OpenAI Codex: what developers actually say
We read every Hacker News comment from Nov 2025 – Nov 2026 that gave a real opinion on OpenAI Codex. 1,708 of the 2,013 opinions come from people who say they use it themselves.
Developers give OpenAI Codex a 69% approval score across 2,013 opinions from 1,386 authors, with 1,708 opinions from firsthand users. Code quality is the strongest aspect at 343 positive mentions against 116 negative, and autonomy (169 to 46) and cost (174 to 54) also score well. Reliability is the weak spot at 112 positive against 127 negative. Approval peaked at 78 in March 2026, fell to 55 in September 2026, and stood at 59 in October; the 50 for November rests on only 9 opinions. In direct comparisons, 181 developers prefer Codex over Claude Code while 62 prefer Claude Code instead.
Pick it if
- Want strong code quality and hands-off autonomy
- Like starting agent sessions and doing other work meanwhile
- Value Codex billing kept separate from chat on a Pro plan
Look elsewhere if
- Need dependable execution on every single run
- Expect generous weekly quotas on the $20 plan
- Depend on a polished TUI or fast Windows performance
Strengths and weaknesses
Each row counts opinions that mentioned the topic. Bars to the right of the line are praise, bars to the left are complaints.
How opinion has moved
What developers say
Praise
Complaints
Summaries are paraphrased. Each links to the original comment.
OpenAI Codex compared
Best OpenAI Codex alternatives, according to developers who switched →
FAQ
Is OpenAI Codex worth it?
69% of 2,013 opinions are positive, and most come from people who used it directly. Code quality and autonomy draw the most praise. Reliability and quota complaints are the main reasons users look elsewhere.
Is Codex better than Claude Code?
181 developers say they prefer Codex over Claude Code, while 62 say they prefer Claude Code instead. Codex also leads Cursor 21 to 7 in the same head-to-head counts, and OpenCode 14 to 7.
How are Codex usage limits and pricing?
Usage limits drew 131 positive and 61 negative mentions, and cost and pricing scored 174 to 54. Some users on the $20 plan report hitting 5-hour limits quickly, and others say native subagents burn through the weekly quota. Approval fell from 78 in March 2026 to 55 in September 2026, then recovered to 59 in October.