AI / Coding & Developer Tools / Anysphere

Cursor

AI code editor and coding-agent workspace with Tab completion, inline edits, repository tools and cloud-agent workflows.

AI Code EditorCoding AgentCode CompletionDebuggingCode ReviewDevelopment Automation

AI Code EditorCompare this model Visit website

Price

Free $0/month · Plus $8/month ($80/year prepaid) · Premium $30/month ($300/year prepaid). USD; taxes and third-party model usage are extra. · Free: Free plan offers limited Agent/Chat usage. A standard trial duration is not disclosed on the current new-plan pricing page; legacy-plan offers may differ. · Paid: New monthly plans: Plus $8 · Premium $30 · Super $100 · Ultra $200. Annual prepaid totals: $80 / $300 / $1,000 / $2,000 respectively. Teams seats: $30, $100 or $200/month; Enterprise custom. Third-party model charges are extra; legacy plans retain their own terms. · Limits: New paid plans use a weekly Cursor-model pool shared across Cursor/Grok surfaces. Premium+ third-party models use prepaid credit at API list prices; Teams/Enterprise add a Cursor Token Rate. Legacy plans retain separate monthly pools.

Specialization

AI Code Editor · Coding Agent · Code Completion · Debugging · Code Review · Development Automation

Quality

Offers Tab suggestions, code diffs, checkpoints and test/browser tools for checking changes. Output quality depends on the selected model and project context. Belliste has not run a comparative benchmark for this profile.

Features

Cursor Tab code completion · Cmd/Ctrl+K inline editing · Multi-file coding agents · Plan Mode and Debug Mode · Terminal commands and test execution · Browser interaction and visual verification · Background and cloud agents · Parallel subagents · Project, user and team rules · MCP and external integrations · Bugbot code review on eligible plans · Self-hosted tool execution and SDK automation

About Cursor

Cursor combines an AI code editor with local and cloud coding agents. Developers can use Tab suggestions, targeted inline edits, planning, debugging and browser tools, with rules and MCP integrations for project workflows. Current new subscriptions differ from legacy Pro/Pro+ plans: included model pools, third-party billing and feature eligibility must be checked separately. Self-Hosted Machines move tool execution to user hardware while keeping the agent loop in Cursor’s cloud. Belliste has not independently benchmarked coding performance. Official sources were reviewed on October 19, 2026.

Specifications

Overview & Compatibility

9 specifications

Starting Price	Free $0/month · Plus $8/month ($80/year prepaid) · Premium $30/month ($300/year prepaid). USD; taxes and third-party model usage are extra.
Tool Type	AI Code Editor / Coding Agent / IDE Assistant; includes desktop editing, agent workflows and a terminal CLI.
Primary Use Case	Write and change application code, explore repositories, fix bugs and automate development tasks.
Best For	Developers and engineering teams wanting inline coding assistance, repository agents and cloud task workflows.
Access Methods	Desktop editor/Agents Window · CLI · Web and mobile Cloud Agents · JetBrains/Xcode integrations. Feature availability varies by surface and plan.
Supported Operating Systems	Desktop: Windows, macOS and Linux, with architecture-specific downloads. CLI installation and sandbox support differ by platform.
Supported IDEs & Editors	Cursor desktop editor; agent integrations for JetBrains and Xcode. CLI runs in a terminal; editor extensions and integration capabilities vary.
Programming Languages	Works across source languages using editor context and project tools. Completion quality and agent capabilities vary; no exhaustive equal-support guarantee is disclosed.
Framework Support

Code Completion	Cursor Tab provides as-you-type code suggestions, multi-line edits and next-edit predictions. Availability and limits depend on the current plan.
Code Generation	Agent creates and edits code files from natural-language instructions using project context.
Inline Code Editing	Select code and use Cmd/Ctrl+K for a targeted edit in place; follow-up instructions refine the selected change.
Multi-File Editing	Agent coordinates edits across files; selected inline-edit context can be handed to Agent for larger changes.
Code Explanation	Ask Agent about repository code, or use inline question mode on a selected block.
Refactoring	Can restructure selected code or perform repository-wide refactoring; checkpoints support restoring file changes.
Debugging Assistance	Debug Mode instruments code, guides reproduction, analyzes runtime logs and proposes a targeted fix, followed by verification and cleanup.
Test Generation	Agent can write tests for requested behavior using the repository’s testing framework and accessible source files.
Documentation Generation	Agent can create or update project documentation and comments from code context and instructions; shared rules can define conventions.
Code Review	On-demand Agent review plus Bugbot PR review. Current Premium and higher include Bugbot access; connected repositories, permissions and usage conditions apply.
Image-to-Code	Vision-capable models accept image files as context; use a mockup or screenshot to guide code generation and UI changes.

