Introduction
Using Paddler API Streaming tokens
Inference service
Continue from conversation history Continue from raw prompt Generate embedding batch WebSocket endpoint
Management service
Get agents Get agents stream Get balancer desired state Get buffered requests Get buffered requests stream Get chat template override Get model metadata Put balancer desired state Get metrics
Compatibility Services
OpenAI

Get metrics

This endpoint allows you to scrape reporting metrics about your current Paddler setup in Prometheus format.

The following metrics are available:

  • paddler_slots_processing - the number of slots currently processing requests

  • paddler_slots_total - number of total available slots

  • paddler_requests_buffered - the number of requests currently buffered

You can read more about the metrics in the Reporting metrics article.

Endpoint

Method: GET
Path: /metrics

Response

# HELP paddler_slots_processing Number of processing slots
# TYPE paddler_slots_processing gauge
paddler_slots_processing 0

# HELP paddler_slots_total Number of total slots
# TYPE paddler_slots_total gauge
paddler_slots_total 2

# HELP paddler_requests_buffered Number of buffered requests
# TYPE paddler_requests_buffered gauge
paddler_requests_buffered 0
Put balancer desired state OpenAI