YouTube throttles and blocks Hetzner ranges, so neoprism cannot talk to
it directly. tinyproxy listens on the retiolum address of each box and
only accepts neoprism, giving invidious a residential exit.

Bare `provider = "custom"` resolves its credential from a host-gated
candidate list and only forwards OPENAI_API_KEY when base_url points at
openai.com (upstream #28660 / GHSA-76xc-57q6-vm5m). For any other host it
substitutes the literal placeholder "no-key-required", so the llama
cluster answered 401. Use a named custom_providers entry with key_env,
which is not host-gated, and rename the env var to LLAMA_API_TOKEN.