A small, personal gateway
for the Gemini API.

One endpoint, OpenAI-compatible, for my own projects. No sign-up, no dashboard, no tracking — it just relays requests to Google's Gemini API and returns the answers.

Read the docs

OpenAI-compatible

Send requests to /v1/chat/completions the way you already do. Existing clients and SDKs work without changes.

Models

Currently serving gemini-3.8-flash as the default model, with gemini-3.5-flash and gemini-2.5-flash available as fallbacks.

Personal use

This gateway is run for one person and a handful of personal projects. It is not a public service and there is no uptime guarantee.

Quick start

curl https://www.gemini-api.site/v1/models \
  -H "Authorization: Bearer YOUR_KEY"

See the docs for the full request format and the model list.

Status

Gateway: ● operational  ·  Last checked: November 2026  ·  Region: Singapore