# PublicAffairs/openai-gemini

✦ Gemini ➜ OpenAI API proxy. Serverless!

Repository: https://github.com/PublicAffairs/openai-gemini
Canonical: https://ross.abutalabs.com/products/openai-gemini
Homepage: https://my-openai-gemini-demo.vercel.app/
Language: JavaScript
License: MIT
License Family: permissive
Topics: chatgpt-api, gemini-ai, openai, proxy, serverless, gemini
Last push: 2026-03-17T21:02:21+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 72, release rhythm 38, longevity 66
- inputs: {"age_days": 926, "days_push": 169, "days_rel": 254, "gap_med": 116.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3630, forks 5881 (observed 2026-08-28T04:08:12.033221+00:00)

## What it is
A serverless proxy that translates OpenAI API requests into Google Gemini API calls, letting any OpenAI-only tool use Gemini's free tier. It deploys with one click to Vercel, Netlify, Cloudflare Workers, or Deno, and can also run locally.

## Use cases
- use Gemini free tier with tools that only support the OpenAI API
- expose an OpenAI-compatible chat completions endpoint backed by Gemini
- deploy a personal LLM API proxy to Vercel, Netlify, or Cloudflare for free
- run an OpenAI-to-Gemini translation proxy locally with Node, Deno, or Bun
- point existing ChatGPT clients at Google Gemini models

## When to choose
- you have tools hardcoded to the OpenAI API but want to use Gemini models
- you want a free, maintenance-free personal proxy endpoint on serverless platforms
- you need OpenAI-compatible /v1/chat/completions semantics with Gemini as backend

## When to avoid
- you need native Gemini features not representable in the OpenAI API schema
- you need high-volume production traffic beyond personal free-tier limits
- you want a managed multi-provider LLM gateway rather than a single Gemini proxy

## Facets
- artifact type: service
- maturity: active
- function: proxy, api-framework, llm-inference, http-server
- domain: artificial-intelligence, large-language-models, apis, self-hosted, cloud-computing
- platform: serverless, bun, cloud, self-hosted, cli
- tags: openai-compatible-api, gemini-api, api-translation, edge-functions, chat-completions, web-server, nodejs, deno

## Member repositories
- PublicAffairs/openai-gemini (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:12.033221+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:31:53.437604+00:00, confidence not recorded.
  - readme: https://github.com/PublicAffairs/openai-gemini (fetched 2026-08-28T04:08:12.033221+00:00, sha 210007f6f193)
  - homepage: https://my-openai-gemini-demo.vercel.app/ (fetched 2026-08-29T09:26:36.416928+00:00, sha c7c109f8e26a)
- Data as of 2026-08-30T08:39:29.467469+00:00.