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 applicable state 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
Common endpoints
Health check

Health check

Paddler exposes a single GET /health liveness-check endpoint. It confirms that a service is running and responding, which is useful for load balancers, orchestrators, and uptime monitoring. The same endpoint is available on several of Paddler's services, so you can reach it at each of their addresses.

Endpoint

Method: GET
Path: /health

It is exposed by the following services:

  • the inference service (e.g. http://127.0.0.1:8061/health),

  • the management service (e.g. http://127.0.0.1:8060/health),

  • the OpenAI-compatible service, if you started it with --compat-openai-addr (e.g. http://127.0.0.1:8070/health).

Response

Returns 200 OK with the plain-text body OK.

OpenAI