by Anysphere, Inc.AI coding assistants
An AI code editor with agents, Tab completions and its own models, sold within The X Subscription; Teams seats from $30 a month.
An editor built around coding agents, with zero data retention with model providers and privacy mode enforced for the team on Teams.
Cursor puts agents, chat and Tab completions in its own editor, CLI and web app, with cloud agents and Bugbot code review from Premium seats. On Teams, at $30 per seat a month, Privacy Mode is enforced for every member, Cursor states zero data retention agreements with its model providers, and SAML SSO is included. Cursor’s terms say it will not use customer data to train models unless the customer explicitly agrees, and its security page lists SOC 2 Type II, ISO 27001 and ISO 42001.
Against 3 other products we reviewed in AI coding assistants: what you pay for with each, the five access facts, the plan limits we recorded and each review's bottom line. The note under the table says how each one was checked.
| Metric | Cursor | GitHub Copilot | Claude Code | JetBrains AI |
|---|---|---|---|---|
| What you're paying for | Saves engineering timeAn editor built around coding agents, with zero data retention with model providers and privacy mode enforced for the team on Teams. | Compliance includedUnlimited completions plus chat and agents on models from several providers, with no training on your code and IP indemnity from $19 a user. | Saves engineering timeA coding agent for the terminal, IDEs and the web, sold with Claude chat on one seat, with no training and IP indemnity on Team. | Worth the priceAI completion, chat and agents inside JetBrains IDEs, with usage at API rates and no surcharge, and free governance for organizations. |
| Overall score | 6.4 | 8.3Best | 5.6 | 5.3 |
| Free option | Free plan | Free plan | Paid only | Free plan |
| Card to start | –Not measured | –Not measured | –Not measured | Card required |
| Getting access | Self-serve | Self-serve | Self-serve | Self-serve |
| Starter priceCheapest paid plan | $8/mo | $10/mo | $20/mo | $10/mo |
| Pricing model | Seat + usage | Seat + usage | Per seat | Seat + usage |
| Pricing page | Public prices | Public prices | Public prices | Public prices |
| Billing unit | Per seat per month; third-party models from prepaid credit at API list price | Per user per month; chat and agent usage in AI credits ($0.01 each) | Per seat per month; extra usage as usage credits at API rates | AI credits ($1 of use each); individual plans per month; governance per seat |
| Free option | Free plan with limited Agent and Chat on Cursor models; Tab on Free not stated | Copilot Free: 2,000 completions a month, limited chat and agent usage | None with Claude Code; the Free plan excludes it | AI Free with a JetBrains IDE licence; 30-day AI Pro trial, card needed |
| Reference scenario (5 developers) | $150/mo on Teams Premium seats ($30 × 5, monthly), computed | $95/mo on Business ($19 × 5, billed monthly), computed | $100/mo on Team Standard seats ($20 × 5, annual), computed | Not priced: no organization plan includes usage (credits bought separately) |
| Included usage (organization plan) | Premium weekly pool per seat (4x Plus); no absolute size stated | 1,900 AI credits ($19) per user a month, pooled; completions unlimited | 1.25x Pro per session per seat, shared with chat; no absolute size stated | None; pooled prepaid credits, 20 per seat with All Products Pack |
| Usage beyond the plan | Prepaid credit at per-token rates, plus $0.25 per million tokens on Teams | Per-token rates in AI credits; on by default for organizations, budgets available | Usage credits at API rates, off until turned on; spend limits | Prepaid credits at API rates, no surcharge; per-user limits |
| Models | Cursor (Grok, Composer), Anthropic, OpenAI and Google models | Anthropic, OpenAI, Google, xAI, Microsoft and Moonshot models on Business | Anthropic only (Fable, Opus, Sonnet, Haiku) | Anthropic, OpenAI and Google models; JetBrains Mellum for completion |
| Training on your code | Not without explicit agreement (terms); Privacy Mode enforced on Teams | Not on Business and Enterprise; Free to Max train unless you opt out | Not on Team and Enterprise by default; Free, Pro and Max opt-out | Not without your agreement (terms), on every tier |
| Data retention | Zero data retention with providers in Privacy Mode, with exceptions | IDE prompts not retained; other surfaces 28 days (Business) | 30 days on Team; zero data retention on qualified Enterprise accounts | Not persisted unless detailed data collection is on; provider retention not stated |
