OpenAI Codex, 2026

Codex Isn't What It Was in 2021.

Today's Codex is OpenAI's agentic coding product: a CLI, IDE extensions and a cloud agent that edit real files and run real tests — bundled into ChatGPT plans including Plus, metered by token credits on a rolling 5-hour window. This guide covers what's included, where the limits bite, and what handles the overflow.

Bundled with ChatGPT Plus $20/mo · credits on a 5-hour window.Honest scope: we don't run Codex
Open @vustbot for overflow questions
CLI · IDE · cloud agentBundled in ChatGPT plansToken credits, 5-hour window

Honest scope

Codex is OpenAI's product — here's our actual place next to it

VUST doesn't resell or wrap Codex, and @vustbot cannot touch your repository. What it does well is the surrounding work: explain the stack trace, compare two architectures, draft the PR description, sanity-check the migration plan — frontier models per-use in Telegram, free tier first, no card. If you want a full agentic-coding switch instead, the /codex-alternative page compares real options.

Plan facts on this page reflect OpenAI's 2026 bundling and metering; verify current numbers on openai.com before purchase decisions.

See the difference

The disambiguation, the plan math, and the mid-task limit — honestly.

The name collision

Codex, 2021

The original Codex was a code-completion model behind early GitHub Copilot — retired long ago. Half the search results still mean that one.

Codex, 2026

Today's Codex is an agentic coding product on your OpenAI account: it reads your repo, edits real files, runs commands and tests, and iterates. Surfaces: a CLI, IDE extensions (VS Code, Cursor, Windsurf), a cloud agent at chatgpt.com/codex, plus desktop and iOS clients.

What it costs

The bundling

Codex has no standalone consumer price — it's included with ChatGPT plans (Plus at $20/mo included; Pro tiers give more capacity; Business/Enterprise can add usage-billed Codex-only seats since June 2026).

The metering

Since April 2026 usage is metered in token credits on a rolling 5-hour window — the practical limit heavy users actually hit. Power-developer overflow spend commonly lands in the $100–200/mo range on top of the seat.

Mid-task credit exhaustion

The moment

Deep in a refactor, the window's credits run out, and the agent stops until the window rolls.

The overflow move

Questions that don't need repo access — 'explain this stack trace', 'compare these two approaches', 'draft the migration plan' — can go to any strong chat model. That's the honest slot @vustbot fills: per-use frontier answers with no plan attached.

02·Practical use cases

Who this guide is for

ChatGPT subscribers

Finding out what your Plus/Pro seat already includes

Codex access is bundled — CLI, IDE extensions and the cloud agent draw from your plan's token-credit allowance. No second subscription.

Name-collision victims

Googling 'Codex' and landing in 2021

The old completion model is retired; today's Codex is an agentic product that edits files and runs tests. This page covers the current one only.

Limit planners

Budgeting real agentic work

Token credits on a rolling 5-hour window are the constraint that matters; heavy users commonly add $100–200/mo in overflow credits.

03·How it works

Codex in three facts

01What it is

OpenAI's agentic coding product: reads your repo, edits real files, runs commands and tests. Surfaces: CLI, VS Code/Cursor/Windsurf extensions, cloud agent at chatgpt.com/codex, desktop and iOS.

02How it's priced

Bundled into ChatGPT plans (Plus $20/mo included; Pro tiers carry more capacity). Since April 2026, usage meters token credits on a rolling 5-hour window; Business/Enterprise can add usage-billed Codex-only seats (June 2026).

03What powers it

GPT-5-series models — GPT-5.5 as the common default, plus selectable variants including a Codex-specialized GPT-5.3. The lineup moves; the CLI's /model command shows your account's current options.

04·Same tool · in Telegram

Telegram

For the questions that don't need your repo

@vustbot · Open @vustbot for frontier answers per-use — GPT-5.5, Claude Opus 4.8, Gemini — free tier, no card, while Codex's window rolls.

Open in Telegram

05·Quality & trust

Honest scope — Codex and us

We don't run Codex

No reselling, no wrapping, and @vustbot cannot touch your repository. That honest limit is also why it needs zero setup.

The overflow slot is real

Mid-task credit exhaustion sends the non-repo questions somewhere: explain the trace, weigh two designs, draft the plan. Frontier chat per-use covers exactly that, cardlessly.

Verify before buying

Plan bundling and metering described here reflect OpenAI's 2026 state at build time — check openai.com before purchase decisions; vendors move.

Frequently asked questions

The agentic-coding reading set.

Codex alternative

The switch-intent page: when you want out of the OpenAI stack.

Claude Code guide

Anthropic's agentic CLI — plans, limits, first session.

Cursor guide

The AI IDE — pricing, credits, when it fits.

Ready when you are

Codex for the repo. A chat for everything around it.

The agentic work stays in Codex; the explain/compare/draft overflow runs cardlessly in Telegram.

Open @vustbotWant to switch instead?