Model Usage

The Model Usage page shows how your API requests are distributed across different LLM models over time.

Historical usage and recorded costs remain available when a provider is removed from the catalogue. Removed providers no longer appear in catalogue listings or routing comparisons.

Breakdown

The breakdown selector picks what each chart series represents:

• Model (default) — One series per model, combining every provider that served it (for example, the same model served by two providers counts as one)
• Mapping — One series per provider mapping, to see which provider served each model
• API key — One series per API key
• User — One series per team member (Enterprise owners and admins)

Filters

Two filters let you narrow down the data:

• API Key — Select a specific API key or view usage across all keys (model views only)
• Date range — Choose a time period to analyze

Usage Chart

The main chart displays a time-series breakdown of requests per model. Each model is represented by a different color, making it easy to see:

• Which models are used most frequently
• How usage patterns change over time
• Whether usage is concentrated on a single model or spread across many

This page is useful for understanding your model distribution and identifying opportunities to optimize costs by switching to more cost-effective models for certain workloads.