# Free Claude Code alternative: what Claude Code costs, and when to pay for it anyway > Source: > Published: 2026-09-18 00:00:00+00:00 # Free Claude Code alternative: what Claude Code costs, and when to pay for it anyway Anthropic does not include Claude Code in its free plan. The pricing page marks it "No" on Free and includes it from **Pro, at $20 a month or $17 a month billed annually**, and in Max from $100 a month. The usage behind those prices is not a number you can plan against: Anthropic says the limits reset on a rolling five-hour window and that "there's no fixed message count". Clixad is a terminal coding agent that meters real tokens in credits. Five cheap models are free up to a daily allowance, and every other model runs on credits you earn in a browser tab or buy, Claude Sonnet 5 and Claude Opus 5 among them. We build Clixad, so trust the sourced numbers here before our verdict. The verdict cuts against us anyway: if you code all day on Claude, the subscription is the better deal. ## What Claude Code costs Everything in this section comes from Anthropic's own pricing page and Claude Code documentation, both read on 18 September 2026. Prices move, so check the date on any figure you plan around, ours included. | Anthropic's individual plans and whether each includes Claude Code, as listed on its pricing page. Vendor figures, not engine output. | | | |---|---|---| | Plan | Price | Claude Code | |---|---|---| | Free | $0 | No | | Pro | $20 a month billed monthly, or $17 a month with the annual discount ($200 billed up front) | Yes | | Max | From $100 a month, for "5x or 20x the usage of Pro per 5-hour session" | Yes | | Console account | Pay as you go, per token at API rates | Yes | Two sentences on the same page decide more than the prices do. The first says where Claude Code's usage comes from: "Claude Code is included in all paid plans. It shares the same usage limits as the rest of your plan, so your work in the terminal and your chats draw from one pool." The second concerns how big that pool is. Anthropic's FAQ says usage varies with what you ask and which model answers, "so there's no fixed message count." Pro is described as at least 5x the usage of Free per five-hour session, and Max as 5x or 20x the usage of Pro. Those are ratios with nothing at the bottom of them, so nobody outside Anthropic can turn a plan into a number of finished tasks. We do not try. The one hard number comes from the pay-as-you-go side. Anthropic's cost documentation reports that "Across enterprise deployments, the average cost is around $13 per developer per active day and $150-250 per developer per month, with costs remaining below $30 per active day for 90% of users." That is what Claude Code costs when you pay for the tokens directly, and it matters again in the section on who should pay. ## What Clixad does differently Clixad does the same job in the terminal. It works through a project the way Claude Code does, editing files and running commands, and it asks before either unless you switch that off. The bill is where it departs from Claude Code. **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. A small job costs a small amount, and the price of each model is public before you pick it. **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, Anthropic's among them, and `/model` switches between them mid-session. 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. **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. Claude Code shows no advertising, and that counts in its favour. **Your project files mostly carry over.** Clixad reads project instructions from `AGENTS.md` and from its own `CLIXAD.md`. It does not read `CLAUDE.md`, so copy that file across if you switch. MCP servers declared in a project's `.mcp.json` use the `mcpServers` object Claude Code writes, and Clixad reads that file as it is. ## 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](https://clixad.io/blog/free-ai-coding-tier-limits/), and a test recomputes every figure below from our pricing engine. | Credits for one twelve-call agent task, then how many whole tasks the daily free allowance (12,000 credits, five cheap models only) and a full day at the earning cap (500,000 credits) each cover. Recomputed from packages/pricing by a test. | | | | |---|---|---|---| | Model | Credits per task | Free allowance, per day | Earning cap, per day | |---|---|---|---| | GPT-5 Nano | 3,051 | 3 | 163 | | Gemini 2.5 Flash-Lite | 5,664 | 2 | 88 | | Claude Haiku 4.5 | 57,690 | not a free model | 8 | | Claude Sonnet 5 | 115,380 | not a free model | 4 | | Claude Opus 5 | 288,450 | not a free model | 1 | `packages/pricing` by a test. Read the Claude rows first. The free allowance does not reach them at all. The 25,000-credit signup bonus does not cover a single Claude task either, since the cheapest one costs 57,690 credits on Haiku 4.5, and one median completed offer at 51,000 credits falls short of it too. A full day at the earning cap buys 4 tasks on Sonnet 5 and 1 on Opus 5. On Claude models, Clixad is free only in the sense that you can earn the credits, and a day of earning buys a handful of tasks. The top two rows are where the free part lives: 3 whole tasks a day on GPT-5 Nano and 2 on Gemini 2.5 Flash-Lite, with no earning at all. Whether a cheap model is good enough depends on your code, and trying it costs nothing. Buying credits changes where the balance comes from and nothing else. The smallest pack, $5 for 500,000 credits, buys exactly what a full day at the earning cap does: 4 tasks on Claude Sonnet 5. ## 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. **Work that cheap models can carry.