AI coding tools · November 2026
Cursor pricing, plan by plan
Cursor is now sold as part of the X Subscription, with one weekly AI pool shared with Grok. Here is what each plan includes, and what Claude, GPT or Gemini costs on top at API list price.
Plans from cursor.com, checked November 3, 2026. Model prices from OpenRouter, November 8, 2026
| Plan | Price | AI usage | Models | Also includes |
|---|---|---|---|---|
| Free | $0 | Limited | Limited agent and Chat requests | Limited Grok Chat, Imagine and Grok Build |
| Plus | $8 a month ($80 a year) | Base pool | Cursor’s own models only (Grok 4.7, 4.6, 4.5, Composer 2.5) | Grok Chat, Voice, Imagine, Build and Grok API access. No Cloud Agents, Bugbot or your own API keys |
| Premium | $30 a month ($300 a year) | 4× Plus | Cursor models, plus Claude, GPT and Gemini at API list price from prepaid credit | Cloud Agents and Automations, code hosting on Origin, code review with Bugbot, Grok Bot |
| Super | $100 a month ($1,000 a year) | 15× Plus | As Premium | Priority model access at peak times |
| Ultra | $200 a month ($2,000 a year) | 50× Plus | As Premium | Earliest access to new products and models |
| Teams | $30, $100 or $200 per seat a month | Matches the seat’s tier | As Premium; third-party models at API list price plus the Cursor Token Rate | Central billing, usage analytics, SSO, team-wide privacy settings, mixed seat types |
| Enterprise | Custom | Pooled | As Teams | Invoice billing, SCIM, granular spend controls, audit logs, priority support |
Prices exclude tax. Paid plans also include X features (Premium checkmark, fewer ads in the timeline). Grok API calls are billed separately at standard rates and don’t use the plan’s pool. Pro, Pro+ and the old Ultra are legacy plans that keep working as they were.
What Claude, GPT and Gemini cost on top
Third-party models aren’t in the pool: on Premium and above Cursor bills them at the model’s API list price, from prepaid credit. An hour of agent coding is about 3M input tokens (90% of them cache reads) and 60K output tokens.
| Model | Input /1M | Output /1M | Per hour | 1 h a day | 4 h a day |
|---|---|---|---|---|---|
| Claude Fable 5.1 | $10 | $50 | $7.42 | $156 | $624 |
| Claude Opus 5.5 | $4 | $20 | $3.24 | $68.04 | $272 |
| Claude Sonnet 5.5 | $2 | $10 | $1.62 | $34.02 | $136 |
| Claude Haiku 5.5 | $0.10 | $0.50 | $0.095 | $1.98 | $7.94 |
| GPT-5.6 Sol | $4 | $20 | $3.78 | $79.38 | $318 |
| GPT-5.6 Terra | $2 | $12 | $2.01 | $42.21 | $169 |
| Gemini 4 Argon | $2 | $10 | $1.47 | $30.87 | $123 |
21 working days a month. Fresh input billed at the cache-write price where the model has a higher one, cache reads at the cache-read price. Your token use can be several times higher or lower; use your own numbers.
The real bill: Premium ($30) plus an hour a day of Claude Sonnet 5.5 comes to about $64.02 a month; four hours a day is about $166. Cursor’s own models come out of the plan’s pool instead.
Cursor vs Claude Code, at the same price
| Monthly price | Cursor | Claude (includes Claude Code) |
|---|---|---|
| $0 | Free: limited agent and Chat requests | Free: Claude chat, no Claude Code |
| $8–$30 | Plus $8 (Cursor’s own models only) or Premium $30 (4× Plus; Claude at API price on top) | Pro $20: Claude Code with Sonnet and Opus, within Pro limits |
| $100 | Super: 15× Plus usage on Cursor’s models; Claude at API price on top | Max: 5× Pro usage on Claude models, plus $100 a month in API credits |
| $200 | Ultra: 50× Plus usage on Cursor’s models; Claude at API price on top | Ultra: 10× Pro usage a week, no 5-hour limit, plus $200 a month in API credits |
Claude plans from claude.com/pricing, checked November 3, 2026. The short version: Cursor’s pool buys Grok and Composer; Claude’s buys Claude. The full Cursor vs Claude Code comparison · Claude Code cost calculator.
Related
Cursor pricing questions
How much does Cursor cost?
Cursor has a free plan and four paid ones: Plus at $8 a month, Premium at $30, Super at $100 and Ultra at $200 (or $80, $300, $1,000 and $2,000 a year). Teams seats are $30, $100 or $200 a month and Enterprise is priced on request. Prices exclude tax. Checked on cursor.com on November 3, 2026.
Does Cursor include Claude and GPT?
Not in the plan’s pool. The pool covers Cursor’s own models (Grok 4.7, 4.6, 4.5 and Composer 2.5). On Premium and above you can use Claude, GPT and Gemini at the model’s API list price from the first request, paid from prepaid credit; Plus and Free don’t include them. A monthly limit caps how much extra usage you can spend.
What happened to Cursor Pro?
Pro, Pro+, the old Ultra, Start and the Teams Standard and Premium seats are now legacy Cursor plans. Cursor says they keep working as they are, with two monthly usage pools and on-demand usage. New subscriptions use the Plus, Premium, Super and Ultra plans.
How do Cursor’s usage limits work?
Each plan has one AI usage pool shared across everything on the subscription (Agent in the editor, the CLI, Cloud Agents, Grok Bot and the Grok apps), and it refreshes every week. Premium has 4× the usage of Plus, Super 15× and Ultra 50×. When it runs out you can wait for the reset, keep going on prepaid credit (Grok 4.7 at $2 in and $6 out per 1M tokens, Composer 2.5 at $0.50 and $2.50) or upgrade.
Is there a free version of Cursor?
Yes. The free plan has limited AI usage, with limited agent and Chat requests.
Which Cursor plan should I choose?
Cursor suggests Premium for new Agent users, Super for daily Agent users and Ultra for power users running several agents or Automations. If you mainly want Claude models, compare with Claude’s own plans, which include them: Claude Code pricing.
How much does Cursor cost for a team?
Teams seats cost $30, $100 or $200 a month, with the usage of the matching individual tier, plus central billing, usage analytics, SSO and team-wide privacy settings. Third-party models on Teams bill at API list price plus the Cursor Token Rate. Enterprise adds pooled usage, invoicing, SCIM and audit logs at a custom price.
Know what your AI stack costs.
Glow shows each product’s AI tools and API bill against its revenue, so you know which app is worth the tokens.