
Codex
openai.comFull description
Codex is OpenAI's AI coding platform, with parallel multi-agent collaboration, custom skills and multimodal input. It works across devices and via API, connects external tools through the MCP protocol, and generates, debugs and reviews code from natural language.Changes and automation on large projects
Two layers of usage limits; slow at peak times
Perks for Codex
Checked against official pages regularly
Original in Chinese- Official resetFree reset for everyone · Announced by the providerAnnounced Oct 13, 2026
Applies to: Codex
- Official resetFree reset for everyone · Announced by the providerAnnounced Oct 13, 2026
Applies to: Codex
- Official resetFree reset for everyone · Applied, per the providerAnnounced Oct 10, 2026
Applies to: Codex
- Official resetFree reset for everyone · Announced by the providerAnnounced Oct 7, 2026
Applies to: Codex
- Official resetFree reset for everyone · Applied, per the providerAnnounced Oct 2, 2026
Applies to: Codex
- Official resetFree reset for everyone · Applied, per the providerAnnounced Sep 26, 2026
Applies to: Codex
User verdicts
User verdicts · independent of our own tests aboveOn a bad day, adding five to seven lines of code can make me wait twenty minutes, and opening a simple PR takes twenty minutes or more, with 429 retry failures along the way. A one-minute job dragged into twenty; that day one release took me four hours.
Hitting the Plus limit isn't a matter of waiting a few hours; I couldn't use it for two or three days straight. Only later did I figure out there are two limits stacked: a five-hour window, plus a weekly total on top. Tasks already running before the limit kicked in could still be checked on and run to completion.
The first time felt like discovering a new world; the other AI coding tools I'd used weren't in the same league on real projects. But after two months I started hunting everywhere for cheaper usage plans: at this intensity on the official plans, the money just won't hold out.
On Windows you must spell out the OS and PowerShell version in AGENTS.md, otherwise it mixes syntax from different versions in its commands and you get a pile of errors. I also added a rule: use Python whenever possible, which is much more stable across environments.
When the desktop app runs tasks, the whole computer crawls: the browser barely opens and typing in a document lags. Switching back to the CLI fixed it at once, so the problem must be the app itself.
I don't just hand it the keys. First I set up guardrails (tests, permissions and rollback) to keep the blast radius of mistakes small enough, and only then let it build, debug and deploy on its own in the dev environment. With those in place, that part really can be handed off.
I used to run five CLI sessions at once without hitting limits. After the update, ten or twenty prompts and it's empty. High-reasoning mode, long sessions, Skills and MCP all eat quota, so now I have to watch for when to switch to a cheaper model.
After a few months it's almost unrecognizable. Since the CLI's engineering ability improved, I've been alternating between it and Claude Code, splitting projects between them, and I can no longer tell which is clearly stronger. The early version was rough; reviews from a year ago can basically be ignored.
Alternatives
Interchangeable picks for the same job · each with its own evidence
Claude CodeAI coding agent for your terminalNot tested yet · info from official sources
kimi codeA web-based AI coding assistant from Moonshot AINot tested yet · info from official sources
千问AI Qwen chatAn AI chat assistant built on Tongyi Qianwen modelsNot tested yet · info from official sourcesKnow a better AI tool?
Recommend a tool you like. It takes seconds, and it goes live after review.
Latest updates
Original in Chinese我们使用 first-party Cookie 做匿名访问统计,以改进内容与体验。匿名标识不关联个人身份信息(手机号/邮箱), 详见《用户协议及隐私政策》。
