ChatGPT vs Codex (2026): Same Account, $20/mo Plus, but One Edits Your Repo and One Doesn't

The Difference Is the Loop, Not the Account

ChatGPT is conversational. You describe a problem, it returns code, you paste it into your editor, run it, and paste errors back. That loop is fast for small things and good for learning, but it has no awareness of your actual files, dependencies, or how a change behaves when run.

Codex is an agent with four surfaces: a CLI, an IDE extension for VS Code, Cursor, and Windsurf, a cloud agent at chatgpt.com/codex, a desktop app, and iOS. The cloud side adds automatic code review and a Slack integration. Each surface reads your repository, makes edits to real files, runs commands and tests, and iterates on the results. Because it works against the truth of your codebase, it catches integration issues a chat box cannot see. For the agent-vs-agent breakdown, see Codex vs Claude Code.

ChatGPT now also includes ChatGPT Work, an agentic surface inside ChatGPT. OpenAI's Codex pricing page states that ChatGPT Work uses the same pricing, credits, and usage limits as Codex. A long ChatGPT Work task and a long Codex CLI session spend the same allowance, so pick the surface by where the work lives: documents and files in ChatGPT Work, a Git repository in Codex.

Pricing: Plus Includes Both

You do not buy Codex separately. The same ChatGPT subscription that powers the chat box also powers Codex. Pro now comes in three tiers at $100, $200, and $500 per month. Only Pro $500 gets Ultrafast mode.

Plus and Pro users who hit the limit can buy ChatGPT credits. Business needs two or more users. Enterprise and Edu add priority processing and admin controls, and workspaces on flexible pricing buy shared credits. Full numbers across coding agents are on our Codex pricing breakdown and Morph pricing.

Usage Limits and the Shared Window

The query that drives most confusion: do ChatGPT and Codex eat from the same allowance? Yes for ChatGPT Work. OpenAI's Codex pricing page states that ChatGPT Work usage inside ChatGPT uses the same pricing, credits, and usage limits as Codex. Local messages and cloud chats share one allowance, and cloud tasks can use more of it than local messages. Pro plans currently have no five-hour limit.

Credit rates explain why the ranges are wide. GPT-6 Astra costs five times GPT-6.1 Sol per token, and GPT-6 Luna costs one twentieth of it. Speed modes multiply usage as well. Fast mode uses included limits at 2.5x the Standard rate. Ultrafast runs on GPT-6 Astra and GPT-6.1 Sol for Pro $500 and eligible Enterprise and Edu plans, and uses included limits at 8x.

Install Codex

ChatGPT needs no install; it runs in the browser and apps. Codex CLI is a separate binary. Mac or Linux:

curl -fsSL https://chatgpt.com/codex/install.sh | sh
# or
npm install -g @openai/codex
# or
brew install --cask codex

On Windows: powershell -ExecutionPolicy ByPass -c "irm https://chatgpt.com/codex/install.ps1 | iex". Then run codex and choose "Sign in with ChatGPT". The CLI is open source under Apache-2.0 at github.com/openai/codex, which has about 129,600 stars.

Models and Benchmarks

GPT-5.5 retired from Codex with ChatGPT sign-in on October 14, 2026; API-key sessions are unaffected. OpenAI now recommends GPT-6.1 Sol on Plus, Pro, Business, Enterprise, and Edu, with GPT-6 Astra for the hardest work and GPT-6 Luna for focused, repeatable tasks. Codex CLI switches between them with the /model command, and the GPT-5.6 models stay selectable during the rollout. You can also auth Codex with an OpenAI API key and pay per-token API rates, though API-key mode drops the cloud features.

On the terminal-loop benchmark Codex was built for, Codex with GPT-6.1 Sol ties GPT-6 Astra at 58.18%, so the cheaper model matches the top tier at one fifth of the credit rate. Claude Code with Opus 5.5 leads the board at 64.85%. See Gemini CLI vs Codex for the third option.

When ChatGPT Fits

When Codex Fits

Running Open Models for Codegen

Neither ChatGPT nor Codex lets you swap in an open-source model; both are tied to OpenAI weights on the OpenAI account. If you want to run DeepSeek or another open model for codegen, the constraint that matters is activation precision. Most serverless providers quantize activations to fp8 to cut cost, which degrades output. Morph serves DeepSeek with 16-bit (bf16) activations, no fp8 or int8 quantization, so responses match the reference weights, which is what you want when output fidelity matters.

For coding specifically, Morph runs codegen-tuned speculative decoding plus custom low-level kernels, which makes it the fastest and highest-quality option for coding agents rather than a general menu. morph-dsv4flash (DeepSeek V4 Flash) is $0.141953125 per 1M input tokens and $0.399625 per 1M output tokens. See Open Source Models and pricing.

Decision Framework

Frequently Asked Questions

What is the difference between ChatGPT and Codex?

Both are OpenAI on the same account, often the same model. ChatGPT is a chat box you copy code in and out of; Codex is an agent (CLI, IDE extension, cloud) that edits your repo and runs commands.

Is Codex free with ChatGPT Plus?

Yes. Plus at $20/mo includes Codex with an estimated 15 to 160 local messages per 5-hour window on GPT-6.1 Sol. Free and Go get GPT-6 Luna in the desktop app, subject to rollout.

Do they share the same usage limit?

ChatGPT Work and Codex share pricing, credits, and usage limits. Local and cloud Codex usage draw from one allowance. Pro plans currently have no five-hour limit.

Do they use the same model?

Often GPT-6.1 Sol, which OpenAI recommends on Plus and above. Codex CLI switches models with the /model command. GPT-5.5 retired from Codex with ChatGPT sign-in on October 14, 2026.

Which should I use?

ChatGPT for snippets and learning; Codex for multi-file changes, running tests, and end-to-end tasks. Most developers use both since they bill against one plan.