# OpenAI Codex Review

> 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.

![OpenAI Codex logo](https://www.versusref.com/logos/openai-codex.png)

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 · facts verified Oct 2, 2026

## 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.

## Fact sheet

### Pricing

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| How usage is metered | Time windows + per-token | Oct 2 | [source](https://developers.openai.com/codex/pricing) |
| What the free plan allows | Free $0: 'GPT-6 Luna at Standard speed in the desktop app | Oct 2 | [source](https://developers.openai.com/codex/pricing) |
| Cheapest paid plan (monthly) | $8 | Oct 2 | [source](https://developers.openai.com/codex/pricing) |
| Top individual plan | $500 | Oct 2 | [source](https://developers.openai.com/codex/pricing) |
| Usage included at entry tier | Plus ($20) | Oct 2 | [source](https://developers.openai.com/codex/pricing) |
| Rate-limit window | per five-hour period + weekly limits may apply | Oct 2 | [source](https://developers.openai.com/codex/pricing) |
| Price beyond the plan | ChatGPT credits at per-1M-token rates (Standard speed)... | Oct 2 | [source](https://developers.openai.com/codex/pricing) |
| Bring your own API key | true | Oct 2 | [source](https://developers.openai.com/codex/pricing) |
| Team plan price | 25 USD/user/mo | Oct 2 | [source](https://developers.openai.com/codex/pricing) |
| Enterprise plan (contact sales) | ✓  Yes | Oct 2 | [source](https://developers.openai.com/codex/pricing) |

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Models available | GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol, GPT-6 Luna +6 more | Oct 2 | [source](https://developers.openai.com/codex/pricing) |
| Default model | Recommended: GPT-6.1 Sol 'when available to your account... | Oct 2 | [source](https://learn.chatgpt.com/docs/models) |
| Pick the model per task | ✓  Yes | Oct 2 | [source](https://learn.chatgpt.com/docs/models) |
| Runs local models | ✓  Yes | Oct 2 | [source](https://learn.chatgpt.com/docs/codex-manual.md) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Trains on your code? | Business | Oct 2 | [source](https://learn.chatgpt.com/docs/codex-manual.md) |
| SOC 2 | ✓  Yes | Oct 2 | [source](https://trust.openai.com/) |
| SSO | SAML SSO and MFA on Business | Oct 2 | [source](https://developers.openai.com/codex/pricing) |
| Self-hosted / VPC deployment | ✓  Yes | Oct 2 | [source](https://learn.chatgpt.com/docs/codex-manual.md) |
| Data residency | Enterprise data residency controls | Oct 2 | [source](https://learn.chatgpt.com/docs/codex-manual.md) |
| Admin audit logs | ✓  Yes | Oct 2 | [source](https://developers.openai.com/codex/pricing) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Where it runs | ChatGPT desktop app | Oct 2 | [source](https://learn.chatgpt.com/docs/codex-manual.md) |
| Editor support | VS Code, VS Code Insiders, Cursor +2 more | Oct 2 | [source](https://learn.chatgpt.com/docs/codex/ide.md) |
| Autonomous multi-file edits | ✓  Yes | Oct 2 | [source](https://learn.chatgpt.com/docs/cloud.md) |
| Runs terminal commands | ✓  Yes | Oct 2 | [source](https://learn.chatgpt.com/docs/agent-approvals-security.md) |
| Background / cloud agents | ✓  Yes | Oct 2 | [source](https://learn.chatgpt.com/docs/cloud.md) |
| Parallel agents | ✓  Yes | Oct 2 | [source](https://learn.chatgpt.com/docs/codex-manual.md) |
| Opens PRs from issues | ✓  Yes | Oct 2 | [source](https://learn.chatgpt.com/docs/codex-manual.md) |
| MCP support | ✓  Yes | Oct 2 | [source](https://learn.chatgpt.com/docs/extend/mcp.md) |
| Project rules files | AGENTS.md (nested/layered) +4 more | Oct 2 | [source](https://learn.chatgpt.com/docs/agent-configuration/agents-md.md) |
| Code review | Code Review via GitHub | Oct 2 | [source](https://developers.openai.com/codex/pricing) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| License | Apache-2.0 (Codex CLI) | Oct 2 | [source](https://github.com/openai/codex) |
| GitHub stars | 127,600 | Oct 2 | [source](https://github.com/openai/codex) |
| Last release | 0.160.0 (2026-10-01) | Oct 2 | [source](https://www.npmjs.com/package/@openai/codex) |
| Supported model providers | OpenAI (ChatGPT sign-in or API key), Azure OpenAI +5 more | Oct 2 | [source](https://learn.chatgpt.com/docs/codex-manual.md) |

## OpenAI Codex head-to-head

| Comparison | Record | Per use case |
| --- | --- | --- |
| [OpenAI Codex vs Claude Code](https://www.versusref.com/coding-agents/claude-code-vs-openai-codex/) | won 4 · lost 3 · tied 0 | Beginners: won; Enterprise: lost; Free Plans: won; Local Models: won; Open Source: won; Terminal Workflows: lost; VS Code: lost |
| [OpenAI Codex vs Cursor](https://www.versusref.com/coding-agents/cursor-vs-openai-codex/) | won 4 · lost 3 · tied 0 | Beginners: won; Enterprise: lost; Free Plans: won; Local Models: won; Open Source: won; Terminal Workflows: lost; VS Code: lost |
| [OpenAI Codex vs GitHub Copilot](https://www.versusref.com/coding-agents/github-copilot-vs-openai-codex/) | won 4 · lost 3 · tied 0 | Beginners: lost; Enterprise: won; Free Plans: won; Local Models: won; Open Source: won; Terminal Workflows: lost; VS Code: lost |
| [OpenAI Codex vs Aider](https://www.versusref.com/coding-agents/aider-vs-openai-codex/) | won 3 · lost 4 · tied 0 | Beginners: won; Enterprise: won; Free Plans: lost; Local Models: lost; Open Source: lost; Terminal Workflows: lost; VS Code: won |

Source: https://www.versusref.com/coding-agents/tools/openai-codex/