Finding out whether the editor suits you
Plus
You have used VS Code for years and want to know whether the agent and the autocomplete are worth changing editors for.
$8/mo
$7/mo billed annually
Start on the Free tier, not on this row: it carries the agent with limited usage and costs nothing. When its unnumbered limit stops you, Plus is the cheapest paid tier, and it is worth knowing what it leaves out. It runs Cursor's own models only, at fixed settings, with no Auto, no third-party models and no key of your own, so it tests the editor more than a frontier model. Pay monthly while you decide: all payments are final under the new terms, so an annual plan bought to try things out is a year you keep.
A full working day with the agent
Super
The agent is open most of the day, on a frontier model, doing real edits rather than answering questions.
$100/mo
$84/mo billed annually
The vendor's own recommendation for daily agent users, and the row where the October reshuffle moved the most. The legacy table maps the old middle tier here, at a higher price than that plan had, and in exchange the vendor says each new tier carries at least twice the coding usage with Cursor models. What went the other way is the included allowance for Claude, GPT and Gemini. If your day runs on those models the pool does not help: they bill from prepaid credit at list price from the first request.
Several agents at once, or cloud agents overnight
Ultra
You run parallel agents, automations or cloud agents that keep working while you are away from the keyboard.
$200/mo
$167/mo billed annually
50x the Plus pool, and the top of the ladder. Cloud Agents and Automations draw on the same weekly pool as the editor, the CLI, Grok Bot and the Grok apps, so a night of agents is spent from the budget you use by day. Past the pool, usage comes from prepaid credit under a monthly additional-usage limit you set, and that limit is the real ceiling. Check which variant is selected, too: Composer 2.5 runs in its fast variant by default, at six times its standard rate.
A team of eight
Teams
A small engineering team wants central billing, SSO and shared rules without a sales process.
$30/seat/mo
Self-serve per seat, and seats can be mixed: Premium for most people, Super or Ultra for those who hit the ceiling. Three things to settle on day one. Each seat has its own weekly pool that teammates cannot share, while everything past it comes from one shared prepaid balance, so set the monthly additional-usage limit before anyone runs an agent overnight; when the balance or the limit runs out, paid usage stops for the whole team. Eligible third-party requests carry the per-token platform fee printed in the table, even on your own key. And Grok Bot is enabled for every member with no switch to turn it off.
An organisation with procurement and a security review
Enterprise
You need invoicing, pooled usage, SCIM, audit logs and a contract your legal team has read.
Custom
The only route with pooled usage, and the only one whose price is not published. Read the Pricing Policy before the order form: precommitted usage does not roll over and is invoiced if unused at the end of the term, seats are trued up against everyone who logged in during the last thirty days of each period, and by default the policy lets the vendor name you as a customer in its marketing. Privacy Mode is on by default here.
You already pay a model provider
Your own API key
You hold an Anthropic, OpenAI or Google key with committed spend or credits, and want Cursor's editor on top of it.
At model rates
This works from Premium up; Plus excludes it. On an individual tier your provider bills the tokens and nothing is drawn from the pool. Three limits apply. Keys cover chat models only, so Tab still runs on Cursor's models. Requests still pass through Cursor's backend, and its zero-retention agreements do not cover them. And on Teams and Enterprise eligible requests carry the platform fee even though the tokens are yours.