Modelpeers
OpenAI Codex charactervsGitHub Copilot character

OpenAI Codex vs GitHub Copilot: Which coding agent should you pay for?

Facts checked Oct 22, 2026. Every number links to its source.

Summary

Derived from sourced facts, not from builder opinions
  • Codex runs OpenAI models only. Copilot lists Claude, GPT-6 and Gemini models under one plan.
  • Copilot Pro costs $10 a month with $15 of AI Credits. Codex comes with ChatGPT: Plus is $20, and Free and Go ($8) get GPT-6 Luna in the desktop app.
  • You do not have to pick only one: Copilot Pro+ and Max can hand tasks to the OpenAI Codex agent, in preview.
  • On the official Terminal-Bench 4.0 board, Codex scored 58.18% with GPT-6 Astra or GPT-6.1 Sol at max effort. Copilot has no entry on that board.

Choose OpenAI Codex if

  • You already pay for ChatGPT, which includes Codex.
  • You want published usage ranges per model before you buy.
  • You want Codex cloud tasks with GitHub code review and Slack.
  • You run agents heavily and do not want usage capped by monthly AI Credits.

Choose GitHub Copilot if

  • You want Claude, Gemini and OpenAI models in one tool.
  • You want to start at $10 a month with monthly credits.
  • You want to assign GitHub issues to an agent and get pull requests back.
OpenAI Codex
GitHub Copilot

Follow both to get an email when either one changes its price, limits or behavior.

Plans

OpenAI Codex plans

Free
Free

GPT-6 Luna in the desktop app, rolling out

Go
$8/month

GPT-6 Luna in the desktop app, rolling out

Plus
$20/month

Web, CLI, IDE and iOS · GPT-6.1 Sol and GPT-6 Luna

Pro
$100/month

Plans at $100, $200 or $500 · no five-hour limit

Business
$25/month

Per user monthly · $20 billed annually

GitHub Copilot plans

Free
Free

Limited chat and agent usage

Pro
$10/month

$15 of GitHub AI Credits a month

Pro+
$39/month

$70 of AI Credits a month

Max
$100/month

$200 of AI Credits a month

Subscription agents are priced per seat with usage limits, so this compares plans rather than dividing a subscription by a guessed number of tasks.

Side by side

OpenAI CodexGitHub Copilot
MakerOpenAI
GitHub (Microsoft)
PlansFree $0 and Go $8 (GPT-6 Luna in desktop app, rolling out) · Plus $20 · Pro $100, $200 or $500 · Business $20/user annual or $25 monthly · Enterprise and Edu by sales · API key pay-as-you-go
Free $0 · Pro $10/month ($15 of AI Credits) · Pro+ $39 ($70 of credits) · Max $100 ($200 of credits)
Usage limitsPlus and Standard Business local messages per 5 hours: GPT-6 Astra 5-45, GPT-6.1 Sol 15-160, GPT-6 Sol 15-150, GPT-6 Luna 350-3,000 · Pro has no 5-hour limit · weekly limits may apply
Monthly GitHub AI Credits: Pro $15, Pro+ $70, Max $200 total (base plus flex allotment) · Free has limited chat and agent usage · extra credits purchasable on paid plans
Fast modesFast mode uses included limits at 2.5x · Ultrafast for Astra and 6.1 Sol at 8x
Not published
Recent model retirementGPT-5.5 retired from Codex with ChatGPT sign-in on 2026-10-14
Not published
PlatformsWeb, CLI, IDE extension, iOS, desktop app · API key mode for CLI, SDK and IDE without cloud features
Editors and IDEs, CLI, GitHub.com and GitHub Mobile on all plans · agent mode in VS Code, Visual Studio, JetBrains, Eclipse and more
Quality tracking (MarginLab)Codex with GPT-6 Sol/high: 54% latest day, 59% 7-day, 79% 30-day · 1-day and 7-day drops flagged but detection paused (last updated 2026-09-29)
Not published
BillingNot publishedUsage-based GitHub AI Credits on all plans since 2026-06-01, priced on input, output and cached tokens at API rates
ModelsNot publishedIncludes Claude Opus 5.5, Sonnet 5.5, Haiku 5.5, Fable 5.1 · GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol and Luna · Gemini 4 Argon (Pro+ and above) · Grok and Kimi K3 models · Claude Opus 4.8 and Opus 5 leave on 2026-11-16

Scores appear side by side only when both were published for the same test. Settings differ between sources, so small gaps can reverse under another harness.

