Head to head · live data
ChatGPT + Codex vs Cursor: plan limits and pricing
Every plan of both tools side by side: price, how usage is metered, when it resets and each limit the vendor states, copied from the vendor's own page. Where a vendor publishes no number, the row says so.
16 plans. Checked October 30, 2026. Full pages: ChatGPT + Codex · Cursor · change log
OpenAI
ChatGPT + Codex
- Free plan
- Free
- Entry paid plan
- Go, $8/mo
- Top self-serve tier
- Pro ($500), $500/mo
- Metered as
- messages per 5 hours
- Reset windows
- five-hour window, week
- Numbers published
- 30 of 40 limits
Per the vendor, the number of Codex messages depends on the model, task size and complexity, and whether work runs locally or in the cloud. Plus and Standard Business get local-message estimates per five-hour period, given as a range per model; these are "not fixed message limits", and the usage dashboard shows current limits and reset times. Cloud tasks may use more of the allowance than local messages. Local messages and cloud chats share the plan's usage allowance, and weekly limits may also apply. Pro plans currently have no five-hour limit. ChatGPT Work shares the same pricing, credits and usage limits as Codex. Fast mode uses included usage at 2.5x (2x on purchased credits). Ultrafast uses 8x (6x on credits). Image generation uses limits about 3-5x faster. After reaching limits, Plus/Pro users and flexible-pricing workspaces can buy credits, which are billed per 1M tokens per model. Enterprise/Edu with flexible pricing have no fixed rate limits.
Cursor
Cursor
- Free plan
- Free
- Entry paid plan
- Plus, $8/mo
- Top self-serve tier
- Ultra, $200/mo
- Metered as
- usage pool
- Reset windows
- week
- Numbers published
- 17 of 20 limits
Cursor is sold as part of The X Subscription (Grok, Cursor and X). Every paid plan includes one weekly pool of usage for Cursor models (Grok 4.7, Grok 4.6, Grok 4.5 and Composer 2.5), shared across Agent in the editor, CLI, Cloud Agents, Grok Bot and the Grok apps; different models draw from the pool at different rates and unused usage does not roll over. Tiers are expressed as multiples of the Plus pool (Plus = Base, Premium 4x, Super 15x, Ultra 50x); Cursor publishes no request or credit counts. Third-party models (Claude, GPT, Gemini) are not in the pool: on Premium and above they are billed at API list price from the first request out of prepaid credit; Free and Plus cannot use them. Prepaid credit (manual top-ups or Auto Top-up) also pays for Cursor-model usage beyond the weekly pool at the same per-model rates; credit expires 365 days after purchase and a monthly additional usage limit can cap spend. Teams and Enterprise pay an extra Cursor Token Rate of $0.25 per million tokens on eligible third-party requests (including BYOK). Grok API usage is billed separately and does not draw from the pool.
What differs
Stated from the two plan sets, no ranking: which tool fits depends on which window and unit matches your work.
- Entry price: ChatGPT + Codex Go at $8/mo; Cursor Plus at $8/mo.
- Top self-serve tier: ChatGPT + Codex tops out at Pro ($500), $500/mo; Cursor tops out at Ultra, $200/mo.
- ChatGPT + Codex has a free plan (Free); Cursor has a free plan (Free).
- Metering unit: ChatGPT + Codex counts "messages per 5 hours", Cursor counts "usage pool".
- Reset windows: ChatGPT + Codex five-hour window, week; Cursor week.
- ChatGPT + Codex prices 1 plan per seat; Cursor prices 1 plan per seat.
- Running out: ChatGPT + Codex: extra usage, Can purchase additional credits after reaching usage limit; Cursor: no overage option stated.
- Transparency: ChatGPT + Codex publishes a number for 30 of 40 limits; Cursor publishes a number for 17 of 20 limits.
