OpenAI Codex vs Cursor
OpenAI Codex (OpenAI) and Cursor (Anysphere (owned by SpaceX)) side by side on public data, as of Nov 20, 2026.
OpenAI Codex has 4.1x the GitHub stars of Cursor (136K against 33.3K).
Which should you choose?
Choose OpenAI Codex if
- you want code you can read, fork or self-host (Apache-2.0)
- you need to run local models
- steady service matters most: 1 incident on its status page in 30 days against 20
- you prefer the more widely used tool, with more docs and answers around (Gid Score 84 against 73)
Choose Cursor if
- you want to switch between model providers (6 documented against 3)
Built from documented features, official prices, status pages and usage data on this page; it does not judge output quality.
Side-by-side numbers
| Metric | OpenAI Codex | Cursor |
|---|---|---|
| Gid Score | 84 | 73 |
| Usage data as of | Nov 19 | Nov 19 |
| Rank by Gid Score | #2 | #6 |
| Downloads, last 7 days | 26.6M | — |
| Downloads, 7-day change | up 2.4% | — |
| Downloads, 30-day change | up 7.4% | — |
| VS Code installs | 16.9M | — |
| Marketplace rating | 2.7 / 5 (975) | — |
| GitHub stars | 136K | 33.3K |
| Homebrew installs, 30 days | 529K | 8,714 |
| Hacker News mentions, 30 days | 1,429 | 395 |
| Latest stable release | 0.168.0 · 7d ago | — |
| Terminal-Bench (best run) | 62.1% · v4.1 | — |
| Price | Free + $8/mo | Free + $8/mo |
| Usage limits | 5-hour limit, weekly limits may apply Go: GPT-6 Luna in the desktop app; limits not published all plans | two monthly usage pools (Cursor's own models and third-party models at API list price) plus on-demand usage Plus: Base usage pool; only Grok models ($80/year with yearly billing) all plans |
| Incidents, last 30 days | 1 | 20 · 3 major or critical |
| License | Apache-2.0 | Proprietary |
| First released | April 2025 | March 2023 |
| Interfaces | CLI, IDE extension, Desktop, Web, Mobile, SDK | Desktop IDE, CLI, Web, Mobile, Slack, GitHub, Linear, API/SDK |
| Models | OpenAI GPT models (GPT-6 family per current docs) via ChatGPT sign-in or an OpenAI API key | Models from OpenAI, Anthropic, Google, SpaceXAI (Grok 4.7/4.6/4.5) and Meta (Muse Wonder), plus Cursor's own Composer 2.5. |
A dash means there is no public data for that metric as of Nov 20, 2026.
Trends
OpenAI Codex
OpenAI's coding agent, offered as an open-source terminal CLI, an IDE extension, a desktop app and a cloud agent that works on repositories. Users sign in with a ChatGPT account or use an OpenAI API key; with an API key, Codex works in the CLI, SDK and IDE extension without cloud features such as GitHub code review and Slack. On the Free and Go plans Codex runs in the desktop app (subject to rollout); the web, CLI and IDE extension come with Plus and higher.
Pricing: Included in ChatGPT plans: Free $0, Go $8/month, Plus $20/month, Pro from $100/month ($100, $200 or $500 tiers), Business $20/user/month billed annually ($25 monthly), Enterprise and Edu by contact. API-key use is billed at API rates (no cloud features).
Latest release 0.168.0:
- Browse model providers under Sessions → Model providers and choose the default for new chats.
- Enable features.tui_workspace to view a side conversation beside the main chat. Drag the divider to resize the panes or press leader z to zoom the focused pane.
- Attach recordings when using an audio-capable model. Codex skips confirmed rejected recordings on later turns and uses clip duration to keep more short recordings in context.
- Enable features.image_generation_animation to generate or edit animated GIFs with optional frame count and timing controls.
Cursor
AI coding editor and agent platform with a desktop app, a CLI, web and mobile agents, and cloud agents that run tasks in remote environments. It offers models from OpenAI, Anthropic, Google, SpaceXAI (Grok) and Meta alongside its own Composer models.
Pricing: Free tier with limited AI usage; Plus $8/mo, Premium $30/mo, Super $100/mo, Ultra $200/mo for individuals with tiered usage pools; Teams $30+/user/mo with pooled usage; Enterprise custom pricing. Plus covers Grok models only. Includes social platform features (posting, replies, creator tools) alongside AI capabilities.
OpenAI Codex vs Cursor: common questions
Is OpenAI Codex or Cursor open source?
OpenAI Codex is open source (Apache-2.0); Cursor is proprietary.
Which is more popular, OpenAI Codex or Cursor?
OpenAI Codex has a Gid Score of 84 against 73 for Cursor. The score combines package downloads, editor installs, GitHub activity and attention, updated daily.
Do OpenAI Codex and Cursor support local models?
OpenAI Codex documents support for local models; Cursor's documentation does not.
Which has had fewer outages recently, OpenAI Codex or Cursor?
In the last 30 days OpenAI Codex's status page listed 1 incident and Cursor's listed 20. Counts come from each official status page.