--- type: analysis slug: guide-codex-cli-whats-new title: "What is new in OpenAI Codex CLI" description: "Codex is OpenAI's coding agent, available as a terminal CLI, an IDE extension (VS Code, Cursor, Windsurf, with Xcode and JetBrains integrations), the ChatGPT desktop app and Codex Cloud, where tasks run in published cloud environments. It is for developers who want an agent to read a repo, edit code" published_at: 2026-10-27T15:00:00.000Z topics: ["tools","developer_tools"] source_urls: ["https://learn.chatgpt.com/docs/codex/cli","https://learn.chatgpt.com/docs/agent-approvals-security","https://learn.chatgpt.com/docs/agent-configuration/agents-md","https://learn.chatgpt.com/docs/non-interactive-mode","https://learn.chatgpt.com/docs/codex/ide","https://learn.chatgpt.com/docs/codex/cloud","https://learn.chatgpt.com/docs/models","https://learn.chatgpt.com/docs/pricing","https://github.com/openai/codex/releases/tag/rust-v0.164.0","https://learn.chatgpt.com/docs/changelog"] author: "Andrey Reshetnikov" author_profile: https://newruntime.com/owner-profile.md --- Codex is OpenAI's coding agent, available as a terminal CLI, an IDE extension (VS Code, Cursor, Windsurf, with Xcode and JetBrains integrations), the ChatGPT desktop app and Codex Cloud, where tasks run in published cloud environments. It is for developers who want an agent to read a repo, edit code and run commands under explicit sandbox and approval controls, and to script it in CI with codex exec. Recent changes center on the GPT-6.1 Sol model replacing GPT-5.5 for ChatGPT sign-in, the retirement of the untrusted approval policy and --full-auto, and CLI 0.164.0 adding /presets and inline /model and /permissions arguments. Codex usage comes with ChatGPT plans from Plus up, or is billed at API rates with an API key. *Field guide compiled 2026-10-23 from the official documentation, pricing pages and changelogs linked below; every line links to the page that states it.* ## What it does - **Codex CLI.** Lets Codex inspect files, make edits and run tools already installed on your machine from the terminal, with your choice of model, reasoning effort, permissions and commands. How: Install on macOS/Linux with curl -fsSL https://chatgpt.com/codex/install.sh | sh, sign in, and run codex from a project directory. [source](https://learn.chatgpt.com/docs/codex/cli) - **Sandbox mode.** Controls what Codex can technically do when it executes model-generated commands: read-only, workspace-write (the default for CLI and IDE: writes limited to the active workspace, no network) or danger-full-access. OS-level mechanisms enforce it. How: --sandbox read-only|workspace-write|danger-full-access, or sandboxmode in config.toml; switch to read-only mid-session with /permissions. [source](https://learn.chatgpt.com/docs/agent-approvals-security) - **Approval policy.** Controls when Codex must ask before acting, for example leaving the sandbox or using the network. The Auto preset is workspace-write plus on-request approvals; a granular policy keeps selected prompt categories interactive, and approvalsreviewer=autoreview routes eligible requests to Auto-review. How: --ask-for-approval on-request|never (-a never), or approvalpolicy in config.toml; --dangerously-bypass-approvals-and-sandbox (alias --yolo) removes both layers. [source](https://learn.chatgpt.com/docs/agent-approvals-security) - **AGENTS.md.** Instruction files Codex reads before doing any work: a global file in ~/.codex plus files from the project root down to the current directory, concatenated so closer files override earlier guidance. How: Create ~/.codex/AGENTS.md for personal defaults and AGENTS.md in the repo (AGENTS.override.md for temporary overrides); the combined size is capped by projectdocmaxbytes, 32 KiB by default. [source](https://learn.chatgpt.com/docs/agent-configuration/agents-md) - **codex exec.** Non-interactive mode for scripts and CI: streams progress to stderr and prints only the final agent message to stdout, accepts piped stdin as context, and can emit a JSON Lines event stream or a final response matching a JSON Schema. How: codex exec "task"; add --json for JSONL events, --output-schema ./schema.json -o out.json for structured output, --ephemeral to skip saving session files, and --sandbox workspace-write to allow edits. [source](https://learn.chatgpt.com/docs/non-interactive-mode) - **Codex IDE extension.** Works beside your code with open files and selections as context, shows diffs in place, and can hand longer work to Codex cloud. How: Install the openai.chatgpt extension in VS Code, Cursor or Windsurf and choose the Codex icon (or run Codex: Open Codex Sidebar); in JetBrains open AI Chat and select Codex; in Xcode choose Codex as the agent. [source](https://learn.chatgpt.com/docs/codex/ide) - **Codex Cloud.** Runs coding tasks in the cloud from a published environment; each task gets its own workspace and keeps working while your computer is asleep, and you review changes, request follow-ups, commit or open a pull request. How: In ChatGPT on web or desktop choose Work in Cloud, create or select an environment, connect GitHub repositories, publish, then start a task. [source](https://learn.chatgpt.com/docs/codex/cloud) - **GPT-6.1 Sol.