Amsterdam-based Orq.ai has launched its AI Router as a standalone product, positioning AI routing as a critical control layer for enterprises grappling with rising large language model (LLM) costs, infrastructure lock-in and growing sovereignty demands.
The move comes as organisations increasingly shift from experimenting with a single model to running production systems across multiple LLMs. While this multi-model approach helps balance performance, reliability and cost, it also introduces operational complexity that traditional application stacks were not designed to handle. For European fintech bunq, those challenges became tangible while operating its own internally built routing solution.
“We built our own LLM routing infrastructure, but maintaining it became increasingly expensive and time-consuming, while still leaving gaps in observability and performance,” said Benjamin Kleppe, GenAI Lead at bunq. “We chose to work with Orq.ai to replace that internal setup with a production-ready AI Router that meets our governance, scalability, and cost-monitoring requirements.”
By making the Router available independently of its broader agent lifecycle platform, Orq.ai is targeting teams that want to start by solving routing and cost control before committing to a full-stack AI management platform. The Router acts as a single gateway through which teams can manage and optimise requests across multiple models.
According to Orq.ai co-founder Sohrab Hosseini, routing quickly shifts from a background function to a bottleneck once systems move beyond a single model. “As soon as AI systems move beyond a single model, routing turns from plumbing into a production bottleneck. Making the router standalone lets teams regain control early, with a single line of code,” he said.
The company is also leaning into Europe’s intensifying debate around AI sovereignty. Hosseini argues that questions around where inference runs, who controls the infrastructure, and how quickly organisations can adapt to geopolitical or regulatory shifts are ultimately enforced at the routing layer. By separating the Router into a standalone product, Orq.ai aims to give enterprises more direct control over those decisions.
The Router allows teams to define routing policies based on geography, latency, cost or custom constraints, without having to re-architect applications. It can also be deployed entirely within a customer’s own infrastructure, supporting both public and private models, an important consideration for regulated industries such as financial services and healthcare.
Pricing is another point of differentiation. Rather than applying a percentage-based mark-up on every model request, a model used by many AI gateways, Orq.ai separates routing from usage-based services. Routing itself carries no platform mark-up, while customers pay for tracing and logging based on data volume.
With the standalone release, Orq.ai is effectively carving out routing as the first entry point into enterprise AI infrastructure. Organisations can deploy the Router immediately and later expand into the company’s broader agent lifecycle capabilities as operational requirements mature.
The Orq.ai Router is available immediately as a standalone product, with further details available here.
Founded in 2022 and headquartered in Amsterdam, Orq.ai is the enterprise control platform for the full AI agent lifecycle. The company's Agent Platform 4.0 enables organizations to experiment, evaluate, deploy, observe, and optimize AI agents through a unified interface that prioritizes safety, collaboration, and scalability. Orq.ai supports over 300+ LLM models and offers flexible deployment options, including cloud, hybrid, and on-premises configurations to meet enterprise data sovereignty requirements. The company serves forward-thinking enterprises and AI-native startups across Europe and the United States. For more information, visit orq.ai.
