Check if llama-server is running and get status

Get or set server properties and default generation settings

List available/loaded models

View current slot processing state

Get Prometheus-compatible metrics (tokens processed, latency, etc.)

Convert text to token IDs

Convert token IDs back to text

Format chat messages using model's template without inference

Generate text completion from a prompt

Chat completion (OpenAI-compatible format)

Generate embeddings for text

Code completion with prefix and suffix context (fill-in-middle)

Rerank documents by relevance to a query

Load a model (router mode only)

Unload the current model (router mode only)

List loaded LoRA adapters

Set LoRA adapter scales

Start llama-server as a child process with the specified model

Stop the running llama-server process