Plan by plan
| Tool | Plan | Price | Metered as | Headline limit | Window | Source |
|---|---|---|---|---|---|---|
| ChatGPT + Codex | Free | Free | messages per 5 hours | Codex: GPT-6 Luna at Standard speed in the desktop app, subject to rollout; no message figures publishedno number published | five-hour window | Codex pricing |
| Go | $8/mo | messages per 5 hours | Codex: GPT-6 Luna at Standard speed in the desktop app, subject to rollout; no message figures publishedno number published | five-hour window | Codex pricing | |
| Plus | $20/mo | messages per 5 hours | Codex local messages, GPT-6 Astra: 5 to 45 per 5 hours | five-hour window | Codex pricing | |
| Pro ($100) | $100/mo | usage allowance | Codex 5-hour limit: None (vendor: Pro plans currently have no five-hour limit) | five-hour window | Codex pricing | |
| Pro ($200) | $200/mo | usage allowance | Codex 5-hour limit: None (vendor: Pro plans currently have no five-hour limit) | five-hour window | Codex pricing | |
| Pro ($500) | $500/mo | usage allowance | Codex 5-hour limit: None (vendor: Pro plans currently have no five-hour limit) | five-hour window | Codex pricing | |
| Business | Per user per month when billed monthly; 2+ users$20/mo annual | messages per 5 hours | Codex local messages, GPT-6 Astra: 5 to 45 per 5 hours | five-hour window | Codex pricing | |
| Business Codex (pay as you go) | No fixed seat fee; usage-based | usage (pay as you go) | Usage: Pay as you go based on usage; no limit figures publishedno number published | Chatgpt Pricing | ||
| Enterprise & Edu | Custom pricing; contact sales | credits | Rate limits (flexible pricing): No fixed rate limits; usage scales with credits | Codex pricing | ||
| Cursor | Free | Free | usage pool | AI usage: Limited agent requests; Limited Chat requestsno number published | week | Cursor pricing |
| Plus | $8/mo$6.67/mo annual | usage pool | Annual price: $80/yr | Models Pricing | ||
| Premium | $30/mo$25/mo annual | usage pool | AI usage: 4x more usage compared to Plus | week | Cursor pricing | |
| Super | $100/mo$83.33/mo annual | usage pool | AI usage: 15x more usage compared to Plus | week | Cursor pricing | |
| Ultra | $200/mo$166.67/mo annual | usage pool | AI usage: 50x more usage compared to Plus | week | Cursor pricing | |
| Teams | $30, $100, or $200 per seat/mo (Premium, Super or Ultra seat tier); pricing page shows $30+/user/month | usage pool | Cursor Token Rate: $0.25 per million tokens on eligible third-party requests (incl. BYOK) | Models Pricing | ||
| Enterprise | Custom; contact sales | usage pool | Cursor Token Rate: $0.25 per million tokens on eligible third-party requests (incl. BYOK) | Models Pricing |
One headline limit per plan. Every limit, with its wording and source, is on the ChatGPT + Codex and Cursor pages.
ChatGPT + Codex vs Cursor: common questions
Which is cheaper, ChatGPT + Codex or Cursor?
Both start at the same price. ChatGPT + Codex Go is $8/mo; Cursor Plus is $8/mo. Prices from the vendors' pricing pages, checked 2026-10-30.
At $8/mo, what do ChatGPT + Codex and Cursor each include?
ChatGPT + Codex Go: Codex, GPT-6 Luna at Standard speed in the desktop app, subject to rollout; no message figures published (no number published). Cursor Plus: Annual price, $80/yr.
How do ChatGPT + Codex and Cursor count usage?
ChatGPT + Codex: Per the vendor, the number of Codex messages depends on the model, task size and complexity, and whether work runs locally or in the cloud. Plus and Standard Business get local-message estimates per five-hour period, given as a range per model; these are "not fixed message limits", and the usage dashboard shows current limits and reset times. Cloud tasks may use more of the allowance than local messages. Local messages and cloud chats share the plan's usage allowance, and weekly limits may also apply. Pro plans currently have no five-hour limit. ChatGPT Work shares the same pricing, credits and usage limits as Codex. Fast mode uses included usage at 2.5x (2x on purchased credits). Ultrafast uses 8x (6x on credits). Image generation uses limits about 3-5x faster. After reaching limits, Plus/Pro users and flexible-pricing workspaces can buy credits, which are billed per 1M tokens per model. Enterprise/Edu with flexible pricing have no fixed rate limits. Cursor: Cursor is sold as part of The X Subscription (Grok, Cursor and X). Every paid plan includes one weekly pool of usage for Cursor models (Grok 4.7, Grok 4.6, Grok 4.5 and Composer 2.5), shared across Agent in the editor, CLI, Cloud Agents, Grok Bot and the Grok apps; different models draw from the pool at different rates and unused usage does not roll over. Tiers are expressed as multiples of the Plus pool (Plus = Base, Premium 4x, Super 15x, Ultra 50x); Cursor publishes no request or credit counts. Third-party models (Claude, GPT, Gemini) are not in the pool: on Premium and above they are billed at API list price from the first request out of prepaid credit; Free and Plus cannot use them. Prepaid credit (manual top-ups or Auto Top-up) also pays for Cursor-model usage beyond the weekly pool at the same per-model rates; credit expires 365 days after purchase and a monthly additional usage limit can cap spend. Teams and Enterprise pay an extra Cursor Token Rate of $0.25 per million tokens on eligible third-party requests (including BYOK). Grok API usage is billed separately and does not draw from the pool.
Do ChatGPT + Codex and Cursor have free plans?
ChatGPT + Codex Free is free: Codex, GPT-6 Luna at Standard speed in the desktop app, subject to rollout; no message figures published; Codex (ChatGPT pricing page), Limited; Image generation in Codex, Not available; Codex Cloud, Not included. Cursor Free is free: AI usage, Limited agent requests; Limited Chat requests; Third-party models, Not available.
When do ChatGPT + Codex and Cursor limits reset?
ChatGPT + Codex: five-hour window, week. Cursor: week. The figure inside each window is listed per plan on this page, or marked "not published" where the vendor gives none.
Limit alerts
Never get hit by a surprise AI quota cap.
One email the moment Anthropic, OpenAI, Cursor, Copilot or Google quietly change a 5-hour rolling limit, a rate limit or a plan price. Every alert links the vendor page and the old and new value.