OpenAI Codex

OpenAI’s coding agent for repository changes, debugging, code review and development automation across desktop, CLI, IDE and cloud workflows.

Coding AgentCode GenerationDebuggingCode ReviewRefactoringDevelopment Automation

Coding AgentCompare this model Visit website

Price

Free $0/month · Go $8/month · Plus $20/month; monthly USD subscription prices. API usage is billed separately. · Free: Free access is included with limited model/client availability; Free and Go currently list GPT-6 Luna Standard in desktop, subject to rollout. A universal paid-plan trial duration is not disclosed. · Paid: Go $8/month · Plus $20/month · Pro $100, $200 or $500/month. Business: $20/user/month billed annually, or $25 monthly, minimum 2 users. Enterprise/Edu: contact sales. Model and interface access vary; API usage is separate. · Limits: Allowance depends on model, reasoning, speed and task. Plus/Standard Business publish 5-hour estimates; weekly limits may apply. Pro currently has no 5-hour limit. Extra credits and API billing are separate.

Specialization

Coding Agent · Code Generation · Debugging · Code Review · Refactoring · Development Automation

Quality

Can inspect changes and run project checks when tools are available. Results depend on model, repository context and verification quality. Belliste has not run a comparative benchmark for this profile.

Features

Multi-file code generation and editing · Repository exploration and debugging · Test generation and execution · Local and connected pull-request review · Terminal commands and development tools · Planning, permissions and sandbox controls · Parallel subagents and Git worktrees · Local and cloud execution · AGENTS.md instructions and optional memory · MCP, plugins and external integrations · Screenshot-guided coding · CLI, SDK and app-server automation

About OpenAI Codex

OpenAI Codex helps developers inspect repositories, implement changes and validate results using available development tools. It combines local coding workflows with cloud tasks, code review, project instructions and optional parallel agents. Models, integrations and permissions vary by client, plan and workspace settings. This profile describes Codex as a developer tool; it does not treat every ChatGPT feature as available in every Codex interface. Belliste has not independently benchmarked its coding performance. Official documentation was reviewed on October 19, 2026.

Specifications

Overview & Compatibility

9 specifications

Starting Price	Free $0/month · Go $8/month · Plus $20/month; monthly USD subscription prices. API usage is billed separately.
Tool Type	Coding Agent / IDE Assistant; local development and cloud task workflows.
Primary Use Case	Implement features, investigate bugs, review changes and automate repository maintenance.
Best For	Individual developers and engineering teams working with repositories, tests and code review.
Access Methods	Desktop app · CLI · IDE extension/integrations · Web/cloud; mobile cloud access depends on plan and client.
Supported Operating Systems	Windows, macOS and Linux; CLI also runs in WSL. Installation, sandboxing and desktop capabilities differ by OS.
Supported IDEs & Editors	VS Code, VS Code Insiders, Cursor and compatible editors; Xcode and JetBrains offer separate integrations.
Programming Languages	Works across programming languages through source files and installed project tools. No exhaustive language-by-language compatibility guarantee is disclosed.
Framework Support	Uses the project’s framework, dependencies and build tools. A complete framework certification/support matrix is not disclosed.

Code Completion	Traditional as-you-type inline code autocomplete: Not disclosed. Codex documents prompted coding, editor-context input and diff review.
Code Generation	Generates code and files from instructions in an existing repository or new project.
Inline Code Editing	Uses selected editor code and open files as context for requested changes; edits can be reviewed beside the source.
Multi-File Editing	Can change multiple files in one repository task and present the resulting diff for review.
Code Explanation	Explains repository structure, functions and unfamiliar implementation details using accessible files.
Refactoring	Refactors existing code using project instructions and can verify the result with available checks.
Debugging Assistance	Investigates error reports, traces code paths and implements fixes; available logs and tests improve verification.
Test Generation	Can write tests for requested behavior and regressions using the project’s testing tools.
Documentation Generation	Can draft or update README files, code comments and project documentation from repository context.
Code Review	On-demand /review for local Git changes; connected PR reviews and automatic GitHub reviews require the relevant integration, permissions and account access. GitLab review integration is beta.
Image-to-Code	Accepts screenshots, diagrams and mockups as input for code changes and UI implementation; supports image input in CLI and editor workflows.

