FreeBuff vs Clixad: two ad-funded coding agents, and where the ad sits

Two products that share a funding word

An earlier post here argued that "ad-supported" is doing too much work as a label, because three different arrangements are sold under it: in-session ads, a vendor-funded daily grant, and a rewarded offerwall. That post also concluded that the in-session model had been tried by the best-resourced company in the category and abandoned inside six months, when Sourcegraph dropped ads from Amp in March 2026.

That conclusion was too quick. FreeBuff launched on 12 February 2026 with in-session text ads and is still running them in August, so one vendor leaving the model did not close it. This post compares two live ad-funded products on what they actually grant.

What FreeBuff grants

FreeBuff is the free, ad-supported build of Codebuff, published under Apache-2.0. Everything in this section is from FreeBuff's own launch post and README, linked in Sources. Where two review sites disagreed about the session limit, we used the primary source.

• No account, no card. The launch post's words are "No account. No credit card. No config file." You install the CLI and start.
• Limited mode: "Deepseek v4 Flash only, 6 one-hour sessions per day." This is what users outside the supported regions get, and what VPN users get.
• Full mode: a wider model picker, described at launch as available in 25+ countries. The roster has changed since launch, so check the current README.
• The ads: "small, text-only ads from sponsors" between agent turns, not inside generated code and not as popups.

That is a genuinely low-friction product: no signup, no wallet, no earning step, and nothing that sends you somewhere else first.

What Clixad grants

Clixad meters usage in credits against real token consumption. The rate is fixed in code: 100,000 credits is one US dollar of advertiser payout. A new account starts with 25,000 credits, and a free account can earn at most 500,000 credits in a day.

There is also a sponsored line above the input box while a model call runs, marked Ad ahead of the text, and up to two more places on screen can carry an ad marked the same way. They earn a fraction of what completing an offer pays, often nothing, and CLIXAD_SPONSOR=0 turns all of them off. Where the ad sits covers what chooses them and what they cost you.

Credits convert into work directly. The table below prices the same twelve-call agent task used across this blog (one instruction that the agent turns into twelve model calls, resending the whole conversation each round) on every model, and divides two Clixad grants by it.

A median completed CPX offer does not buy one agent task on nearly half the catalogue, and the daily cap does not buy a single task on Claude Fable 5.1.

Credits arrive on completion, and the most common outcome of starting a survey is a screenout: a few questions in, it decides you are not the respondent it is paying for, and it ends with nothing credited. That is how offerwalls work everywhere, and it happens on the wall's side before anything reaches us. From our own ledger: completed offers on our CPX wall have credited from 9,000 to 114,000 credits on completion, with a median of 51,000: 26 completions recorded in our ledger between 27 July 2026 and 12 September 2026, as of 14 September 2026. The ledger does not record how long an offer took.

The units do not convert

FreeBuff's free allowance is measured in time: six one-hour sessions a day in limited mode. Clixad's is measured in tokens, priced into credits. There is no exchange rate between them, and inventing one would be the exact error the tier-limits post exists to name.

If your constraint is wall-clock time at the keyboard, a session limit is the thing that will bite you. If your constraint is how much the model has to read and write, a token meter is. Long sessions with little inference favour the meter. Short bursts of heavy inference favour the clock.

Where the ad sits, and what it has to see

Both products put an ad on your screen. The difference is what is allowed to select it.

An ad rendered inside a coding session is selected by a process that already holds your session, so the vendor has to decide how much of it informs the selection. FreeBuff's launch post answers:

"Prompts and messages may be analyzed to personalize ads, using Freebuff systems and service providers acting on our behalf."

The same page draws a boundary in the other direction, "Separate uploads and connected repositories are not provided to advertising providers", and notes that models or features labelled "May use data for AI training" may keep submissions to develop and improve AI models. So prompts and messages are in scope for ad personalisation, and repositories and uploads are not handed to ad providers. That is a more careful line than most products in this space draw.

An ad that pays for a completed action in a separate tab works differently. The advertiser pays a fixed amount for a finished survey or signup, and the payout reaches our server as a signed postback naming a transaction and an amount. No step in that path has a prompt in it. That comes from how the money path is built, which matters because a policy is a promise and can be revised.

Clixad's own in-session ads, in a line above the input box and in up to two more places, have to pass the same test. They are selected by one fixed category, set on our server, which says the reader is using a developer tool in a terminal. Each request carries a publisher id, that category, an opaque token standing in for your account, and a one-off value. There is no field in it a prompt could travel in. What they do cost you is a connection: each is fetched by your machine, so the ad network sees your IP address. CLIXAD_SPONSOR=0 stops those requests altogether. FreeBuff has no equivalent switch, because its ads are the revenue rather than a top-up on it.

So the question is whether what you write is an input to choosing the ad. FreeBuff's launch post says prompts and messages may be. Ours cannot be, because the selection never sees them.

The trade cuts both ways. Clixad asks you to leave the terminal, do something unrelated, and accept that it often pays nothing. FreeBuff asks for none of that and lets the funding touch what you type. Which is worse depends on what you are working on.

What each one is better at

Pick FreeBuff if you want to be coding in a minute with no account, no wallet and no interruption; if you would rather be shown a text ad than go and complete a survey; if a session-based clock fits your day better than a token meter; or if you want an Apache-2.0 codebase you can read.

Pick Clixad if you want frontier models paid for by offers rather than a subscription, where a stronger model simply costs more credits per turn; if you would rather no part of your prompt be involved in selecting an advertisement; or if you want an allowance denominated in the thing you actually consume, so an unused hour costs nothing.

Pick neither if you already have an API key you are happy paying for. Both of these exist for people who do not, and a key you already hold beats both arrangements on predictability.

These two are also not the only options with inference included. The shortlist post puts both alongside Copilot Free, Cursor's Hobby plan, Amp Free and the Gemini CLI free tier, and applies the same test to all six: what does the grant actually finish?

FAQ