API boundary
ChatGPT plan access, Codex credits, and OpenAI API token billing are separate systems. API usage should be modeled from OpenAI API pricing, not ChatGPT plan allowances.
Pricing
Codex Pricing 2026: ChatGPT Access, Credits, and API Costs
Codex pricing depends on access path: ChatGPT plan access, Codex credits, Business seat options, Codex-only seats, or separate OpenAI API billing. The right plan depends on usage volume and team workflow.
AI Coding Assistants
Pricing checked May 26, 2026
Buyer guide
Where to start before you compare plans
Use this section to separate the buying route, billing boundary, and usage caveats before you follow a canonical pricing page.
Tracks
Which plan fits whom
ChatGPT plan access
Use the ChatGPT route when you want first-party Codex surfaces and plan-based usage limits instead of a separate developer-platform bill.
Best for: Solo developers and teams already choosing a ChatGPT subscription tier.
Avoid if: You need API keys, CI automation, or a separately metered platform budget.
Codex usage credits
Use the Codex rate card when you are estimating how extra usage consumes credits after included plan limits.
Best for: Buyers modeling heavier Codex sessions, parallel tasks, or faster processing modes.
Avoid if: You only need a simple yes/no answer about whether your ChatGPT plan unlocks Codex.
Business workspace
Use Business when seat mix, admin controls, and workspace credits matter more than a single individual subscription tier.
Best for: Teams that may mix standard ChatGPT seats with Codex-only usage-based seats.
Avoid if: You are a solo user without workspace governance needs.
API route
Use API pricing when you are building custom coding-agent systems, product integrations, or CI workflows with API keys.
Best for: Engineering teams with programmatic automation and separate platform spend.
Avoid if: You mainly want human-driven repository work inside Codex product surfaces.
Access paths
Subscription, API, and workspace routes
Use this section to separate what is bundled with Codex from routes that need a different pricing page, meter, or sales conversation.
Bundled appShared subscription quotaRecommended route
ChatGPT plan access
Codex is available to eligible ChatGPT plans across the Codex app, web, CLI, and IDE-extension surfaces.
Best for: Developers who already pay for ChatGPT and want bundled coding-agent usage.
Boundary: Codex capacity depends on the ChatGPT plan and may require add-on credits or a higher tier for heavy use.
Open ChatGPT pricing contextBundled appShared subscription quota
Codex product surfaces
Use Codex through first-party product surfaces rather than building directly against model APIs.
Best for: Interactive repository work, code review, and agent sessions managed by OpenAI product UX.
Boundary: This route is plan/quota based, not token-metered API billing.
Open Codex pricing contextDirect APISeparate API meter
Codex-family API models
Use OpenAI API pricing when building custom systems around Codex-family coding models.
Best for: Programmatic coding agents, internal tools, and product integrations.
Boundary: API spend is separate from ChatGPT subscription allowances and should be modeled by tokens or request units.
Open Codex pricing contextWatchouts
What buyers often miss
These are the boundary conditions and purchase traps worth checking before you optimize for the lowest headline number.
ChatGPT prices belong on ChatGPT pricing
Codex can be reached through ChatGPT plans, but this page should not duplicate the full ChatGPT plan table. Open the canonical ChatGPT pricing page for exact subscription tiers.
Credits are not the same as API spend
Buying or consuming Codex credits extends plan-based Codex usage. It does not prepay or discount OpenAI API token bills.
Business has two seat types
Standard ChatGPT seats bundle ChatGPT and Codex. Codex-only seats remove the fixed seat fee but require workspace credits for all activity.
The rate card is the Codex-owned fact layer
For heavy usage, model choice and token mix matter more than a copied subscription ladder. Use the Codex rate card for credits per 1M tokens.
Editorial pricing notes
Pricing notes
Official plan caveats, contract details, and feature access notes that do not fit into the summary cards above.
How Codex pricing works in 2026
Codex pricing is not one simple number. Buyers need to separate ChatGPT plan access, Codex credits, Business or Codex-only seats, and separate OpenAI API token billing before comparing cost.
Is Codex included with ChatGPT?
Codex access is often packaged through ChatGPT plans, but plan limits, credits, and workspace policies still matter. Treat ChatGPT subscription access and API-key usage as separate budget paths.
Codex credits vs OpenAI API billing
Codex credits are a product access and usage meter. OpenAI API billing is a separate developer billing lane. Teams should decide whether work belongs in ChatGPT/Codex surfaces, API workflows, or both.
Best Codex plan by use case
Use a lower paid ChatGPT plan for occasional coding help, higher individual tiers for heavier coding sessions, Business or Codex-only seats for managed teams, and API billing for custom workflows that run outside ChatGPT.
