The Auto-Router is Infere's AI-powered model router. It analyzes prompt complexity and required capabilities, then selects the best model-provider combination for the chosen routing mode: cost-optimized, balanced, or quality-optimized. It is enabled per API token and can be constrained by provider preferences.

Why it matters

Manual routing rules are hard to maintain as models and prices change. An AI router updates the decision automatically as the catalog changes.

How it works

The Auto-Router analyzes prompt complexity and required capabilities, then selects the optimal model-provider combination for a routing mode - cost-optimized, balanced, or quality-optimized - under any provider preferences you set. It is enabled per API token and disabled by default.

Example

A short factual question is answered by a cheap model, while a multi-step reasoning request is routed to a frontier model - both under the cost-optimized mode.

← Back to the full glossary

Put the platform behind the terms

Route, evaluate, and monitor every AI request from one OpenAI-compatible platform.

Start Free → Explore the Features