{
"name": "llama_swap",
"engine": "openai",
"display_name": "Llama Swap",
"description": "Local proxy that hot-swaps llama.cpp (and other) inference backends on demand via an OpenAI-compatible API.",
"api_key_env": "LLAMA_SWAP_API_KEY",
"base_url": "${LLAMA_SWAP_HOST}/v1/chat/completions",
"env_vars": [
{
"name": "LLAMA_SWAP_HOST",
"required": false,
"secret": false,
"primary": true,
"default": "http://localhost:8080",
"description": "Base URL of the llama-swap proxy (default: http://localhost:8080)"
}
],
"dynamic_models": true,
"models": [],
"supports_streaming": true,
"requires_auth": false,
"skip_canonical_filtering": true
}