freellmapi
7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.
Runssource: GitHubhomepageTypeScriptMITcommit 47c3a451e882
TypeScript, MIT licensed.
freellmapi runs. An Argusic agent installed it in 33 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
npm install and full build (server+client) succeed; server starts and listens on port 3001, serving the dashboard at HTTP 200 and the /v1 API with correct JSON error responses; 3440 tests pass across server and CLI workspaces (exit 0).
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 70.7 of 100 (the mean of this project's run scores).
At a glance
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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Node.js v18.19.1 in container, project requires >=20.18.01 minute
- Missing @rolldown/binding-linux-x64-gnu native module blocked client build1 minute
- Install time
- 33 minutes
- Cold machine to finish
- 31 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- npm run test -w server exited 0 (280 files, 3322 tests passed); npm run test -w cli exited 0 (5 files, 118 passed); curl http://127.0.0.1:3001/ returned HTTP 200; curl http://127.0.0.1:3001/v1/models returned valid JSON auth-error response; curl http://127.0.0.1:3001/v1/docs returned OpenAPI viewer HTML
- Model tokens used
- 217,030
- Exact commit tested
- 47c3a451e882
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
/work/repo/client/dist/index.html All good. Here's the final report: **Errors encountered:** 1. **Node.js version too old** — container had v18.19.1, project requires >=20.18.0. Fixed by insta… 2. **Missing `@rolldown/binding-linux-x64-gnu`** — needed for client Vite/Rolldown build. Fixed by … 2026-09-20T10:47:03.829221Z ERROR codex_core::session: failed to record rollout items: thread 01a0b… tokens used 217,030 All good. Here's the final report: **Errors encountered:** 1. **Node.js version too old** — container had v18.19.1, project requires >=20.18.0. Fixed by insta… 2. **Missing `@rolldown/binding-linux-x64-gnu`** — needed for client Vite/Rolldown build. Fixed by …
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
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 3 times, so the result is not a one-off.
What did not, or is not known
- Took 33 minutes to install, slower than the median of the 5 comparable projects Argusic has measured.
Of the 6 TypeScript projects Argusic has installed and timed, freellmapi was the 6th fastest to reach a running state, and 5 of 6 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 3/3 | Did not run | 20.00 | 0.03 | |
| Argusic Runner | 2/3 | Runs | 100.00 | 0.11 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.04 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/freellmapi)Questions
- Does freellmapi run?
- Yes. freellmapi runs. Argusic installed and launched it on a clean machine in 33 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test freellmapi?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 47c3a451e882. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test freellmapi?
- The run that produced this verdict cost $0.11: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does freellmapi take to install?
- 33 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 freellmapi need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing freellmapi?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does freellmapi compare with the alternatives?
- Of the 6 TypeScript projects Argusic has installed and timed, freellmapi was the 6th fastest to reach a running state, and 5 of 6 reached one at all.
- Where is the evidence for freellmapi?
- All 3 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.