Agent Mode & Planning	Agent can execute multi-step tasks; Plan Mode supports researching a change and reviewing the implementation plan before building.
Terminal Command Execution	Runs terminal commands and monitors output. Run Modes, allowlists and sandbox policy determine execution and approval behavior.
Automated Test Execution	Can invoke installed tests and build tools, inspect failures and iterate on changes; dependencies and test infrastructure must be available.
Browser Interaction	Integrated browser tools navigate pages, interact with UI, capture screenshots and help test applications or verify visual changes.
Background / Cloud Agents	Cloud Agents run remotely and can be followed from web/mobile; current new-plan access starts at Premium. Local background work depends on its host.
Parallel Agent Tasks	Supports concurrent subagents and background workstreams; cloud subagents can use separate VMs and branches while the parent continues.
Human Approval Controls	Auto-review, Allowlist and Run Everything modes control tool autonomy. Configurable approval policies and team rules apply to shell, MCP and Fetch calls.
Execution Isolation / Sandbox	Supported shell commands can run with filesystem/network limits; documented local sandbox implementations cover macOS and Linux. Some calls run outside the sandbox. Managed Cloud Agents use isolated VMs.
Execution Environment	Both: local desktop/CLI tool execution and remote Cloud Agents. Self-hosted machines run tools locally while the Cloud Agent loop stays in Cursor’s cloud.

Supported AI Models	Current catalog includes Grok 4.7/4.6/4.5 and Composer 2.5; third-party options include Claude 5.5/Fable 5.1, Gemini and GPT-5.6 variants. Access varies by plan; new plans bill third-party models separately.
Model Selection	Manual model picker plus Auto routing where eligible. Plus uses fixed settings and has no Auto; effort, speed and model controls depend on plan.
Bring Your Own API Key	BYOK for supported providers, including OpenAI, Anthropic, Google, Azure and Bedrock. New Plus excludes BYOK; eligible individual and team plans have different billing. Tab still uses Cursor models.
Local Model Support	Official local-model inference support is not disclosed. BYOK targets supported provider services and requests still pass through Cursor’s backend. Self-hosted tool execution is a separate feature.
Codebase Context & Indexing	Agent reads repository files and searches code. Current Instant Grep builds and queries its index locally; opened file content can still enter model requests.
Context Window	Varies by model and plan. New Plus fixes Grok 4.7 at 256K tokens. Other models have separate limits; legacy Max Mode has different eligibility and billing.
Custom Instructions / Rules	Project rules in .cursor/rules, global user rules, team-managed rules and AGENTS.md guide behavior. Rule scope and version requirements apply.
Persistent Project Memory	Persistent guidance is available through saved project/user/team rules. Current documentation does not establish a separate generally available automatic project-memory feature; rules should not be treated as learned memory.

Git & Pull Requests	Git workflows and connected repository/PR operations; Cloud Agents can work on branches and prepare PRs. Git-provider support and permissions vary by integration.
MCP & External Integrations	MCP connects external tools and data. Documented integrations include GitHub, GitLab, Azure DevOps, Bitbucket, Slack, Teams, Jira, Linear and Notion.
Web Search	Agent can generate search queries and search the web for documentation and development context. Network and run-mode policies apply.
API / SDK Access	Cursor SDKs support TypeScript and Python; documented APIs control agents and integrate workflows. Headless CLI supports scripts and CI. This is separate from a general-purpose model API.
Deployment Support	Agent can run configured deployment commands and connected tools with approval. Deployment accounts, hosting services and infrastructure costs remain provider-specific.

Free Plan / Trial	Free plan offers limited Agent/Chat usage. A standard trial duration is not disclosed on the current new-plan pricing page; legacy-plan offers may differ.
Usage Limits / Extra Usage	New paid plans use a weekly Cursor-model pool shared across Cursor/Grok surfaces. Premium+ third-party models use prepaid credit at API list prices; Teams/Enterprise add a Cursor Token Rate. Legacy plans retain separate monthly pools.
Team Administration	Teams/Enterprise offer centralized billing, usage analytics, shared rules/plugins and privacy enforcement. Enterprise adds pooled usage, audit/access controls and advanced administration.
Code Privacy & Data Retention	AI prompts and code context are processed by Cursor/providers. Privacy Mode prevents training, with retention exceptions for abuse checks, opt-in non-ZDR models and BYOK. No single retention duration applies to every surface.
Self-Hosting	Self-Hosted Machines execute tools on user-controlled hardware; Team Pools support enterprise fleets. The agent loop remains in Cursor’s cloud, so this is not a fully offline/self-hosted product.
SSO / Enterprise Security	Teams/Enterprise list SAML/OIDC SSO. Cursor lists SOC 2 Type II and other security certifications; Enterprise adds audit/model controls and customer-managed keys for Cloud Agent data.

Cursor

About Cursor

Specifications

Overview & Compatibility

Coding Capabilities

Agents & Execution

AI Models & Codebase Context

Developer Workflow & Integrations

Pricing, Teams & Security

Compare Cursor

Compare before you choose

Similar AI models

OpenAI Codex

Claude Code

GitHub Copilot

Lovable