
Cortecs acts as a unified LLM router designed for teams seeking policy-based access to European model providers. It routes AI workloads to the best models based on cost, speed, and policy requirements subject to your provider and regional policies. Cortecs offers a data processing agreement covering its gateway service and describes itself as the primary data processor for upstream access.
The platform supports standard OpenAI and Anthropic endpoints, making it simple to plug into your existing development stack without rewriting code. You get access to a governance layer and multiple European providers through a single integration.
Cortecs states that it processes payloads in temporary memory, does not retain prompts and prohibits training by its standard providers. Usage metadata and upstream terms should be checked separately. You keep full control to exclude providers that do not meet your internal policies directly from your dashboard.
Routing policies matter. Choose the Sovereign Cloud option when your requirement is providers established in the EU.