Local‑LLM
Sign in

Private inference

Local LLM

Open models on dedicated GPU hardware, behind a standard OpenAI-style API with OAuth 2.1. Use the official OpenAI SDKs — only the base URL and the sign-in change.

Request access Sign in How it works
API
OpenAI-compatible
chat, completions, embeddings, streaming
Sign-in
OAuth 2.1
client credentials, 15-minute tokens
Privacy
No prompt logs
API requests are not stored

How access works

  1. Sign in with Google and describe your project.
  2. The request is reviewed; you get an email when it is approved.
  3. Create your API secret in the dashboard and follow the setup guide — or try the models right away in the chat.