Agent Mode & Planning	Agent can inspect, plan, edit and verify a task. Planning and execution follow the selected mode and permission policy.
Terminal Command Execution	Runs shell commands, builds and installed development tools within the allowed filesystem and network scope.
Automated Test Execution	Runs available test suites, reads failures and can iterate on fixes; dependencies and test infrastructure must be configured.
Browser Interaction	Built-in interactive browser in the desktop app for sites and local previews. It is not built into Codex CLI or IDE extension; browser tools can be added separately where supported.
Background / Cloud Agents	Cloud tasks run in isolated workspaces and continue while the local computer sleeps. Local background work depends on the host remaining available.
Parallel Agent Tasks	Supports parallel subagents and separate concurrent tasks; Git worktrees help isolate repository changes. Parallel work increases usage.
Human Approval Controls	Permission profiles control file, network and execution access. Requests outside permitted scope can require approval; managed settings can constrain available policies.
Execution Isolation / Sandbox	macOS uses Seatbelt; Linux/WSL2 use the Linux sandbox; native Windows has a Windows sandbox. Cloud tasks get isolated workspaces. Isolation depends on configuration.
Execution Environment	Both: local CLI/IDE/desktop execution and Codex Cloud tasks. Remote-model inference is separate from where commands execute.

Supported AI Models	GPT-6.1 Sol, GPT-6 Sol, GPT-6 Luna and GPT-6 Astra where eligible. GPT-5.6 variants remain during rollout; model access depends on plan, client and sign-in method.
Model Selection	Configurable defaults plus manual model/reasoning selection via the picker, /model or --model. Available settings depend on client and workspace policy.
Bring Your Own API Key	Supports OpenAI API-key authentication in CLI, SDK and IDE workflows. API billing is separate; ChatGPT-dependent cloud features are limited or unavailable with API-key sign-in.
Local Model Support	CLI OSS mode supports local providers such as Ollama and LM Studio via --oss. Hardware, model tool support and feature compatibility vary.
Codebase Context & Indexing	Reads and searches accessible repository files, uses editor selections and project guidance. A universal persistent semantic-index specification is not disclosed.
Context Window	Model/provider dependent; context usage and compaction affect a session. No single fixed Codex-wide context window is disclosed; API model maximums do not guarantee equivalent usable product context.
Custom Instructions / Rules	AGENTS.md provides repository and directory instructions; user/project configuration and execution rules add workflow constraints.
Persistent Project Memory	Optional local memory carries useful context across eligible chats. Desktop, CLI and IDE use the host’s local store; it is separate from ChatGPT web memory.

Git & Pull Requests	Local Git diff, branch/worktree and change-review workflows. Authenticated Git tools/integrations can prepare and create pull requests; remote-provider permissions apply.
MCP & External Integrations	MCP supports external tools and data sources. Plugins and integrations can connect GitHub, GitLab beta, Slack, Linear and other services; availability and permissions differ.
Web Search	Web search is supported, with availability and network behavior determined by client, configuration and workspace policy.
API / SDK Access	Codex SDKs for TypeScript and Python, app-server for custom clients, and codex exec for automation/CI. Authentication and usage billing follow the chosen runtime.
Deployment Support	Can run deployment commands or connected tools with permission. Sites adds a build/publish workflow on eligible clients and plans; external hosting has separate credentials and costs.

Free Plan / Trial	Free access is included with limited model/client availability; Free and Go currently list GPT-6 Luna Standard in desktop, subject to rollout. A universal paid-plan trial duration is not disclosed.
Usage Limits / Extra Usage	Allowance depends on model, reasoning, speed and task. Plus/Standard Business publish 5-hour estimates; weekly limits may apply. Pro currently has no 5-hour limit. Extra credits and API billing are separate.
Team Administration	Business/Enterprise provide workspace administration; managed configuration controls Codex access, permissions, models and rollout. Enterprise adds broader governance and audit capabilities.
Code Privacy & Data Retention	Cloud inference processes supplied context unless a local provider is configured. Business/API data is not used for training by default. Retention varies by service, plan and controls; API abuse-monitoring logs are generally retained up to 30 days, with exceptions and eligible ZDR. No universal Codex retention duration is disclosed.
Self-Hosting	Local Codex CLI/app-server can run on infrastructure you manage, including local-model setups. This does not self-host the managed Codex Cloud service; hosted-service parity is not disclosed.
SSO / Enterprise Security	Business includes SAML SSO and MFA. Enterprise/Edu add controls such as SCIM, role-based access, audit/compliance access and retention/residency settings; exact scope depends on plan.

OpenAI Codex

About OpenAI Codex

Specifications

Overview & Compatibility

Coding Capabilities

Agents & Execution

AI Models & Codebase Context

Developer Workflow & Integrations

Pricing, Teams & Security

Compare OpenAI Codex

Compare before you choose

Similar AI models

Claude Code

Cursor

GitHub Copilot

Lovable