Get model usage distribution across the fleet
Fleet
Get model usage distribution across the fleet
Use when: caller wants to see which models the fleet is actually using and in what proportion (informing model-pool decisions)
Per-model request count, percentage of fleet traffic, cost, average latency, tokens, and success rate. Sorted by request volume. Useful for understanding which models the fleet actually depends on.
GET
Get model usage distribution across the fleet
Documentation Index
Fetch the complete documentation index at: https://docs.verlon.ai/llms.txt
Use this file to discover all available pages before exploring further.