OpenAI Codex Review
Coding agent across CLI (Apache-2.0), IDE extension, Codex Cloud (cloud_agent) and ChatGPT desktop app; usage shared with ChatGPT Work. The standalone Codex app merged into the ChatGPT desktop app on 2026-07-09.
See pricing
If you sign up through links on this page, vsref may earn a commission; programs exist on both sides of most comparisons, and commissions never change verdicts. How we make money
What we know about OpenAI Codex
OpenAI Codex sits in the ai coding agents category, where it is coding agent across CLI (Apache-2.0), IDE extension, Codex Cloud (cloud_agent) and ChatGPT desktop app; usage shared with ChatGPT Work. The standalone Codex app merged into the ChatGPT desktop app on 2026-07-09. We keep this OpenAI Codex profile grounded in primary sources, each fact dated to when we last confirmed it.
OpenAI Codex does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current OpenAI Codex quote, it is the fastest way for us to close that gap.
On capabilities, OpenAI Codex covers enterprise plan (contact sales), pick the model per task, runs local models, soc 2, self-hosted / vpc deployment, and admin audit logs. Each of those is verified against OpenAI Codex's own docs or dashboard, not marketing copy.
For compliance, with OpenAI Codex: SOC 2 Type II is in place. If you are in a regulated space, confirm the current posture with OpenAI Codex before you commit, since these change plan by plan.
In total we track 34 verified facts for OpenAI Codex today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the OpenAI Codex fact sheet below.
Reviewed by vsref Editorialfacts verified Oct 2, 2026Methodology →
Fact sheet
Every row independently verifiedConsidering a switch? Best OpenAI Codex alternatives →