gemini-web-to-api

✨Reverse-engineered API for Gemini web app. It can be used as a genuine API key from OpenAI, Gemini, and Claude.

Runs with mockssource: GitHubGoMITcommit 363317054e02

Go, MIT licensed. The project labels itself: ai, api, chatbot, claude, docker, fiber framework, gemini and gemini api.

gemini-web-to-api runs, with stand-ins for the services it depends on. An Argusic agent installed it in 2 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

Go 1.27.2 installed, project builds, server launches and serves /health on port 4981 responding HTTP 200, all 9 test suites pass (85+ subtests), Gemini auth fails with dummy cookies as expected

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.38 (measured)
recorded runs
1
last tested
stars
681
forks
181
open issues
4
watchers
8
size
83 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Install time
2 minutes
Cold machine to finish
18 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
`go build -o /tmp/gemini-web-to-api cmd/server/main.go` succeeded; `go test gemini-web-to-api/...` exited 0 with 85+ subtests across 12 suites all PASS; `curl -s -o /dev/null -w %{http_code} http://localhost:4981/health` returned 200 with body {"service":"gemini-web-to-api","status":"ok"}
Model tokens used
349,562
Exact commit tested
363317054e02
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

All works. Let me compile the final results.
- **Go 1.27.2** was installed at `/tmp/go`. The binary `v` at `/tmp/v/v` is the **V programming lan…
- The project builds successfully with `go build -o /tmp/gemini-web-to-api cmd/server/main.go` (0 e…
- The server starts and responds to `GET /health` with `{"service":"gemini-web-to-api","status":"ok…
- All 9 test suites pass (configs, models, utils, claude, gemini, openai, providers, openai_dto, e2…
tokens used
349,562
All works. Let me compile the final results.
- **Go 1.27.2** was installed at `/tmp/go`. The binary `v` at `/tmp/v/v` is the **V programming lan…
- The project builds successfully with `go build -o /tmp/gemini-web-to-api cmd/server/main.go` (0 e…
- The server starts and responds to `GET /health` with `{"service":"gemini-web-to-api","status":"ok…
- All 9 test suites pass (configs, models, utils, claude, gemini, openai, providers, openai_dto, e2…

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Installed in 2 minutes, faster than the median of the 236 comparable projects Argusic has measured.
  • Nothing broke on the way: zero errors between clone and running.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 237 ai projects Argusic has installed and timed, gemini-web-to-api was the 54th fastest to reach a running state, and 168 of 237 reached one at all.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks92.000.38

Topics (from GitHub)

aiapichatbotclaudedockerfiber-frameworkgeminigemini-apigenerative-aigooglellmopenaiproxy-serverrest-apireverse-proxy

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/gemini-web-to-api.svg)](https://argusic.com/subject/gemini-web-to-api)

Questions

Does gemini-web-to-api run?
gemini-web-to-api runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test gemini-web-to-api?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 363317054e02. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test gemini-web-to-api?
The run that produced this verdict cost $0.38: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does gemini-web-to-api take to install?
2 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does gemini-web-to-api need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing gemini-web-to-api?
Nothing did, in the recorded run: zero errors between clone and running.
How does gemini-web-to-api compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, gemini-web-to-api was the 54th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for gemini-web-to-api?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion