As of October 2026, Cursor costs $0 (Free), $8 a month (Plus), $30 (Premium), $100 (Super) or $200 (Ultra), with Teams seats at $30, $100 or $200 per seat per month and custom Enterprise pricing. Every paid plan includes a weekly usage pool for Cursor's own models, while third-party models like Claude and GPT are billed separately at API list price.
That structure is new. Cursor is now sold as part of what its docs call "The X Subscription, one subscription for Grok, Cursor, and X," so the plan names and the way usage works changed from the old Pro and Pro+ plans. This guide covers both, based on cursor.com/pricing, the Models & Pricing docs and the pricing help page, all read on 24 October 2026. Prices can change, so check those pages before you buy.
What are Cursor's plans and prices?
| Plan | Price (monthly) | Annual | Included usage | Third-party models |
|---|---|---|---|---|
| Free | $0 | Limited | Not available | |
| Plus | $8/mo | $80/yr | Base | Not available |
| Premium | $30/mo | $300/yr | 4x Plus | API list price, from prepaid credit |
| Super | $100/mo | $1,000/yr | 15x Plus | API list price, from prepaid credit |
| Ultra | $200/mo | $2,000/yr | 50x Plus | API list price, from prepaid credit |
| Teams | $30, $100 or $200 per seat/mo | Matches the seat's tier | API list price plus the Cursor Token Rate | |
| Enterprise | Custom | Pooled | API list price plus the Cursor Token Rate |
Prices exclude tax. The pricing page also says to cancel "at least 24 hours prior to renewal to avoid additional charges," and that self-serve plans take credit and debit cards, with invoices and wire transfers reserved for Enterprise.
What does each Cursor plan include?
The docs describe each tier as building on the one below it:
- Free: Agent and Chat with limited usage. The help page adds that Free includes Tab completions with Cursor models, and the Tab troubleshooting page notes that Free users have a limited Tab allowance.
- Plus: Agent with Cursor's own models (Grok 4.7, Grok 4.6, Grok 4.5 and Composer 2.5) at fixed settings: Fast is off, effort is medium, and Grok 4.7 uses the 256k context window. There is no Auto, Cloud Agents, Automations, Bugbot, Origin, third-party models or your own API keys.
- Premium: 4x the Plus usage, plus Cloud Agents and Automations, code hosting on Origin, code review with Bugbot, third-party models at API list price and Grok Bot.
- Super: 15x Plus usage and priority model access at peak times.
- Ultra: 50x Plus usage and earliest access to new products and models.
Cursor's own recommendation, from the pricing FAQ: "We recommend Premium for new AI users, Super for daily agent users, and Ultra for power users." Plus is pitched at people with light AI usage, so most developers who want Cursor as a coding agent start at Premium.
How does the weekly usage pool work?
Each paid plan includes one pool of usage for Cursor models. The pool is shared across Agent in the editor, the Cursor CLI, Cloud Agents, Grok Bot and the Grok apps. In the words of the pricing page: "Your allowance refreshes weekly, so one heavy day never wipes out your whole month."
A few details from the docs matter in practice:
- Different models draw from the pool at different rates, so model choice changes how long it lasts.
- Your remaining usage and next reset date show in editor settings and under Usage at grok.com/dashboard.
- Unused included usage does not roll over.
- Auto on individual plans runs in Cost mode, which "bills as a Cursor-model request and draws from your included pool whatever model serves it."
When the pool runs out, you can wait for the weekly reset, pay from prepaid credit or upgrade. The docs state: "Requests are never downgraded in quality or speed."
How much do Claude, GPT and other models cost in Cursor?
Third-party models are not part of the included pool. On Premium and above, they are billed at the model's API list price from the first request, paid from prepaid credit. The same per-token rates apply when you go past your weekly pool on Cursor's own models.
A few rows from the Models & Pricing table, per million tokens, as of October 2026:
| Model | Input | Cache read | Output |
|---|---|---|---|
| Composer 2.5 | $0.5 | $0.2 | $2.5 |
| Grok 4.7 | $2 | $0.5 | $6 |
| Claude Sonnet 5.5 | $2 | $0.1 | $10 |
| Claude Opus 5.5 | $4 | $0.2 | $20 |
| GPT-5.6 Terra | $2 | $0.2 | $12 |
| Gemini 3.1 Pro | $2 | $0.2 | $12 |
The full table lists many more models, along with notes on long context, Fast mode and cache writes. Opting in to regional data residency adds a 10% uplift on eligible models.
How do top-ups and spending caps work?
Top-ups add prepaid credit to your subscription. You can buy credit whenever you like or turn on Auto Top-up to refill when your balance drops below a threshold. A monthly additional usage limit caps paid additional usage each month, however much credit you hold. All three live under Additional usage credits at grok.com/dashboard/billing.
The usage limits help page says credit lasts "until used or until it expires (currently 365 days after purchase)." On individual plans, requests made with your own API key are billed by your provider and do not count against included usage or credit.
How is Cursor priced for teams?
Teams are priced per seat. Each member gets a Premium, Super or Ultra seat at the same price and weekly usage as the matching individual plan, and you can mix tiers on one team. Plus is not available for teams.
Team plans add centralized billing, a team marketplace for internal rules, skills and plugins, usage analytics, team-wide privacy mode enforcement, custom Chat data retention and SAML/OIDC SSO. Admins manage one shared prepaid balance and one cap for the whole team. Enterprise adds pooled usage, invoicing, SCIM, granular spend controls and advanced security controls.
Teams and Enterprise also pay the Cursor Token Rate: $0.25 per million tokens on eligible third-party model requests, including bring-your-own-key requests. The team pricing docs say it covers "Custom model execution (Tab, Apply, etc.)" and infrastructure costs. Cursor models, Cost mode requests and a list of lightweight models are exempt.
What happened to Cursor Pro, Pro+ and Hobby?
They are now legacy Cursor plans. Existing subscribers keep them, and switching to The X Subscription is optional but permanent. The legacy plans page maps them like this:
| Legacy plan | Price | Comparable current plan |
|---|---|---|
| Hobby | Free | Free |
| Pro | $20/mo | Premium ($30/mo) |
| Pro+ | $60/mo | Super ($100/mo) |
| Ultra | $200/mo | Ultra ($200/mo) |
| Teams Standard | $40/user/mo | Teams, Premium seat ($30/user/mo) |
| Teams Premium | $120/user/mo | Teams, Super seat ($100/user/mo) |
Legacy plans work differently. They include two monthly pools, Cursor Models and Other Models, so Pro, Pro+, Ultra and Teams get an included allowance for third-party models. Extra usage is on-demand and billed in arrears, and Pro, Pro+ and Ultra include unlimited Tab completions.
Cursor says each current paid plan "includes at least twice as much coding usage with Cursor models as the legacy plan it replaces," but it also drops the included third-party allowance. If you mostly use Claude or GPT models today, compare both before you switch. Max Mode, which extends a model's context window, is available only on legacy request-based plans.
How much does Bugbot cost?
Bugbot code review moved to usage-based billing in 2026. Cursor's Bugbot billing help page says "The average Bugbot run costs between $1.00 and $1.50, depending on PR size and complexity." On individual plans, reviews draw from included usage first, then from prepaid credit. Bugbot is not part of Plus. The Cursor Bugbot guide covers setup and settings.
How do you pick a Cursor plan?
Start from how you work:
- Occasional autocomplete and chat: Free is enough to try Tab and Agent.
- Cursor models only, light use: Plus, if you do not need Bugbot, Cloud Agents or Claude and GPT models.
- Daily coding with an agent: Premium, then move to Super if you hit the weekly pool often.
- Heavy third-party model use: budget for prepaid credit on top of the plan, since those tokens are billed at list price.
- A team: Teams seats, mixing tiers by how much each person uses the agent.
For a comparison with Anthropic's pricing, see the Claude Code pricing guide.
Keep your prompts when you switch tools
Pricing changes are a common reason to move between Cursor, Claude Code and Codex. If your prompts and Agent Skills live as Markdown in a GitHub repo you own, they move with you. Kipt gives you a searchable library over that repo and installs every skill into Claude Code or Codex with one npx skills add command.