Free Codex CLI alternative: what Codex costs, and what its free plan does not say

What Codex costs

Codex is one agent with several front ends: a CLI, an IDE extension, a desktop app and a cloud version. This post is about the CLI. Its README states that the repository "is licensed under the Apache-2.0 License", and it signs in two ways: with a ChatGPT account, spending the plan's allowance, or with an OpenAI API key, paying per token.

The README recommends signing in "to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan". OpenAI's Codex pricing page goes further down the ladder and adds two cheaper tiers below Plus. Everything below comes from that page and the README, both read on 18 September 2026.

Read the descriptions in order and they form a ladder of usage: quick tasks, lightweight tasks, a few focused sessions a week, then multiples of that. Plus is the plan most people mean when they say Codex, and OpenAI describes it as enough for "a few focused coding sessions each week". That is worth knowing before you plan a working week around it.

What the free plan does not say

OpenAI publishes usage estimates for Codex, and its table starts at Plus. There is no column for Free or for Go. The Free plan is priced at $0 and linked from the page, and its allowance is stated nowhere on it.

The published estimates are counted in local messages per five-hour period, and OpenAI attaches warnings to them. Above the table: "These estimates are not fixed message limits". Below it: "Local messages and cloud chats share your plan's usage allowance. Weekly limits may also apply."

A message is what you send. What it costs depends on what the agent does next, and OpenAI says so on the same page: "Tasks that look similar can consume different amounts of your allowance." It adds that "prompt length alone isn't a reliable estimate." That is why the ranges run as wide as tenfold, and it is the problem our post on request counts describes: an allowance counted in anything other than tokens cannot tell you how much work it holds.

The page is also quiet on what happens when the Free plan runs out. It says that Plus and Pro users "can purchase additional credits to continue working", and that "All users may also run extra local chats using an API key". For a free account, then, the route past the limit is the API, paid per token. Our post on reset windows found the paid plans documenting their limits better than the free tiers do, and Codex's free plan fits that pattern.

What Clixad does differently

Clixad does the same job in the terminal. It works through a project the way the Codex CLI does, editing files and running commands, and it asks before either unless you switch that off. The bill is where it departs from Codex.

Tokens are the unit. Every model call is metered from its real token count at a published rate, 100,000 credits to one US dollar of list value. The price of each model is public before you pick it, and a small job costs a small amount.

Five cheap models are free every day. GPT-5 Nano, Gemini 2.5 Flash-Lite, DeepSeek V4 Flash, Gemini 3.1 Flash-Lite and Kimi K2 cost nothing up to 12,000 credits of usage per account per day. That allowance sits inside a daily budget shared by everybody, so on a busy day the free turns can run out sooner. Free usage adds and deducts nothing. Past either limit those models cost credits again until the next day.

The rest of the catalogue runs on credits. Fourteen models from five vendors sit on one balance, and /model switches between them mid-session. OpenAI's four run from GPT-5 Nano at the cheap end to GPT-5.2 Pro at the top, with GPT-5.2 and GPT-5.5 between them. A new account starts with 25,000 credits. After that you earn credits by completing an advertiser action on an offerwall page in a browser tab, or you buy them; the smallest pack is $5 for 500,000 credits.

OpenAI's newest models are missing. The GPT-5.6 family and GPT-6 Astra that Codex offers are not in our catalogue, which was last read from OpenRouter on 26 July 2026. The pricing page also says "GPT-5.5 retires from ChatGPT, ChatGPT Work, and Codex on all plans on October 14, 2026. The OpenAI API isn't affected." Our GPT models are reached through the API.

Earning is uneven, and we say so. Credits arrive on completion. The most common outcome of starting a survey is a screenout: a few questions in, the survey decides you are not the respondent it wants and ends with nothing credited, or with a small bonus. 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, so we cannot tell you what a minute pays.

There is one ad in the session. While a model call runs, one line above the input box shows a sponsored message marked Ad. Nothing you type takes part in choosing it, and CLIXAD_SPONSOR=0 stops the request for it being made at all. Codex shows no advertising, and that counts in its favour.

Your instruction file carries over. Codex reads project instructions from AGENTS.md, which its pricing page mentions in its advice on making limits last. Clixad reads the same file, next to its own CLIXAD.md, so a repository set up for Codex needs no new one.

One agent task, priced

A plan price tells you what you pay and leaves out what you get, so this blog prices one fixed workload: a single instruction that an agent turns into twelve model calls, starting at 12,000 input tokens and resending the whole conversation every round. The shape is declared in the markup of the tier-limits post, and a test recomputes every figure below from our pricing engine.

The OpenAI rows below GPT-5 Nano sit outside the free allowance. The 25,000-credit signup bonus does not cover a task on any of them, and a full day at the earning cap buys 4 tasks on GPT-5.2 and 1 on GPT-5.5. GPT-5.2 Pro costs more per task than the whole cap, at 1,279,531 credits, so a day of earning does not buy a single task on it.

The free part is the top two rows: 3 whole tasks a day on GPT-5 Nano and 2 on Gemini 2.5 Flash-Lite, with no earning at all. Next to what Plus estimates for GPT-5.6 Luna, that is small.

Who Clixad fits

Someone who codes in bursts. Credits do not expire, so a quiet week costs nothing and the balance is still there the week after. A subscription bills the quiet week at the price of the busy one.

Someone who wants a price before the task. Codex's free plan publishes no allowance and its paid plans publish ranges. Our table gives one number per model for a defined task, and the wallet is checked before a request starts.

Someone who wants several vendors on one balance. Claude, GPT, Gemini, DeepSeek and Kimi models sit behind the same /model picker, priced per token. Trying Claude Sonnet 5 on a problem GPT-5.2 fumbled costs that call and nothing more.

Someone without a card to put on file. The account is a GitHub login, and neither the free allowance nor the offerwall asks for payment details.

Who should pay for Codex

Anyone for whom Codex is the daily tool. Plus costs $20 a month and includes, in OpenAI's words, "GPT-5.6 Luna for higher usage limits on lighter-weight or high-volume workloads", estimated at 250 to 2,000 local messages every five hours.

We cannot convert those messages into our tasks, and OpenAI warns against converting them into anything. The gap is wide enough that the conversion hardly matters. Take GPT-5.5, the one model both sides carry and price. The bottom of OpenAI's Plus estimate for it is 15 messages in five hours, and our whole daily earning cap covers 1 twelve-call task on it. The units differ, and the gap is too wide for that difference to rescue us.

Buying credits from us does not change the picture for full-time use. Bought credits pay for tokens at provider cost with our margin on top, a 1.5 markup that the funding post sets out, where a subscription is one flat price.

Codex also does things we do not. Its Plus plan includes "Cloud-based integrations like automatic code review and Slack integration", and Clixad has neither. OpenAI's newest models are in Codex and not here. If those matter to how you work, stay with Codex and pay for Plus or Pro.

Other free agents exist, and they are built differently from ours. FreeBuff grants a daily allowance of hours on its own model picker. If your work leans on Anthropic's models, the Claude Code comparison runs the same numbers against Anthropic's plans.

FAQ