Codex is OpenAI’s coding agent: a Rust CLI, an IDE extension, a desktop app, and a cloud service, all included in ChatGPT plans.
Codex is the only big-lab harness whose Apache-2.0 CLI an individual can still just run, and that matters more day to day than any single feature difference with Claude Code.
What it is #
The codex CLI runs locally against your repository, with /init writing an AGENTS.md, sandboxed permissions, /review for local code review, skills and a plugin marketplace, subagents, and codex exec for scripts and CI.
Codex cloud runs the same agent in cloud environments reachable from web, CLI, and GitHub (@codex on issues and PRs), and the SDK, app server, and MCP server expose the harness as a platform.
Default models are the GPT-6 family (Astra, Sol, and Luna) rolling out across plans alongside the GPT-5.6 family (Sol, Terra, Luna), with GPT-5.5 retiring from ChatGPT on October 14, 2026.
Status #
Active.
openai/codex shows about 127.5k stars, about 19.9k forks, and about 11.7k commits under Apache-2.0 as of 2026-10-02.
The CLI launched April 2025 and has been rewritten and rebuilt since; the current docs position it as an open agent harness platform.
Strengths #
- Open-source CLI you can audit, fork, and drive with an API key, no subscription required.
- Included from the ChatGPT Free tier upward, so the entry price is zero.
- AGENTS.md is the first-class configuration convention, not a vendor variant.
- Model tiering (Sol/Terra/Luna) makes high-volume work cheaper without changing tools.
- Sandboxing and permission profiles are documented and prominent.
Cautions #
- API-key mode drops the cloud features (GitHub code review, Slack integration); those need a ChatGPT plan.
- Usage is metered in shared five-hour windows across ChatGPT and Codex features, and the published per-window message ranges are wide (for example 10-100 local Sol messages on Plus).
- The April 2025 launch drew sharp comparisons: early builds hallucinated docs Claude Code wrote correctly, and the original TypeScript CLI was rough; judge current releases, not that launch thread.
- Skills and plugins are converging on formats every vendor now claims, so expect churn.
Pricing #
Included in ChatGPT Free, Go ($8/month), Plus ($20/month), Pro (three tiers at $100, $200, and $500/month, the $500 tier carrying Ultrafast Astra access), Business ($20-25 per user), Enterprise and Edu. Overage is sold as credits; API-key usage is plain token pricing.
Price history #
| Date | Plan | Change | Source |
|---|---|---|---|
| 2026-09 | ChatGPT plans | Baseline: included from Free up, Go $8/mo, Plus $20/mo, Pro 5x $100/mo, Pro 20x $200/mo, Business $20-25 per user, Enterprise and Edu custom; overage sold as credits. | |
| 2026-10-03 | Pro | The pricing page now lists Pro as three tiers at $100, $200, and $500 per month, where the note previously carried Pro 5x $100 and Pro 20x $200; the $500 tier is listed with Ultrafast Astra access. |
Compared to #
- Claude Code: deeper orchestration layer, heavier token baseline, closed client; pick Anthropic’s stack only if you are all-in on Claude models.
- Gemini CLI: also Apache-2.0, but Google ended free consumer access in June 2026.
- OpenCode: provider-neutral and MIT, but no bundled subscription usage.
Bottom line #
Recommended for anyone already paying for ChatGPT: it is the subscription-backed harness with the least lock-in. My own split: work that suits a subscription goes here, metered work goes to aider or OpenCode on my keys. Not the cheapest path if your usage is light and token-based (aider or OpenCode with your own keys costs less).
Changes #
- 2026-08-22 - Created in the Harnesses category seed.
- 2026-08-23 - Bolded each section’s key insight, named the launch-thread referent in the April 2025 caution, and set the updated field.
- 2026-08-26 - Qualified the overbroad only-open-source-CLI thesis to what distinguishes it from Gemini CLI.
- 2026-08-27 - Moved the three doc references to learn.chatgpt.com after the domain migration and reworded a banned-term phrase.
- 2026-09-16 - Refreshed repository scale to about 125k stars, about 19.3k forks, and about 10.8k commits.
- 2026-09-20 - Added the Price history section tracking price changes in a table, per the new owner rule.
- 2026-09-22 - Recorded the GPT-6 family (Astra, Sol, Luna) arriving across ChatGPT plans alongside GPT-5.6 and the October 14, 2026 GPT-5.5 retirement, and refreshed repository scale.
- 2026-09-26 - Linked the ChatGPT plans note in the new Model access category, where the subscription that carries this harness is tracked with its price history.
- 2026-10-03 - Recorded the pricing page listing Pro as three tiers at $100, $200, and $500 per month (previously Pro 5x $100 and Pro 20x $200), with the $500 tier carrying Ultrafast Astra access, and appended the matching Price history row.
See also #
- Agentic Coding Tools Landscape - Codex’s place in the four-layer map
- Managing Many Concurrent LLM Agent Sessions - what running Codex plus siblings in parallel looks like
- my-ai-workflow - a practitioner’s harness rotation that includes Codex
- Claude Code - the direct subscription-first rival
- ChatGPT plans - the subscriptions that carry Codex, with their published limits and credit rates
References #
https://learn.chatgpt.com/docs - product overview and surfaces
https://learn.chatgpt.com/docs/codex/cli - CLI features, plugins, review, exec
https://learn.chatgpt.com/docs/pricing - plans, usage windows, credit rate card, GPT-6 rollout, the GPT-5.5 retirement date, and the Pro tier ladder at $100, $200, and $500, as of 2026-10-03
https://github.com/openai/codex - repository scale and Apache-2.0 license, as of 2026-10-02
https://news.ycombinator.com/item?id=43708025 - launch discussion with early critical comparisons