A self-hosted, OpenAI-compatible inference endpoint running on dedicated GPU hardware — built and operated by Hoelee, full-stack developer & DevOps engineer.
This is a private large-language-model endpoint, not a public service. It exposes the standard OpenAI chat-completions contract so that any compatible client — a desktop assistant, an editor plugin, an automation workflow, or internal tooling — can use it. Access is keyed: requests without a valid API token are rejected.
Prompts and completions are processed on hardware we control and are not retained by any third-party cloud. There is no external inference provider in the path.
POST /v1/chat/completions
Authorization: Bearer <api-token>
Content-Type: application/json
{"model":"<model-id>","messages":[{"role":"user","content":"Hello"}]}
← {"choices":[{"message":{"role":"assistant","content":"…"}}]}/v1/chat/completionsGET /v1/models (requires a token)Tokens are issued individually and provisioned manually, so this endpoint stays private by default. Message me if you want access for your own tooling or team.
I build this kind of internal infrastructure: self-hosted services with proper authentication, GPU workloads that share hardware sensibly, and the integration layer that makes them usable from the devices your staff already carry.
Private LLM inference is one example. The same approach applies to private document search, internal automation, VPN/remote access, monitoring, and backups — running on hardware you own, so your data never leaves the building.
Available for freelance and contract work — remote, worldwide.
This is one of several private APIs I run on my own hardware — I don't offer a single service:
OpenAI-compatible transcription running on private GPU hardware (whisper.cpp).
OpenAI-compatible chat completions on local GPU — private, no third-party cloud in the path.
Dual-engine neural speech synthesis (Microsoft + Google) behind a single keyed contract.
Beyond these APIs I design and build websites, mailbox hosting, and self-hosted infrastructure for small businesses. See www.hoelee.com for services and blog.hoelee.com for write-ups of how this infrastructure is built — including what running it actually costs.
See how this kind of private infrastructure is built — the hardware, the auth layer, and what running it actually costs: the speech-to-text equivalent is documented on the blog.