OrcaRouter Introduces Routing DSL for Programmable AI Model Selection

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.