record of AI usage, and by letting you route high-risk workloads only to EU-sovereign providers.

What does "EU sovereign" mean in practice?

In TechVera terms, an EU-sovereign request is served by a provider that is legally headquartered in the EU, operates on EU infrastructure, and is not subject to third-country access regimes such as the US Cloud Act. A US hyperscaler's EU region does not qualify as sovereign — that is the core distinction TechVera enforces.

Which LLM providers does TechVera support?

TechVera integrates eight providers today across three jurisdictional tiers.

The full catalogue with every routable model is at /models. The catalogue grows on customer demand — to nominate a provider for the next wave, write to office@techvera.ai.

Is the API OpenAI-compatible?

Yes. TechVera exposes the OpenAI Chat Completions, Embeddings and Responses APIs on https://api.techvera.ai/v1. Existing code using the OpenAI SDK migrates by changing the base_url and API key — no other changes required. The model parameter is used to select a routing policy or a specific model.

Where is customer data processed?

It depends on the routing policy you choose. Under the EU Sovereign policy, the request is served only by providers legally headquartered in the EU with EU infrastructure. Under EU Hosted, providers with EU-hosted endpoints are also eligible. Under Global, any configured provider is eligible. Every response carries a header indicating provider, country and model actually used.

Who operates TechVera?

TechVera GmbH, Friedhofstraße 57, 4600 Wels, Austria. Commercial register: Landesgericht Wels, FN 673823 t. VAT: ATU83067547. Managing Director: Leopold Strohmayr, MSc, MBA.

The company is 100 % privately owned in Austria — no foreign capital, no parent company outside the EU. The same sovereignty bar we apply to upstream providers applies to TechVera itself.

Contact office@techvera.ai.