Glossary · Routing & cost

cascading inference

The technique of routing easy queries to small models and only invoking large models on the subset of queries that need them.

Related terms

• AI gateway
• BYOK (bring your own key)
• LLM gateway
• LLM router
• LLM unit economics
• cost ceiling

Vynaris is an inference gateway that routes each request to the cheapest right-sized model and shows the receipt. Get an API key or read the docs.