Free
Individual
Free
VerifiedClaude chat only. Claude Code is not included.
Do not plan a coding workflow on the free plan.
A decision for a beginner, not a spec sheet. Scores are our weights. Prices are the public plans, and anything marked verify on the tool page should be re-checked before you pay.
Pick Claude Code if you want an agent in the terminal on an existing repo.
Pick Replit if you are learning by building a web app, script, or simple browser game in one place.
A terminal coding agent that shares your Claude plan.
Cheapest verified paid plan: Pro · $20/mo
A browser IDE and agent, closest thing here to an all-in-one starter.
Cheapest verified paid plan: Core · $20/mo
Web app or SaaS
Mobile app
Game
Website or landing page
Automation or script
No code
I can follow a change
I already develop
Last verified 2026-10-19
Individual
Free
VerifiedClaude chat only. Claude Code is not included.
Do not plan a coding workflow on the free plan.
Individual
$20/mo
Verified$17/mo when billed annually ($200 up front).
Includes Claude Code. At least 5x Free chat usage per five-hour session, plus weekly limits. Shared with claude.ai. No fixed prompt count.
Anthropic's pricing page lists $20 monthly and $17/mo annual.
Individual
$100/mo
Verified5x Pro usage per five-hour session, higher output limits, and a weekly cap. Max also has a separate weekly limit for Fable, and the pricing table caps Fable at 50% of weekly limits. Includes $100/mo of platform API credits that Anthropic says cannot be spent inside Claude Code.
Price is from Anthropic's Max plan help article. The marketing page says Max starts at $100.
Individual
$200/mo
Verified20x Pro usage per five-hour session, plus a separate weekly limit for Fable (50% of weekly limits on the pricing table). Includes $200/mo of platform API credits that do not spend inside Claude Code.
Price is from Anthropic's Max plan help article, which lists Max 20x at $200/mo.
Last verified 2026-10-19
Individual
Free
VerifiedDaily Agent allowance and Free Mode with a daily cap. One published app, listed as 30-day on the Core comparison table. Built-in database. Exact daily credit count is not a single published number.
The 30-day publish window is on the Core plan comparison table. The daily credit count is still not one published number.
Individual
$20/mo
VerifyOn 2026-10-19 the pricing page showed $18/mo billed annually next to $20. The page still mixes the subscription price, the annual rate, and the $20 credit line.
$20 toward more powerful models. The pricing page listed up to 30 hours of Free Mode chat and up to 60 projects on Free Mode. Credits do not roll over.
Core docs list 1 active background task. The pricing page on 2026-10-19 did not print a parallel-task count. The $20 subscription figure is used for matching and marked verify because the page layout mixes it with the annual rate and the credit line.
Individual
$100/mo
VerifyThe pricing page showed $90/mo billed annually on 2026-10-19.
$100 toward more powerful models, more Free Mode usage, up to 15 collaborators, and database rollback up to 28 days. Docs say unused credits roll for two months.
The $100 list price is consistent. The $90 annual rate is marked verify with the rest of this card because the pricing page markup is easy to misread.
A rolling five-hour window, plus weekly limits on paid plans. Chat and Claude Code share one pool.
Wait for the five-hour window or the weekly reset. There is no fixed message count.
Starter keeps a daily cap. Core and Pro Free Mode allowances reset every five hours and also have weekly limits, per Replit's plan docs. Core credits reset each billing cycle and do not roll over. Pro credits roll for two months.
Stay in Free Mode for everyday agent work. Power and Max spend credits and Replit asks before a paid action.
Claude Code Pro and Replit Core are both listed at $20/mo. Replit Core is marked verify.
Claude Code is for developers who want an agent in the terminal on an existing repo, web app and automation work where you already have a project, and people who also want Claude chat and are fine sharing one allowance.
Replit is for learning by building a web app, script, or simple browser game in one place, people who want an IDE without installing one, and a project that needs hosting and a database next to the agent.
Claude Code scores 0 out of 5 for someone who does not want to read code. Replit scores 4 out of 5. Replit has the higher no-code score. Skip it. Claude Code assumes a terminal, a repo, and comfort with commands. Agent can carry a beginner, and you are still looking at an IDE. Expect files.
Claude Code: Free Claude does not include Claude Code. You need Pro or Max before this tool exists for you. Replit: Daily Agent credits and Free Mode with a daily cap, a built-in database, and one published project. The pricing page does not state one universal credit number.