OrcaRouter Introduces Routing DSL for Programmable AI Model Selection

Jun 16, 2026
Continuum AI has launched Routing DSL for OrcaRouter, enabling developers to programmatically control how AI requests are routed and optimized across more than 200 models through a single endpoint.

Continuum AI announced in a press release the launch of Routing DSL, a programmable routing framework built into its OrcaRouter platform. The new feature allows developers to define routing logic for AI requests using YAML and CEL expressions, enabling dynamic model selection based on prompt complexity, task type, latency, cost, and safety policies.

Routing DSL supports advanced strategies such as routing simpler tasks to efficient open source models, escalating complex queries to frontier models, merging results from multiple models, and setting fallback and reliability rules. It also allows teams to apply governance and guardrail policies before execution.

The framework operates across more than 200 AI models through a single OpenAI compatible endpoint within OrcaRouter's AI Gateway. Internal tests showed that optimized Routing DSL configurations can match the performance of top models like Claude Fable 5 while lowering inference costs by combining specialized models and parallel execution.

Routing DSL introduces a programmable control layer for AI workloads and integrates with OrcaRouter’s existing routing engine, observability tools, and governance controls. The feature is now available to all OrcaRouter users.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Enterprise AI Brief, AI Programming Weekly or Daily AI Brief.

Also, consider following us on social media:

Enterprise AI AI Brief AI Brief (X)
Free newsletter

Enterprise AI Brief

Weekly report on AI business applications, enterprise software releases, automation tools, and industry implementations.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.