Free
Free
Usage: Quick coding tasks
PricingAI Coding Assistants
Codex Pricing: Plans, Credits, and Limits
Codex pricing is hybrid: ChatGPT plan access, included five-hour limits, optional ChatGPT or workspace credits, and API-key billing for local automation workflows.
Where most buyers should start
Start with Plus. It is the clearest baseline before you compare usage ceilings and higher-spend tiers.
Verified against Codex's official pricing pages on April 14, 2026.
Plan matrix
Pricing breakdown
Compare entry price, billing cadence, and feature access before you commit to annual spend or a higher tier.
Plans listed
7
Benchmark plan
Plus
Go
$8/mo
Usage: Lightweight coding tasks
Plus
$20/mo
Usage: GPT-5.4: 20-100 local msgs/5h; GPT-5.3-Codex: 30-150 local, 10-60 cloud, 20-50 reviews/5h
Pro $100
$100/mo
Usage: GPT-5.4: 200-1000 local msgs/5h; GPT-5.3-Codex: 300-1500 local, 100-600 cloud, 200-500 reviews/5h
Pro $200
$200/mo
Usage: GPT-5.4: 400-2000 local msgs/5h; GPT-5.3-Codex: 600-3000 local, 200-1200 cloud, 400-1000 reviews/5h
Business
Contact for pricing
Usage: Pay as you go; standard or usage-based Codex seats; workspace credits available
Enterprise & Edu
Contact for pricing
Usage: Contact sales; flexible pricing scales with credits and can remove fixed limits
Free plan
Available
Trial
No trial listed
Billing unit
Hybrid
Last checked
April 14, 2026
Editorial pricing notes
Pricing notes
Official plan caveats, contract details, and feature access notes that do not fit into the summary cards above.
Plan Snapshot
As of April 14, 2026, OpenAI lists Codex inside ChatGPT Free, Go, Plus, Pro, Business, Edu, and Enterprise.
Plan | Price | Best fit | Notes |
|---|---|---|---|
Free | $0/mo | Quick tests and short tasks | Limited included usage |
Go | $8/mo | Lightweight paid access | Lower-cost plan for lighter work |
Plus | $20/mo | Regular solo use | Web, CLI, IDE extension, iOS, and cloud integrations |
Pro $100 | $100/mo | Heavy daily use | 10x Plus limits through May 31, 2026 |
Pro $200 | $200/mo | Power users | 20x Plus limits |
Business | Pay as you go | Teams | Standard or usage-based Codex seats |
Enterprise & Edu | Contact sales | Large orgs | Flexible pricing can remove fixed limits |
Included Usage by Plan
OpenAI publishes five-hour ranges for local messages, cloud tasks, and GitHub code reviews.
Plan | GPT-5.4 local messages / 5h | GPT-5.3-Codex local / cloud / review / 5h |
|---|---|---|
Plus | 20-100 | 30-150 / 10-60 / 20-50 |
Pro $100 | 200-1000 | 300-1500 / 100-600 / 200-500 |
Pro $200 | 400-2000 | 600-3000 / 200-1200 / 400-1000 |
Business standard seats | 20-100 | 30-150 / 10-60 / 20-50 |
The same pricing page also points users toward GPT-5.4-mini when they want included limits to last longer.
Credits and API-Key Pricing
Codex does not stop at the base plan price. Plus and Pro users can buy ChatGPT credits after hitting included limits. Business, Edu, and Enterprise workspaces can buy workspace credits, and OpenAI says new Business and new Enterprise customers moved to token-based credit rates on April 2, 2026.
If you use Codex with an API key, OpenAI positions that route for automation in shared environments such as CI. The tradeoff is that you only get Codex in the CLI, SDK, or IDE extension, not cloud-only features like GitHub code review or Slack workflows.
Decision archive
Price history snapshots
Track how Codex pricing has moved over time, including plan lineup shifts, free access changes, and starting price updates.
