OpenAI · Tools

OpenAI Codex

Visit website

At a glance

Price
from 8 $/mo
Vendor
OpenAI

Specifications & properties

Key decision factors

Pricing model
Freemium 1
Tool form
  • CLI agent
  • IDE plugin
  • Web app
1
Autonomy level
Autonomous agent 1
Model choice
Multiple models 1

Pricing

Price from
8 $/mo 1
Free tier
Yes 1

Integration

API available
Yes 1

Model

Available models
gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.5, gpt-5.3-codex-spark 1

Capabilities

Terminal/command execution
Yes 1
Report data / suggest a correction

OpenAI's coding agent that runs as a CLI, IDE extension, and in parallel isolated cloud environments, included with ChatGPT plans.

Profile

OpenAI Codex is OpenAI's coding agent: a software engineering assistant that can read, plan, write, test, and modify code inside a sandboxed execution environment, shipped as one connected product across ChatGPT (web and desktop), a command-line tool (Codex CLI), an IDE extension, and a cloud/async execution mode. This is the current, actively developed Codex product line, distinct from the original 2021 Codex API (the code-davinci-002-era model that once powered early versions of GitHub Copilot); OpenAI retired API access to that legacy model in 2023, and today "Codex" refers to the agentic coding product described here.

Company

Codex is developed and operated by OpenAI, the company behind ChatGPT and the GPT model family. Inside OpenAI's product line-up, Codex is positioned as the dedicated tool for professional software engineering work, distinct from ChatGPT as a general-purpose chat assistant.

Core features

Codex is built around handing the agent a starting point — a goal, an idea, or a task — and letting it gather context across a codebase, take action, and produce a reviewable result such as a diff, a pull request, or a running change. According to OpenAI's own product documentation, Codex can:

  • Work locally through Codex CLI or inside an editor via the Codex IDE extension, or run tasks remotely in Codex cloud, with the ability to hand tasks off between a local machine and a remote host.
  • Execute inside a sandbox with configurable agent approvals and security settings, including permission profiles and control over internet access, plus an auto-review step before changes are applied.
  • Take actions beyond editing files, including browser and computer-use functionality, image generation, and web search when a task calls for it.
  • Turn a demonstrated workflow into a reusable "skill" through a record-and-replay capability.
  • Run scheduled or long-running tasks that continue in the background instead of requiring a developer to stay in the loop.
  • Use a dedicated security-review capability to scan and flag risky changes.

Pricing and access

Codex is not sold as a separate subscription; access is bundled into ChatGPT plans. Usage is included, up to plan-specific limits, in the Free, Go, Plus, Pro, Business, Edu, and Enterprise tiers, and ChatGPT Business and Codex usage are now billed together on the same seat. Once included usage runs out, further Codex use is metered through a credit system whose cost varies by model, context size, reasoning effort, and tools used. Separately, Codex can be run against an OpenAI API key on a pay-as-you-go basis, charged at standard API token rates rather than through a ChatGPT plan. OpenAI has also introduced flexible, usage-based pricing aimed at teams running many Codex tasks in parallel, on top of seat-based Business and Enterprise plans.

Who it's for

Codex targets professional developers and engineering teams who want an agent to handle real, multi-file coding work — bug fixes, refactors, test-writing, reviewing pull requests, or building small features — rather than just inline autocomplete suggestions. The combination of a local CLI, an IDE extension, and a cloud execution mode suits teams that want to run coding tasks both interactively and asynchronously, including workflows where many tasks run unattended in the background and are reviewed once complete. Business and Enterprise customers get seat-based billing, data-handling controls, and a data processing addendum, positioning Codex for organizations with compliance requirements alongside individual developers.

Frequently asked questions

Is OpenAI Codex free?

OpenAI Codex is not a separate paid product — it is bundled into ChatGPT plans, including the free ChatGPT tier, so a limited amount of Codex usage is available at no cost. Heavier or continuous use requires a paid ChatGPT plan (Go, Plus, Pro, Business, Enterprise, or Edu), or, once included usage is exhausted, additional usage billed through Codex's credit system or a pay-as-you-go OpenAI API key.

What does OpenAI Codex cost?

OpenAI Codex has no separate flat subscription price — cost depends on how you access it. Codex usage is included, up to plan-specific limits, in ChatGPT's Free, Go, Plus, Pro, Business, Edu, and Enterprise plans, with ChatGPT Business and Codex usage now billed on the same per-seat plan. Beyond the included allowance, further use is metered through a credit system whose cost varies by model, context size, reasoning effort, and tools used, or you can run Codex against your own OpenAI API key on a pay-as-you-go basis at standard API token rates. OpenAI has also rolled out flexible, usage-based pricing aimed at teams running many Codex tasks at once.

Is OpenAI Codex GDPR-compliant, and where is data hosted?

OpenAI offers a Data Processing Addendum (DPA) for ChatGPT Business, ChatGPT Enterprise, and API-based use — which covers Codex usage through those channels — to support customers' GDPR compliance. By default, OpenAI does not use data, inputs or outputs, from ChatGPT Business, ChatGPT Enterprise, ChatGPT Edu, or the API platform to train or improve its models, and customer data on these plans remains owned and confidential to the customer. For data residency, eligible Enterprise, Edu, and API platform customers can choose to store data at rest in specific regions, including the U.S., Europe, the UK, and several other countries.

How is OpenAI Codex different from GitHub Copilot or Claude Code?

OpenAI Codex is an autonomous coding agent, not an inline autocomplete tool: instead of just suggesting the next few lines as you type (the classic GitHub Copilot model), Codex takes a goal or task, gathers context across a codebase, and works through it in a sandboxed environment — locally via Codex CLI or an IDE extension, or remotely via Codex cloud — before handing back a reviewable diff or pull request. Claude Code, Anthropic's comparable product, follows a similar agentic pattern, so the practical difference from Codex tends to come down to which underlying model family and which ChatGPT/Claude plan a team already standardizes on, rather than a fundamental difference in what the tool does.

What is OpenAI Codex best for?

OpenAI Codex is best suited to real, multi-file software engineering work — bug fixes, refactors, writing tests, reviewing pull requests, and building small features — that a developer can hand off as a defined task rather than type line by line. Its mix of a local CLI, an IDE extension, and a cloud/async execution mode makes it particularly suited to teams that want to run coding tasks unattended in the background, including scheduled or long-running jobs and workflows recorded once and replayed as reusable skills, then review the results once complete.

Is there an OpenAI Codex API?

Yes — beyond using Codex through a ChatGPT plan, it can be run directly against an OpenAI API key on a pay-as-you-go basis, with usage charged at standard OpenAI API token rates rather than through ChatGPT plan credits. This lets teams integrate Codex into their own CI/CD pipelines or tooling and pay purely for the tokens consumed, separate from ChatGPT seat billing.