| IP indemnity | In the MSA; plans covered not stated | Business and Enterprise, unmodified suggestions with the filter on | Commercial plans (Team, Enterprise, API), no liability cap | Not offered |
| SSO / SCIM / audit log | SAML SSO on Teams; SCIM and audit log on Enterprise | SAML SSO and audit log listed for Business; SCIM through managed users in an enterprise account | SAML SSO on Team; SCIM and audit logs on Enterprise | SSO listed on Basic; SAML in IDE Services; SCIM coming soon; console audit page |
| SOC 2 / ISO 27001 | SOC 2 Type II, ISO 27001 and ISO 42001 | SOC 2 Type II and ISO 27001 cover Copilot Business and Enterprise | SOC 2 Type II, ISO 27001 and ISO 42001 | SOC 2 Type II covers JetBrains AI; ISO 27001 not listed |
| Editors and surfaces | Cursor app, CLI, web, iOS; JetBrains and Xcode integrations on paid plans | VS Code, Visual Studio, JetBrains, Xcode, Eclipse, Neovim, Zed, CLI, github.com | Terminal, VS Code, JetBrains, desktop, web, iOS and Android, Slack, CI | JetBrains IDEs, Android Studio, JetBrains Air app and web |
| Bottom line | From its public pages, Cursor gives a team an agent-first editor with privacy mode enforced and SSO for $30 a seat. Included usage is stated only as multiples, several pages disagree, and SCIM and the audit log need Enterprise. | From its public pages, Copilot Business puts unlimited completions, $19 of pooled usage per user, a wide model choice and the main enterprise controls on a $19 seat. Set budgets early: extra usage is on by default for organizations. | From its public pages, Claude Code gives a team an agent for the terminal, IDE and web, plus Claude chat, on a $20 annual seat with no-training terms and uncapped IP indemnity. Usage is stated only as multiples, and models are Anthropic-only. | From its public pages, JetBrains AI suits teams in JetBrains IDEs that want unlimited completion and usage at API rates with per-user limits. There is no IP indemnity, no seat with usage included, and several governance features are still coming. |
Evidence: Cursor: facts checked 2026-10-16 from its public sign-up and pricing pages, no completed hands-on run; GitHub Copilot: facts checked 2026-10-16 from its public sign-up and pricing pages, no completed hands-on run; Claude Code: facts checked 2026-10-16 from its public sign-up and pricing pages, no completed hands-on run; JetBrains AI: facts checked 2026-10-16 from its public sign-up and pricing pages, no completed hands-on run. Prices in USD as listed, excluding tax. "–" means not recorded.
Review from public pages
Written from Cursor's public pages (pricing, security or privacy, and docs) as read on Oct 16, 2026. We did not sign up, and no hands-on run is published yet.
We read Cursor's pricing page, its docs and help center on models and pricing, usage limits, overages, spend limits, Teams pricing and members, the dashboard, analytics, privacy and enterprise, its security, data-use and student pages, the Terms of Service, MSA and DPA, and the post on joining SpaceX on Oct 16, 2026; we did not sign up, start a trial or buy a seat. The pricing page showed US dollars. The X Subscription terms page refused our request, so we read its Internet Archive copy of Oct 13, 2026.
Cursor is now sold as part of The X Subscription, one bundle covering Grok, Cursor and X, through X Subscription Corp; the earlier Pro, Pro+ and Teams Standard plans are legacy. Each paid plan has a weekly pool for Cursor's own models (Grok and Composer), shared with the Grok apps and sized as a multiple of Plus (Premium 4x, Super 15x, Ultra 50x). Third-party models are paid from prepaid credit at API list price.
Several pages disagree. The Teams page says each seat includes at least $20 a month of agent usage, while the docs say a seat matches the individual weekly pool; one help article puts SCIM on Teams, while the pricing table and SSO help put it on Enterprise; the Teams docs describe per-member spend limits that the pricing table lists as Enterprise only; and the dashboard and analytics docs disagree on whether the Admin API is on Teams. The annual price for Teams seats is not stated.
Teams enforces Privacy Mode for every member, and Cursor states zero data retention agreements with all model providers when it is on, with exceptions for Claude Fable models and your own keys.
vs Claude Code: Claude Code offers zero data retention only to qualified Enterprise accounts through sales; Copilot keeps non-IDE prompts for 28 days.