1 archived snapshot
Starting price
$8
Access model
Free plan available
Plan count
8
Billing unit
Hybrid
Free
free
Monthly: $0/mo + usage
Annual: Not listed
Usage: Quick coding tasks
Go
go
Monthly: $8/mo + usage
Annual: Not listed
Usage: Lightweight coding tasks
Plus
plus
Monthly: $20/mo + usage
Annual: Not listed
Usage: GPT-5.4: 20-100 local msgs/5h; GPT-5.3-Codex: 30-150 local, 10-60 cloud, 20-50 reviews/5h
Pro $100
pro-100
Monthly: $100/mo + usage
Annual: Not listed
Usage: GPT-5.4: 200-1000 local msgs/5h; GPT-5.3-Codex: 300-1500 local, 100-600 cloud, 200-500 reviews/5h
Pro $200
pro-200
Monthly: $200/mo + usage
Annual: Not listed
Usage: GPT-5.4: 400-2000 local msgs/5h; GPT-5.3-Codex: 600-3000 local, 200-1200 cloud, 400-1000 reviews/5h
Business
business
Monthly: Not listed
Annual: Not listed
Usage: Pay as you go; standard or usage-based Codex seats; workspace credits available
Enterprise & Edu
enterprise-edu
Monthly: Not listed
Annual: Not listed
Usage: Contact sales; flexible pricing scales with credits and can remove fixed limits
API key workflow
api-key
Monthly: Not listed
Annual: Not listed
Usage: Usage-based token billing in CLI, SDK, and IDE only; no cloud-only GitHub or Slack features
Codex pricing FAQ
Is Codex included with ChatGPT?
Yes. As of April 14, 2026, OpenAI lists Codex inside ChatGPT Free, Go, Plus, Pro, Business, Edu, and Enterprise plans, with different limits and feature access by tier.
Can I use Codex with an API key instead of a ChatGPT plan?
Yes. OpenAI supports API-key sign-in for Codex in the CLI, SDK, and IDE extension. That route is usage-based and does not include cloud features such as GitHub code review or Slack integrations.
Does Codex support internet access and GitHub workflows?
Yes. Codex cloud tasks can be configured for public internet access, and OpenAI documents GitHub integrations for pull requests, reviews, and repository workflows.
Internal links
What to open next
Keep researching Codex
Pair the pricing snapshot with verdict, alternatives, and the full profile page.
ToolProfile: CodexOpenAI's cross-surface coding agent for local and cloud software work.Review: Codex Review: OpenAI's Coding Agent in 2026Codex is one of the strongest agentic coding assistants available if you want the same OpenAI workflow across ChatGPT, CLI, IDE, iOS, and desktop, but its blended plan-plus-credit pricing is still harder to understand than simpler rivals.Alternatives: Best Codex Alternatives in 2026Cursor, GitHub Copilot, and Windsurf are the clearest Codex alternatives if you want a more editor-first workflow, cheaper seat pricing, or a different balance between agent power and IDE convenience.FAQCodex FAQCommon product questions and structured answers.UpdatesCodex changelogRecent product updates, fixes, and feature releases.
Head-to-head pages
Open direct comparison pages before choosing a plan.
VSCodex vs Claude CodeTie overall: Claude Code wins on local control and provider flexibility, while Codex wins on price, cloud delegation, and GitHub review automation.VSCodex vs CursorCursor wins overall for most developers because its editor-first UX, clearer pricing, and broader model choice make it easier to adopt as a daily driver. Codex is stronger when you want a dedicated multi-agent control plane with deeper OpenAI-native automation.
Other reviews in this category
Sanity-check nearby tools before committing to a pricing tier.
ReviewClaude Code ReviewClaude Code is one of the strongest agentic coding tools for deep repo work, but its CLI-first workflow and hybrid pricing make it a better fit for serious developers than casual users.ReviewTabnine ReviewTabnine is a strong enterprise AI coding assistant for teams that care about privacy, deployment control, and governance, but its public pricing and mixed user feedback make it less compelling for budget-conscious individual developers.ReviewCursor ReviewCursor is one of the strongest AI coding editors available in 2026, especially for developers who want autonomous agents and deep codebase context, but its pricing is harder to predict than simpler rivals.