nomyo-router/doc/examples/sample-config.yaml

# config.yaml
# Ollama endpoints local + remote
endpoints:
  - http://localhost:11434
  - http://192.168.0.51:11434
  - http://192.168.0.52:11434
  # External OpenAI-compatible endpoints (will NOT be queried for /api/ps /api/ps_details)
  - https://api.openai.com/v1

# llama-server endpoints (OpenAI-compatible with /v1/models status info)
# These endpoints will be queried for /api/tags, /api/ps, /api/ps_details
# and included in the model selection pool for inference routing
llama_server_endpoints:
  - http://localhost:8080/v1
  - http://192.168.0.33:8081/v1

# Maximum concurrent connections *per endpoint‑model pair* (equals to OLLAMA_NUM_PARALLEL)
max_concurrent_connections: 2

# Optional router-level API key that gates router/API/web UI access (leave empty to disable)
nomyo-router-api-key: ""

# API keys for remote endpoints
# Set an environment variable like OPENAI_KEY
# Confirm endpoints are exactly as in endpoints block
api_keys:
  "http://192.168.0.50:11434": "ollama"
  "http://192.168.0.51:11434": "ollama"
  "http://192.168.0.52:11434": "ollama"
  "https://api.openai.com/v1": "${OPENAI_KEY}"
  "http://localhost:8080/v1": "llama-server"  # Optional API key for llama-server - depends on llama_server config
  "http://192.168.0.33:8081/v1": "llama-server"