SSO with SAML 2.0 is included at no extra cost on Teams and Enterprise, and Teams is bought online by card.
Premium and higher seats can use Anthropic, OpenAI and Google models at API list price from prepaid credit, alongside Cursor’s own Grok and Composer models in the weekly pool.
vs Claude Code: Claude Code runs Anthropic models only; Gemini Code Assist runs Google models only.
The security page lists SOC 2 Type II, ISO 27001, ISO 42001 and AIUC-1, and Cursor signs HIPAA BAAs for Enterprise customers.
Compared: JetBrains lists SOC 2 Type II but no ISO 27001.
The weekly pool is given as multiples of Plus (Premium 4x, Super 15x, Ultra 50x) with no absolute size, and the Teams page’s "at least $20 a month" differs from the docs.
Workaround: Set a team spend limit and watch the usage dashboard during the first weeks.
The pricing table and SSO help put SCIM and the audit log on Enterprise, priced through sales; model access controls and repository blocklists are Enterprise-only too.
Subscriptions are sold by X Subscription Corp as part of The X Subscription, with Grok and X perks. The bundle terms make payments and top-ups final, apart from statutory cancellation rights for consumers in some regions, such as 14 days in the EEA, UK and Switzerland.
Legacy plans included unlimited Tab completions; for current plans the pages do not say whether Tab is unlimited or draws on the weekly pool.
Cursor bills each seat per month. For our scenario, 5 developers on Teams with Premium seats cost 5 × $30 = $150 a month ($1,800 a year, computed); the docs publish annual prices for individual plans ($300 a year for Premium) but not for Teams seats. Each seat gets the Premium weekly pool for Cursor models, not shared between seats. Third-party models are paid from prepaid credit at API list price, for example $4 in and $20 out per million tokens for Claude Opus 5.5, plus $0.25 per million tokens on Teams; top-ups expire after 365 days. Super ($100) and Ultra ($200) seats raise the pool to 3.75x and 12.5x Premium. Pooled usage, SCIM and the audit log need Enterprise, priced by sales.
Code stays in your repositories: Cursor's search docs say it does not upload code to build an index or store embeddings. Teams can download analytics as CSV; exporting chat history is not described. Cancelling moves the account to Free, account deletion removes data within 30 days, and under the MSA data can be downloaded for 30 days after termination.
From its public pages, Cursor gives a team an agent-first editor with privacy mode enforced and SSO for $30 a seat. Included usage is stated only as multiples, several pages disagree, and SCIM and the audit log need Enterprise.
| Limit | As recorded |
|---|---|
| Billing unit | Per seat per month; third-party models from prepaid credit at API list price |
| Free option | Free plan with limited Agent and Chat on Cursor models; Tab on Free not stated |
| Reference scenario (5 developers) | $150/mo on Teams Premium seats ($30 × 5, monthly), computed |
| Included usage (organization plan) | Premium weekly pool per seat (4x Plus); no absolute size stated |
| Usage beyond the plan | Prepaid credit at per-token rates, plus $0.25 per million tokens on Teams |
| Models | Cursor (Grok, Composer), Anthropic, OpenAI and Google models |
| Training on your code | Not without explicit agreement (terms); Privacy Mode enforced on Teams |
| Data retention | Zero data retention with providers in Privacy Mode, with exceptions |
| IP indemnity | In the MSA; plans covered not stated |
| SSO / SCIM / audit log | SAML SSO on Teams; SCIM and audit log on Enterprise |
| SOC 2 / ISO 27001 | SOC 2 Type II, ISO 27001 and ISO 42001 |
| Editors and surfaces | Cursor app, CLI, web, iOS; JetBrains and Xcode integrations on paid plans |
Read from the vendor's public pages on Oct 16, 2026. No hands-on run is published yet. How we check
We have not published a sign-up run for Cursor yet. The access facts above were read from its sign-up and pricing pages on Oct 16, 2026.
We have not published API calls for Cursor yet.
Cursor lists 6 plans. The cheapest paid plan, Plus (individual), costs $8/mo.
Prices as listed, USD, excluding tax; observed 2026-10-16.
Source: cursor.com pricing page. Prices change; the observed date above is when our agent read them.
We read the pricing, docs, trust and legal pages of three AI coding assistants on the same day and scored them on the same six indicators. What 5 developers cost, how usage is counted, what the terms say about your code, and who should pick which.
