# Sophomoresty/gemini-web2api

Convert Google Gemini web into OpenAI-compatible API. Zero auth, cross-platform, single file.

Repository: https://github.com/Sophomoresty/gemini-web2api
Canonical: https://ross.abutalabs.com/products/gemini-web2api
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-14T18:29:19+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 35, longevity 6
- inputs: {"age_days": 97, "days_push": 19, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2880, forks 639 (observed 2026-08-28T04:07:27.561906+00:00)

## What it is
A single-file Python server that exposes Google Gemini's web interface as an OpenAI-compatible API, supporting chat completions, streaming, tool calling, and Gemini-native endpoints. It requires no official API key and runs cross-platform with only httpx as an optional dependency.

## Use cases
- use Gemini models through OpenAI-compatible clients like Cherry Studio or ChatBox
- run a free local LLM API endpoint without paying for Gemini API keys
- connect OpenAI Codex CLI or Gemini CLI to Gemini web models
- get streaming chat completions with tool calling from Gemini web
- adjust thinking depth for extended reasoning outputs
- self-host a drop-in replacement for /v1/chat/completions

## When to choose
- you want OpenAI-format access to Gemini web without an API key or cost
- you need a lightweight, single-file, cross-platform proxy server
- you use clients or CLIs that speak the OpenAI or Gemini native API formats
- you want built-in web search and adjustable thinking depth

## When to avoid
- you need guaranteed uptime or SLA-backed official API access
- you require features not available through the Gemini web interface
- your usage may violate Google's web terms of service or risk account restrictions
- you need production-grade authentication beyond simple bearer keys

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, http-server, api-framework, chatbot, web-scraping
- domain: large-language-models, apis, self-hosted, developer-tools, artificial-intelligence
- platform: python, cross-platform, self-hosted, cli
- tags: openai-compatible-api, gemini, reverse-proxy, api-wrapper, single-file, free-tier, streaming, tool-calling

## Member repositories
- Sophomoresty/gemini-web2api (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:27.561906+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 2026-08-30T07:35:33.000615+00:00, confidence not recorded.
  - readme: https://github.com/Sophomoresty/gemini-web2api (fetched 2026-08-28T04:07:27.561906+00:00, sha 32ae4a7f3359)
- Data as of 2026-08-30T08:39:29.467469+00:00.