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 Cursor if you want a web app or SaaS you will keep editing in a repo.
Pick OpenAI Codex if you already pay for ChatGPT and want the coding agent in that allowance.
An editor with agents, built for people who can read a diff.
Cheapest verified paid plan: Plus · $8/mo
A coding agent included with ChatGPT, not a separate app subscription.
Cheapest verified paid plan: Plus · $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
VerifiedLimited Agent and Chat requests, and Tab completions on Cursor models (Grok and Composer). No published request count. Third-party models are not available.
The current free plan on cursor.com/pricing. Legacy Hobby is the same kind of limited trial for older accounts.
Individual
$8/mo
VerifiedAnnual is $80/yr on Cursor's pricing docs.
Base weekly pool for Cursor models (Grok 4.7, Grok 4.6, Grok 4.5, and Composer 2.5), shared with Grok. Fast is off and effort is medium. No Auto, Cloud Agents, third-party models, or your own API keys. The pool size is not published as a prompt count.
The entry paid plan. Cursor recommends Premium, not Plus, for new agent users.
Individual
$30/mo
VerifiedAnnual is $300/yr on Cursor's pricing docs.
4x Plus usage of the weekly Cursor-model pool. Adds Cloud Agents, Automations, Origin, Bugbot, and third-party models at API list price from prepaid credit. Third-party models are not included in the $30.
Cursor's pricing page calls this the plan for new AI users.
Individual
$100/mo
VerifiedAnnual is $1,000/yr on Cursor's pricing docs.
15x Plus usage, plus priority model access at peak times. Third-party models bill the same way as on Premium.
The plan Cursor points daily agent users to.
Individual
$200/mo
VerifiedAnnual is $2,000/yr on Cursor's pricing docs.
50x Plus usage, plus earliest access to new products and models. Third-party models bill the same way as on Premium.
For several agents or automations, not a first plan.
Individual
Free
VerifiedAgent, Chat, and Tab with limited usage. No Cloud Agents, Bugbot, or Origin. No on-demand usage. No published request count.
The free plan from before The X Subscription. Not sold to new customers. Left out of budget matching so it does not duplicate Free.
Individual
₹649/mo, tax inclusive
VerifiedCursor Models pool only. No Other Models pool. Fast mode and effort controls are off. No on-demand usage.
Legacy regional plan. The legacy plans page still lists ₹649/mo, tax inclusive. Left out of US-dollar budget matching.
Individual
$20/mo
VerifyTwo monthly pools: Cursor Models and Other Models. Older help text listed $20 of included Other Models usage. The current legacy plans page no longer prints that dollar amount. Unlimited Tab. On-demand after the pools, if you turn it on.
Not sold to new customers. The $20 price is on the legacy plans page. The included Other Models dollar amount is no longer published, so this row stays Verify and does not count toward the budget.
Individual
$60/mo
VerifySame two monthly pools as legacy Pro, with more of each pool. Older help text listed $70 of included Other Models usage. The current legacy plans page no longer prints that dollar amount.
Not sold to new customers. The $60 price is published. The $70 pool figure is not, so this row stays Verify.
Individual
$200/mo
VerifySame two monthly pools, with more of each than legacy Pro+. Older help text listed $400 of included Other Models usage. The current legacy plans page no longer prints that dollar amount.
Not sold to new customers. The $200 price is published. The $400 pool figure is not, so this row stays Verify. New customers buy Ultra on The X Subscription instead.
Last verified 2026-10-19
Individual
Free
VerifiedLimited trial access to Codex and limited access to GPT-5.6. Codex pricing docs also list GPT-6 Luna at Standard speed in the desktop app, subject to rollout. No published prompt count.
Confirmed on the Codex pricing page as a limited trial. GPT-6 Luna on Free is listed as subject to rollout, so it is not treated as a guarantee.
Individual
Confirm on chatgpt.com/pricing
VerifyLimited Codex, above Free. Codex pricing docs at learn.chatgpt.com/docs/pricing list Go at $8/mo. chatgpt.com/pricing still did not print a dollar amount on 2026-10-19.
Left out of budget matching. The $8 figure is on a Codex pricing doc, and the live ChatGPT pricing page still does not show it.
Individual
$20/mo
VerifiedExpanded Codex for a few focused sessions a week. Codex app on macOS and Windows. Local and cloud usage share the allowance. Weekly limits may apply. GPT-6 Astra access is limited, with credits for more.
Plus is $20/mo on OpenAI's help center. Annual billing is not offered.
Individual
$100/mo
VerifiedHigher Codex allowance for longer daily sessions. GPT-6 Astra is included in the allowance. Ultrafast is not included.
From OpenAI's Pro tiers help article.
Individual
$200/mo
VerifiedMore included usage than Pro 100. Ultrafast is not included. New subscriptions may have a lower allowance than older Pro 200 accounts.
OpenAI says the monthly price remains $200.
Individual
$500/mo
VerifiedHighest included Pro usage. Ultrafast for GPT-6 Astra and GPT-6.1 Sol is included and draws the included allowance at 8× the Standard rate for that model.
Ultrafast is only on this Pro tier. The 8× rate is from OpenAI's Pro tiers help article.
On The X Subscription the included pool refreshes weekly, and unused included usage does not roll over. Legacy Cursor plans reset monthly with the billing cycle.
On a paid X Subscription plan, add prepaid credit or wait for the weekly reset. Third-party models on Premium and above are paid from that credit from the first request.
Plan allowance, with weekly limits that may also apply. Local messages and cloud chats share it. OpenAI does not publish one universal reset clock.
Switch to a lower-cost model. OpenAI says that stretches the same allowance.
Cursor's cheapest paid plan the ranking counts is Plus at $8/mo. OpenAI Codex's cheapest paid plan the ranking counts is Plus at $20/mo.
Cursor is for a web app or SaaS you will keep editing in a repo, scripts and automations next to existing code, and people who can follow a diff even if they did not write it.
OpenAI Codex is for developers who already pay for ChatGPT and want the coding agent in that allowance, web apps and automations with local and cloud tasks, and a few focused coding sessions a week on Plus.
Cursor scores 1 out of 5 for someone who does not want to read code. OpenAI Codex scores 1 out of 5. The scores are the same. You will be reading diffs. If code on screen is a dealbreaker, use a browser builder. You are still in a coding agent. This is a poor pick if you never want to see a file.
Cursor: Free includes limited Agent and Chat, plus Tab completions on Cursor's own models. Cursor does not publish a request count. OpenAI Codex: Free includes a limited Codex trial. OpenAI does not publish a fixed prompt count. It is enough to see the product, not to build through the month.