Updates

OpenAI Codex

12 recorded incidents in the last 90 days.

GitHub Copilot

4 recorded incidents in the last 90 days.

Now available

Copilot Fusion adds local model routing in experimental preview

Copilot Fusion can now choose between supported on-device models and cloud models in Copilot CLI, the Copilot app and VS Code. MAI Code 1.1 Flash can be downloaded on supported Windows devices.

Who is affected:
Copilot users who want to run local models with automatic routing.
What to do:
Enable experimental local routing to try it.

Plan change

GitHub Enterprise now includes Copilot for every licensed user, Standalone is $10

Enterprises working with a GitHub or Microsoft account team can get Copilot included with GitHub Enterprise. Users without an Enterprise license get Copilot Standalone at $10 per user per month, with no monthly AI credits per seat.

Before

Separate Copilot seats plus AI usage to manage

After

Copilot included with GitHub Enterprise, usage metered against the enterprise budget

Who is affected:
Enterprise admins and users on GitHub Enterprise Cloud who manage Copilot seats and AI usage budgets.
What to do:
Talk to your sales team about moving an enterprise account to the new model, or keep your current plan.

Switching checklist

  1. Keep AGENTS.md: Copilot's cloud agent, VS Code chat and the Copilot CLI read it, and the nearest one in the tree wins.
  2. Move anything in AGENTS.override.md into AGENTS.md or .github/copilot-instructions.md. Copilot reads AGENTS.md, CLAUDE.md and GEMINI.md, not the override file.
  3. Rewrite each [mcp_servers] table from ~/.codex/config.toml as an entry in your editor's mcp.json.
  4. Add repository MCP servers on GitHub for the cloud agent and code review.
  5. If you want to keep Codex for some tasks, Copilot Pro+ and Max can delegate tasks to it, in preview.
  6. Compare your monthly use with Copilot's AI Credits: $15 on Pro, $70 on Pro+, $200 on Max.
  7. Run one real task in your own repository with both tools and compare the diffs before moving a team.

FAQ

Is Codex better than GitHub Copilot?

There is no shared test. Codex scored 58.18% on Terminal-Bench 4.0 with GPT-6 Astra or GPT-6.1 Sol, and Copilot has no entry on that board.

Can I use Codex inside GitHub Copilot?

Yes, in preview. Copilot Pro+ and Max can delegate tasks to third-party agents, including OpenAI Codex and Claude.

How much do Codex and Copilot cost?

Copilot is free, $10 (Pro), $39 (Pro+) or $100 (Max) a month. Codex comes with ChatGPT: Free, Go at $8, Plus at $20 and Pro at $100, $200 or $500.

Which models does Codex use?

OpenAI models only: GPT-6.1 Sol and GPT-6 Luna on Plus, with GPT-6 Astra and GPT-6 Sol also listed.

Does Copilot read AGENTS.md?

Yes, in the cloud agent, VS Code chat and the Copilot CLI. Visual Studio reads only copilot-instructions.md files.

Is Codex free?

Yes, on ChatGPT Free with GPT-6 Luna in the desktop app, still rolling out. Plus adds Codex on the web, CLI, IDE and iOS.

Are there usage limits on Copilot?

Yes. Each plan includes a monthly amount of GitHub AI Credits: $15 on Pro, $70 on Pro+, $200 on Max. Free has limited chat and agent usage.

Related comparisons

OpenAI Codex vs Claude CodeCursor vs GitHub CopilotOpenAI Codex vs CursorClaude Code vs GitHub CopilotOpenAI Codex pageGitHub Copilot page

Sources and method

Prices, specs and limits come from each maker's own pages. Benchmark scores come from independent benchmark publishers and the makers' announcements, with the setting each was measured in. Changes come from changelogs, deprecation pages and status pages. The summary is written from these facts only.