Claude Code vs Cursor: cost after Cursor's pricing change
Independent verdict · Updated 2026-11-02
Cursor moved to the X Subscription in late October 2026, and Claude and GPT models are no longer included in its plans. Here is what each tool costs for the same kind of work, using only prices on the official pricing pages.
Verdict: Both top out at $100 and $200 tiers, but they buy different things. Every paid Claude plan (Pro $20/mo or $17/mo billed annually, Max $100, Ultra $200) includes Claude Code, and that usage covers Claude models such as Opus and Sonnet. Cursor's plans (Plus $8, Premium $30, Super $100, Ultra $200) include a usage pool shared with Grok, but Claude and GPT models cost extra at API list price. If you mainly want Claude models, Claude Code gives you a flat monthly price; if you are happy on Grok models or want Cursor's editor, Cursor Plus at $8 is the cheapest paid entry.
Cost side by side
| Claude Code | Cursor | |
|---|---|---|
| Cheapest paid plan | Pro: $20/mo, or $17/mo billed annually ($200 up front) | Plus: $8/mo (Grok models only) |
| Mid tiers | Max: $100/mo (5x Pro usage every 5 hours and every week) | Premium: $30/mo (4x Plus usage); Super: $100/mo (15x Plus usage) |
| Top individual tier | Ultra: $200/mo (10x Pro weekly usage, no 5-hour limit for verified accounts) | Ultra: $200/mo (50x Plus usage) |
| Claude models (Opus, Sonnet) | Included in plan usage | Not included; billed separately at API list price (Premium and up) |
| Usage pool is shared with | Claude on web, desktop and mobile; 5-hour and weekly limits | Grok (Chat, Imagine, Voice, Bot); refreshes weekly |
| When you hit the limit | Wait for the reset, upgrade, or turn on usage credits at standard API rates | Buy top-offs or wait for the weekly refresh |
| Extras | Max and Ultra include $100 and $200 a month in Claude API credits (not usable inside Claude Code) | Premium and up include cloud agents, Bugbot code reviews and Origin code hosting |
| Teams | Team plan for 2 to 150 people; Enterprise $20/seat/mo plus usage at API rates | Teams from $30/user/mo; Enterprise custom |
| Reference API rates (Anthropic) | Opus 5.5: $4 input / $20 output per million tokens; Sonnet 5.5: $2 / $10 | Cursor bills third-party models at API list price |
Prices in USD, before tax, from the official pricing pages listed under Sources.
| Claude Code | Cursor | |
|---|---|---|
| Category | Terminal coding agent | AI code editor |
| Pricing | Included with Claude Pro ($20/mo, or $17/mo billed annually), Max ($100/mo), Ultra ($200/mo), Team and Enterprise; or pay-as-you-go API credits via a Console account | Free; Plus $8/mo (Grok models only); Premium $30/mo; Super $100/mo; Ultra $200/mo; Teams from $30/user/mo, sold as the X Subscription (see site) |
| Pros | Excellent on large refactors; Works with any editor; First-class MCP support; Automated PR Code Review now GA for Team and Enterprise plans | Strong multi-file agent edits; Familiar VS Code UX and extensions; Supports MCP servers; CLI and Cloud Agents for terminal and background work; Agent SDK (GA, Oct 2026): define agents as code, test with evals, deploy to Cursor or your own infrastructure |
| Cons | Terminal-first; less visual; Plan usage is shared with Claude chat (5-hour and weekly limits); Not included on the Free plan | Requires coding comfort; Weekly usage pool is shared with Grok; Claude, GPT and other third-party models are billed separately at API list price, not included in the plan |
Choose Claude Code if…
- You mostly want Claude models (Sonnet, Opus) at a flat monthly price
- You already pay for Claude Pro, Max or Ultra, which include Claude Code at no extra cost
- You want to switch to pay-as-you-go API credits for heavy coding sprints
Choose Cursor if…
- You are fine using Grok models, which are included in the plan's usage pool
- You want the cheapest paid AI editor plan ($8/mo Plus)
- You want cloud agents, Bugbot AI code reviews and Origin code hosting, included from Premium ($30/mo)
Where they rank
- Best AI tools for building a SaaS MVP: Claude Code #5, Cursor #4
- Best AI coding tools for an existing codebase: Claude Code #1, Cursor #2
- Best terminal (CLI) coding agents: Claude Code #1, Cursor #4
Recent changes
