ServiceActive

OpenRouter Private Models

Bring your own model endpoints to OpenRouter, scoped to approved users and organizations.

Open source page

Product features

Product features

​ Advanced Sorting with Partition

​ Example: Using Multiple Percentile Cutoffs

​ Floor Price Shortcut

​ How Percentiles Work

​ Nitro Shortcut

​ Performance Thresholds

​ Price-Based Load Balancing (Default Strategy)

Provider Routing

​ Provider Sorting

​ Use Case 1: Route to the Highest Throughput or Lowest Latency Model

​ Use Case 2: Find the Cheapest Model Meeting Performance Requirements

​ When to Use Percentile Preferences