Glossary term
Model routing
Sending each request or step to the most suitable model based on difficulty, cost, latency or data sensitivity.
Routine steps can use smaller, cheaper models while complex reasoning uses stronger ones.
Routing decisions should be validated on the evaluation set so cost savings do not reduce quality.
Related terms
- OrchestrationCoordinating the steps of an AI-enabled process: model calls, retrieval, tools, rules, approvals, retries and error handling.
- LLM observabilityCollecting traces, metrics and quality signals from language model applications to understand behaviour in production.
- Fine-tuningFurther training a pre-trained model on task-specific examples to adjust its behaviour, style or format.
Turning concepts into a working system?
We help teams choose the right pattern and build it with evaluation from day one.