- 2026-10-26 Claude Code: Security warning: the same researchers showed a planted CLAUDE.md can get Claude Code to reroute its API traffic and leak its OAuth token about half the time. Check unfamiliar instruction files and settings before starting an agent in a folder you didn't create. Source
- 2026-10-15 Claude Code: Claude Code Review leaves research preview and is generally available for Claude Team and Enterprise, with Quick, Standard and Deep modes. Source
- 2026-10-26 Cursor: Cursor's Agent SDK is generally available: an agent is a folder (instructions.md, tools/, skills/, mcp-connections/, channels/) that you test with evals and deploy to Cursor or your own infrastructure. Agents can wake on GitHub, GitLab and Bitbucket events, Slack mentions, webhooks or a cron schedule. Source
- 2026-10-28 Cursor: Cursor pricing is now the X Subscription: Free, Plus $8/mo (Grok models only), Premium $30/mo, Super $100/mo, Ultra $200/mo and Teams from $30/user/mo, with one weekly usage pool shared across Cursor and Grok. Third-party models like Claude and GPT are no longer included and are billed at API list price, which has drawn developer pushback on X. Source
- 2026-10-22 Cursor: Cursor CLI v2026.10.22: redeploy Cloud Agent environments, team-scoped self-hosted workers, nested AGENTS.md rules applied on edit. Source
Sources
- https://claude.com/pricing
- https://support.claude.com/en/articles/11145838-use-claude-code-with-your-pro-or-max-plan
- https://cursor.com/pricing
Official sites: Claude Code · Cursor
FAQ
Which is better, Claude Code or Cursor?
Both top out at $100 and $200 tiers, but they buy different things. Every paid Claude plan (Pro $20/mo or $17/mo billed annually, Max $100, Ultra $200) includes Claude Code, and that usage covers Claude models such as Opus and Sonnet. Cursor's plans (Plus $8, Premium $30, Super $100, Ultra $200) include a usage pool shared with Grok, but Claude and GPT models cost extra at API list price. If you mainly want Claude models, Claude Code gives you a flat monthly price; if you are happy on Grok models or want Cursor's editor, Cursor Plus at $8 is the cheapest paid entry.
When should I choose Claude Code?
You mostly want Claude models (Sonnet, Opus) at a flat monthly price. You already pay for Claude Pro, Max or Ultra, which include Claude Code at no extra cost. You want to switch to pay-as-you-go API credits for heavy coding sprints.
When should I choose Cursor?
You are fine using Grok models, which are included in the plan's usage pool. You want the cheapest paid AI editor plan ($8/mo Plus). You want cloud agents, Bugbot AI code reviews and Origin code hosting, included from Premium ($30/mo).
How much do Claude Code and Cursor cost?
Claude Code: Included with Claude Pro ($20/mo, or $17/mo billed annually), Max ($100/mo), Ultra ($200/mo), Team and Enterprise; or pay-as-you-go API credits via a Console account. Cursor: Free; Plus $8/mo (Grok models only); Premium $30/mo; Super $100/mo; Ultra $200/mo; Teams from $30/user/mo, sold as the X Subscription (see site). BuildJury only states prices confirmed on official pricing pages.
Is Claude Code cheaper than Cursor?
At the entry level Cursor is cheaper: Plus is $8/mo versus $20/mo for Claude Pro, but Plus only includes Grok models. If you want Claude models, Claude Pro includes them in its usage, while Cursor bills Claude separately at API list price on Premium ($30/mo) and up. At the top end both have $100 and $200 tiers.
Can I still use Claude models in Cursor?
Yes, on Premium and higher. Third-party models such as Claude and GPT are not included in the plan allowance and are billed separately by usage at API list price. The Plus plan includes Grok models only.
Does Claude Code cost extra on top of a Claude subscription?
No. Claude Code is included in all paid Claude plans (Pro, Max, Ultra, Team and Enterprise) and shares the plan's usage limits with Claude chat. It is not included on the Free plan. You can also run it on pay-as-you-go API credits through a Console account.
Do the API credits in Claude Max work in Claude Code?
No. Anthropic says the monthly API credits included with Max plans can't be used in Claude Code or the Claude apps; they are for building on the Claude Platform.