Codex
by OpenAI · Agent · Text & code
promising
OpenAI's coding agent; early users report good results, mostly with GPT-6.2.
OpenAI reinstated the 5-hour usage limit for Codex on Plus and Business standard plans, on top of the weekly limit
AccessOpen codePricefree; Go $8/month, Plus $20/month, Pro from $100/monthRuns onWindows, macOS, Linux, Web, iOSLicenseApache 2.0
Why we say so
Simon Willison used the desktop app with GPT-6.2 Astra to build a comparison video, and AI Search calls it the best harness for GPT 6.2. An HN commenter says it unlocked and reimplemented paid Android app features offline. These are positive but few, and no independent benchmarks are cited.
Evidence
- Nov 19A user had Codex unlock premium features of subscription Android apps and reimplement them offline, with no extra skills
- Sep 9OpenAI case study: Codex running GPT-5.6 Sol helps run quantum computing lab experiments
- Sep 8Verbosity reported as a smaller problem with Codex than with Claude
- Sep 7One commenter says Codex limits are much better than Claude's, and the model smarter
- Sep 3Armature's 17k-session study found Codex almost always searches the web before choosing tools
Show all 8
- Aug 27When run on AWS Bedrock, Codex reportedly gets almost no prompt-cache reads and heavy cache writes, causing roughly 10x expected charges
- Aug 22A user who downgraded Max to Pro over Fable's perceived quality drop calls Codex with GPT 5.6 Sol very good
- Aug 21Reports conflict: some say Codex over-engineers (25,000+ line diff on a small ticket, excess provenance gates); others say Claude does
Alternatives
Made for Codex