** The daily allowance handles small tasks for free. When a problem needs a frontier model you pay for that one task, 288,450 credits on Claude Opus 5, with no monthly commitment behind it. **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 a second model on a problem the first one 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 Claude Code Anyone who codes all day on Claude models. Anthropic builds its top plan for exactly that reader, in its own words: "The Max plan is built for people who work with Claude throughout the day and want longer, uninterrupted sessions." Our own numbers point the same way. Anthropic's average for enterprise developers paying by the token is around $13 per active day. Our whole daily earning cap is 500,000 credits, which is $5 of list value, less than half of that average day, and reaching it takes several completed offers. Buying credits from us does not close the gap cheaply either. Bought credits pay for tokens at provider cost with our margin on top, a 1.5 markup that [the funding post](https://clixad.io/blog/how-clixad-is-funded/) sets out. Anthropic's own per-token average of $150-250 per developer per month already sits above the $100 at which Max starts, and our route is per token with a markup added. Claude Code also does more than we do. Its documentation covers hooks, skills, plugins and agent teams, and Clixad has none of them. If those are part of how you work, stay with Claude Code. Other free agents exist, and they are built differently from ours. [FreeBuff](https://clixad.io/blog/freebuff-alternative/) grants a daily allowance of hours on its own model picker, and [the shortlist of agents that include model access](https://clixad.io/blog/free-ai-coding-agent-no-api-key/) covers the rest. If your work leans on OpenAI's models, [the Codex comparison](https://clixad.io/blog/free-codex-cli-alternative/) runs the same numbers against ChatGPT's plans. ## FAQ ## ### Is there a free version of Claude Code? No. Anthropic's pricing page lists Claude Code as not included on the Free plan and includes it from Pro upward, at $20 a month billed monthly or $17 a month billed annually. The same page says Claude Code shares one usage pool with the rest of the plan. You can also run Claude Code on pay-as-you-go API credits through a Console account, which costs whatever the tokens cost. Nothing in Anthropic's own offer gives you Claude Code at no charge. ## ### Can I use Claude Code with Clixad credits? No. Anthropic's gateway guide says a gateway must expose Anthropic's Messages format or one of two cloud-provider formats for Claude Code to use it, and our gateway speaks the OpenAI-compatible chat format only. The same documentation says Anthropic does not support routing Claude Code to non-Claude models through any gateway. What you can do is run Claude models inside Clixad's own terminal agent, on the same credits as every other model in the catalogue. ## ### Does Clixad's free tier include Claude models? No. The free allowance of 12,000 credits a day covers five cheap models, and none of them is a Claude model. On Claude models you spend credits: one twelve-call agent task costs 115,380 credits on Claude Sonnet 5 and 288,450 on Claude Opus 5. A full day at our earning cap of 500,000 credits covers 4 tasks on Sonnet 5 and 1 on Opus 5, and the 25,000-credit signup bonus does not cover a single Claude task. ## ### Should I switch from Claude Code to Clixad? Not if you use Claude Code every working day. Anthropic's own average for enterprise developers paying by the token is around $13 per active day, and our whole daily earning cap is 500,000 credits, which is $5 of list value. A full-time day does not fit inside what Clixad grants, and credits bought from us cost provider rates plus our margin. Clixad suits someone who codes a few times a week and wants no subscription, and who can do most of the work on cheap models and pay for a frontier model when a problem needs one. ## Sources 1. Anthropic, [Plans & Pricing](https://claude.com/pricing) , for the plan prices, Claude Code listed as "No" on Free and "Yes" from Pro, "5x or 20x the usage of Pro per 5-hour session", "Claude Code is included in all paid plans. It shares the same usage limits as the rest of your plan, so your work in the terminal and your chats draw from one pool.", "so there's no fixed message count", the Console account as the pay-as-you-go route, and "The Max plan is built for people who work with Claude throughout the day and want longer, uninterrupted sessions." Read 18 September 2026. 2. Anthropic, [Claude Code: manage costs effectively](https://code.claude.com/docs/en/costs) , for "Across enterprise deployments, the average cost is around $13 per developer per active day and $150-250 per developer per month, with costs remaining below $30 per active day for 90% of users." and for Claude Code's hooks, skills, plugins and agent teams. Read 18 September 2026. 3. Anthropic, [Other LLM gateways](https://code.claude.com/docs/en/llm-gateway) , for Anthropic not supporting routing Claude Code to non-Claude models through any gateway, and[Claude Code gateway compatibility guide](https://code.claude.com/docs/en/llm-gateway-protocol) , for "A gateway must expose at least one of the following API formats to Claude Code clients." and the three formats it lists. Read 18 September 2026. 4. Anthropic, [Connect Claude Code to tools via MCP](https://code.claude.com/docs/en/mcp) , for project-scoped servers stored in a`.mcp.json` file at the project root under an`mcpServers` key. Read 18 September 2026. 5. Per-task credit figures: Clixad's own pricing engine, `packages/pricing` , over the model catalogue read from OpenRouter on 26 July 2026, recomputed by the test beside this post. The twelve-call task shape is read from the`#session` table of[the tier-limits post](https://clixad.io/blog/free-ai-coding-tier-limits/) so the two pages cannot drift. 6. Credit rate, signup bonus, earning cap, free allowance and credit packs: `packages/pricing` (`creditUsd` ,`signupBonusCredits` ,`maxAdRewardUsdPerDay` ,`freeTierDailyCreditsPerUser` ,`FREE_MODEL_IDS` ,`CREDIT_PACKS` ). That credits do not expire: section 6 of our[terms](https://clixad.io/terms.html) . Which instruction files and MCP config Clixad reads:`apps/cli/src/context.ts` and`apps/cli/src/mcp.ts` . 7. Offer payouts: completed CPX offers as recorded in Clixad's own ledger, credited between 27 July 2026 and 12 September 2026 and read on 14 September 2026, held as `CPX_COMPLETIONS` in`packages/pricing` .