~/llamay $ llamay serve -m qwen2.5:0.5b -addr 127.0.0.1:11439 -api-key demo-key-not-a-secret
time=2026-09-18T08:49:40.239-04:00 level=INFO msg="device graph attached" max-tokens=256
time=2026-09-18T08:49:40.239-04:00 level=INFO msg="llamay serving" addr=127.0.0.1:11439 mode
l=qwen2.5:0.5b arch=qwen2 max-loaded=2 keepalive=5m0s params="0.36 GB" context=32768 threads
=7 kv=f32 lexicon=0

  OpenAI      POST http://127.0.0.1:11439/v1/chat/completions
  Anthropic   POST http://127.0.0.1:11439/v1/messages
  Embeddings  POST http://127.0.0.1:11439/v1/embeddings     (start with -embed <encoder.gguf
>)
  Rerank      POST http://127.0.0.1:11439/rerank            (start with -rerank <reranker.gg
uf>)
  Contexts    POST http://127.0.0.1:11439/v1/contexts        (then /{id}/fork?n=8, /{id}/sna
pshot)
  Models      POST http://127.0.0.1:11439/api/pull          (and /api/copy, /api/delete)
  Stats       GET  http://127.0.0.1:11439/v1/stats


~/llamay $ # the server stays up; the rest of this is a second terminal
~/llamay $ # no key: refused
~/llamay $ curl -s -o /dev/null -w '%{http_code}\n' http://127.0.0.1:11439/v1/models
401
~/llamay $ curl -s http://127.0.0.1:11439/v1/models | jq
{
  "error": {
    "message": "this server requires an API key: send Authorization: Bearer <key>",
    "type": "Unauthorized"
  }
}
~/llamay $ # the health check stays open, because a load balancer has no key
~/llamay $ curl -s -o /dev/null -w '%{http_code}\n' http://127.0.0.1:11439/healthz
200
~/llamay $ # with the key
~/llamay $ curl -s http://127.0.0.1:11439/v1/models -H 'authorization: Bearer demo-key-not-a
-secret' | jq '.data[].id'
"all-minilm:latest"
"gemma2:2b"
"gemma3:270m"
"gpt2:q8_0"
"qwen2.5:0.5b"
"smollm2:135m"
"azmx-code-test:latest"