The free tier runs on models that cost a fraction of a cent per request, so ad revenue covers them comfortably. That part is genuinely free and stays free. Kimi and Qwen cost more than that but nowhere near frontier prices, so one sponsor spot covers a reply on either.

The catch, if you want to call it that, is the premium tier: Claude and Kimi cost real money per token, so you pay for them with attention instead of euros. If you never watch a sponsor spot, you never get premium access, and you keep the free models anyway.

No. Ad matching reads your dependency manifest (package.json, requirements.txt, go.mod) on your machine, and turns it into a short list of tags like react, postgres, aws. Those tags and your country are what get sent, anonymously.

Your prompts do go to the model provider you selected, because that's how inference works. That's true of every AI coding assistant, and any tool that tells you otherwise is being careless with the word "private".

Yes. Anthropic's API, at Anthropic's prices, which is exactly why it is credit-gated rather than free. The model that answered is named in the ledger entry for that request.

What we can't do, and won't pretend to do, is resell a Claude Pro subscription at a discount. Nobody can. If someone offers you that, ask what they're actually routing your requests to.

Because the audience is the product. A verified developer in a specific city working in a specific stack is worth several times a generic browser user to the recruiters and companies who fund this. Opening it up to everyone with a browser dilutes exactly the thing that makes the ad slots worth buying.

Chess Code is real chess where you move a piece by writing the CSS that puts it on the square. Pick a piece and the board shows you a rule with the values missing. Files a to h are grid-column, one to eight. Ranks are grid-row, counted from the top of the board. Write the rule, the piece moves. It is the same grid you use for layout, doing the thing it actually does.

There are fifty puzzles from the Lichess open database, six bots from beginner up, and one versus one either on the same device or online with a code you send a friend. Free, in the browser, no signup. An account only adds a profile, board themes and achievements.

Scroll up and play it.

It is on here because it is the part of 4devs that exists today. The extension is still being built; this is a thing you can actually use while you wait, and it is the same idea in miniature: describe what you want in code, and the code does it. If moving a knight with a grid rule was fun, the extension is that pointed at your real work.

The request is refused before it's sent, and you're offered the free model instead. The balance floor is zero, checked server-side. No overdraft, no "you owe us", no card on file to charge.

Two reasons, one idealistic and one commercial. Frontier model subscriptions cost the same in Athens as in San Francisco while salaries do not, so the price of good tooling bites harder here. And it is where we are: we can talk to the companies hiring, and to the developers using this, without a plane ticket. The product is for developers anywhere in Europe.

The site launches in English and Greek. Other languages follow based on where waitlist signups actually come from. Building translations for a market that has not shown up yet is how small projects run out of time.

Those tools pay you cash for ad impressions while you use someone else's AI. This is the other way round: the ad revenue is spent inside the product, on model access, which is why the free tier can exist at all rather than being a discount on a subscription you're still buying.

The other difference is where the ads come from. Their inventory is global and programmatic. Ours is meant to be sold directly, locally, at rates that only make sense because the audience is specific.