** The recommended model for complex coding and agentic work, with near-Astra performance at lower cost; GPT-6 Luna is recommended for focused, repeatable tasks. Max gives more reasoning time, and Ultra splits work across subagents. How: codex --model gpt-6.1-sol, codex exec -m gpt-6.1-sol, /model in the CLI, or model = "gpt-6.1-sol" in config.toml. [source](https://learn.chatgpt.com/docs/models) ## Modes - **Auto (preset).** --sandbox workspace-write --ask-for-approval on-request; reads, edits and runs commands in the workspace, asks to edit outside it or use the network. [source](https://learn.chatgpt.com/docs/agent-approvals-security) - **Safe read-only browsing.** --sandbox read-only --ask-for-approval on-request. [source](https://learn.chatgpt.com/docs/agent-approvals-security) - **Read-only non-interactive (CI).** --sandbox read-only --ask-for-approval never; never asks for approval. [source](https://learn.chatgpt.com/docs/agent-approvals-security) - **Auto-review mode.** Same boundary as on-request, but eligible approval requests go to Auto-review (approvalsreviewer = "autoreview"). [source](https://learn.chatgpt.com/docs/agent-approvals-security) - **Dangerous full access.** --dangerously-bypass-approvals-and-sandbox (alias --yolo): no sandbox, no approvals, not recommended. [source](https://learn.chatgpt.com/docs/agent-approvals-security) ## Pricing and limits - **Free:** $0/month. GPT-6 Luna at Standard speed in the desktop app, subject to rollout [source](https://learn.chatgpt.com/docs/pricing) - **Go:** $8/month. GPT-6 Luna at Standard speed in the desktop app, subject to rollout [source](https://learn.chatgpt.com/docs/pricing) - **Plus:** $20/month. Codex on the web, CLI, IDE extension and iOS; GPT-6.1 Sol and GPT-6 Luna; cloud integrations like automatic code review and Slack; extendable with ChatGPT credits [source](https://learn.chatgpt.com/docs/pricing) - **Pro:** From $100/month (plans at $100, $200, or $500 USD per month). Everything in Plus; Ultrafast mode access on Pro $500 [source](https://learn.chatgpt.com/docs/pricing) - **Business:** $20 / user / month (2+ users, billed annually. $25 per user per month when billed monthly.). Larger virtual machines for cloud chats, admin controls, SAML SSO, no training on business data by default [source](https://learn.chatgpt.com/docs/pricing) ## Recent changes - 2026-10-23: Codex CLI 0.164.0: ten numbered /presets slots for reusable prompts and slash commands, inline /model and /permissions arguments, image previews on Kitty or Sixel terminals, enterprise MCP authentication, and resumed sessions restoring saved thread settings. [source](https://github.com/openai/codex/releases/tag/rust-v0.164.0) - 2026-10-14: GPT-5.5 retired from Codex for users signed in with ChatGPT; use GPT-6.1 Sol where available. [source](https://learn.chatgpt.com/docs/changelog) - 2026-10-09: Composer predictions beta suggests a follow-up prompt in the Codex desktop app; press Tab to accept as an editable draft. [source](https://learn.chatgpt.com/docs/changelog) - 2026-10-08: GPT-6.1 Sol Ultrafast mode launched in Codex and ChatGPT Work for Pro $500 and eligible Enterprise and Edu plans. [source](https://learn.chatgpt.com/docs/changelog) - 2026-09-29: GPT-6.1 Sol added to Codex and ChatGPT Work. [source](https://learn.chatgpt.com/docs/changelog) ## Traps - --full-auto is no longer supported in codex exec; scripts must switch to --sandbox workspace-write or --approve-for-me. [source](https://learn.chatgpt.com/docs/non-interactive-mode) - codex exec runs in a read-only sandbox by default, so CI jobs that need edits must pass --sandbox workspace-write. [source](https://learn.chatgpt.com/docs/non-interactive-mode) - approvalpolicy = "untrusted" is no longer supported; use sandboxmode = "read-only" with approvalpolicy = "on-request" instead. [source](https://learn.chatgpt.com/docs/agent-approvals-security) - In the default workspace-write sandbox, network access is off unless enabled in configuration, and writableroot/.git stays read-only. [source](https://learn.chatgpt.com/docs/agent-approvals-security) - AGENTS.md files stop being added once the combined size reaches projectdocmaxbytes (32 KiB by default). [source](https://learn.chatgpt.com/docs/agent-configuration/agents-md) - GPT-5.5 retired from Codex for ChatGPT sign-in on October 14, 2026; saved settings, managed configs, custom agents and scripts that select gpt-5.5 need updating. API-key sessions are unaffected. [source](https://learn.chatgpt.com/docs/models) Author: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json ## Continue in the graph Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`. - topic hub: [Tools](https://newruntime.com/topics/tools.md): Explore the tools topic hub. - topic hub: [Developer Tools](https://newruntime.com/topics/developer-tools.md): Explore the developer_tools topic hub. - collection: [Analysis](https://newruntime.com/analysis.json): Open the latest authorial analysis. - collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph. - whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)