Buying path
Start with the ChatGPT plan access route when Codex is being used as part of the hosted OpenAI workspace. This page should be read as a route decision first: decide whether the buyer needs interactive Codex product access, workspace packaging, or model access for developer automation.
Upgrade triggers
Upgrade when coding work repeatedly runs into capacity, credit, or collaboration limits that block real delivery. A higher lane makes sense when Codex is used across multiple repositories, long-running tasks, or team workflows rather than occasional experiments.
API and team boundaries
Keep ChatGPT plan access, Codex usage credits, Business workspace access, and OpenAI API billing separate. Seats and workspace routes buy product access for users, while API usage belongs to a metered developer budget and should not be inferred from subscription allowances.
Final pricing check
Before committing, verify which Codex surface the team will use, how credits or limits are consumed, and whether the buyer needs workspace governance or token-priced model access. If the main job is programmatic integration, price the API route directly instead of treating a seat as the budget.
FAQ
Codex pricing FAQ
What is the cheapest paid plan that makes Codex feel usable?
Go at $8 per month in the US is the cheapest paid Codex entry, but it should be treated as limited access. Plus at $20 per month is the first dependable self-serve tier for focused weekly coding sessions.
Do Pro tiers change Codex quality or mostly usage?
The main change is headroom. The value of Pro is mostly more usage and higher limits, although OpenAI also positions the broader Pro package as the path for its highest-end ChatGPT model access.
Can a Business workspace buy Codex without buying ChatGPT seats for everyone?
Yes. OpenAI now offers Codex-only seats in Business. They have no fixed seat fee, but all usage is billed through workspace credits.
Do my ChatGPT payments cover API use?
No. ChatGPT plan access and API token billing are separate systems. If you use Codex with an API key or build your own workflows, you should expect a separate API bill.
What happens after I hit included Codex limits?
OpenAI lets eligible plans extend Codex usage with credits. That keeps you on the plan-based Codex path, which is still different from paying API token rates directly.
Are Codex API calls included in ChatGPT?
No. ChatGPT subscription access and OpenAI API billing are separate. If a workflow uses an API key, model that cost from the OpenAI API pricing path rather than the ChatGPT seat price.
What is the best Codex plan for code review?
For individual review work, start with the lowest ChatGPT plan that provides enough Codex usage. For team review workflows, compare Business controls, Codex-only seats, and API-based automation.
Internal links
What to open next
Keep researching Codex
Pair the pricing snapshot with verdict, alternatives, and the full profile page.
ToolProfile: CodexOpenAI's AI coding tool for coding agents, code review, ChatGPT plan access, Codex credits, and API billing paths.Review: Codex Review: Is OpenAI's GPT-5.5 Coding Agent Worth It?Codex is easier to recommend because GPT-5.5 brings stronger long-horizon coding, a 400K context window, and better token efficiency than GPT-5.4 for most users, but the product still asks buyers to navigate subscriptions, credits, and separate API billing.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.UpdatesCodex changelogRecent product updates, fixes, and feature releases.
Head-to-head pages
Open direct comparison pages before choosing a plan.
VSCodex vs WindsurfCodex is the preferred default when the buyer wants an autonomous coding agent that can handle repo-level tasks, run commands, produce diffs, support cloud delegation, and plug into review workflows. Windsurf is the better switch when the real purchase is an AI-native IDE with autocomplete, Cascade, previews, local context awareness, model routing, and a tighter in-editor flow.VSCodex vs GitHub CopilotCodex should be the default when the team is buying for deeper agentic coding work: repository understanding, task execution, command-running, tests, code review preparation, and reviewable diffs. GitHub Copilot should lead when the team values GitHub-native IDE assistance, pull request workflow, seat administration, and organization policy more than standalone agent depth.VSCodex vs CursorCursor is the better default for most developers because it combines an AI-native editor, broader model choice, and stronger day-to-day workflow tooling. Codex is stronger for multi-agent delegation, cross-tool reach, and direct OpenAI API usage.VSCodex vs Claude CodeThis comparison is a real tie: Claude Code is stronger for local-first coding workflows and deployment flexibility, while Codex is stronger for cloud orchestration and supervisory multi-agent work.
Other reviews in this category
Sanity-check nearby tools before committing to a pricing tier.
ReviewWindsurf ReviewWindsurf is one of the strongest AI-native IDEs available, with multi-file agent workflows, MCP, browser previews, and JetBrains support. Its main tradeoffs are hybrid overage pricing and a less mature ecosystem than safer editor-plus-plugin setups.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.ReviewGitHub Copilot ReviewGitHub Copilot remains one of the easiest AI coding assistants to adopt, combining GitHub-native workflow fit, broad IDE coverage, code review, and flexible plans from free to enterprise.ReviewCursor ReviewCursor is one of the strongest AI coding environments available, pairing deep codebase context with agentic workflows, but its usage-based pricing makes plan selection less predictable.