Glossary
What is Model Routing?
The practice of automatically selecting which LLM model handles each request based on criteria like cost, capability, or latency.
Model routing allows you to define rules that determine which model processes each request. Simple queries might go to cheaper models like GPT-4o-mini, while complex reasoning tasks go to GPT-4. Routing can also consider latency requirements, provider availability, and specific capabilities like long context or vision.
Examples
- → Route simple classification tasks to GPT-4o-mini ($0.15/1M) instead of GPT-4 ($30/1M)
- → Use Claude for documents over 100K tokens
- → Route time-sensitive requests to the fastest provider
Related Terms
Ready to implement model routing?
ScaleMind provides everything you need.
Get Started Free →