Home / Guides / How Much Does Codex Cost
How Much Does Codex Cost? A 2026 Pricing Breakdown
On paper, OpenAI Codex pricing is simple: $8, $20, or $100 to $500 a month through ChatGPT. But the April 2026 switch to token-based metering changed what those dollars actually buy you. Here's the real breakdown, plus the pay-per-token API option and how to track what you spend.
Last updated October 2026 · By Soren Starck
The Short Answer
Codex itself does not have a standalone subscription. You get it bundled with an OpenAI ChatGPT plan, or you pay per token through the OpenAI API. There are three common paths:
- ChatGPT Plus ($20/month): the cheapest plan with Codex in the CLI, the IDE extension and on the web (Go, at $8, covers lightweight tasks in the desktop app). Smaller token allowance, fine for short bursts.
- ChatGPT Pro ($100, $200 or $500/month): more usage than Plus (OpenAI says Pro 200 includes more than Pro 100 and Pro 500 the most, without giving a multiple), no five-hour limit for now, plus access to OpenAI's top reasoning models. Built for all-day Codex CLI use.
- OpenAI API (pay-per-token): no subscription, you pay only for tokens consumed. Predictable per-task, unpredictable per-month.
One thing to keep straight throughout this guide: the prices above are what you pay OpenAI for Codex access. That is completely separate from SessionWatcher, the $8.99 one-time Mac and Windows app that tracks your Codex usage. We'll cover SessionWatcher pricing at the end and keep it clearly labeled.
Codex Subscription Tiers (What You Pay OpenAI)
Codex access comes through ChatGPT subscriptions. The price is fixed; what varies is how many tokens you can burn before you get rate limited: a five-hour limit on Plus and Standard Business (none on Pro for now), with weekly limits that may also apply.
| Plan | Monthly Cost | Codex Allowance (per 5h) | Best For |
|---|---|---|---|
| ChatGPT Go | $8/mo | Not published | Lightweight coding tasks (GPT-6 Luna in the desktop app, subject to rollout) |
| ChatGPT Plus | $20/mo | 15–160 local messages (GPT-6.1 Sol) | Short bursts, general ChatGPT + light Codex |
| ChatGPT Pro 100 | $100/mo | No five-hour limit | Daily Codex use plus GPT-6.1 Sol in ChatGPT Work |
| ChatGPT Pro 200 | $200/mo | No five-hour limit | All-day Codex CLI, parallel agents, top reasoning |
| ChatGPT Pro 500 | $500/mo | No five-hour limit | Heaviest use, plus GPT-6 Astra Ultrafast access |
The Plus figure is OpenAI's own estimate of local messages per five-hour period on GPT-6.1 Sol, not a hard limit – OpenAI does not publish an exact token cap per tier, usage depends on the model and task, and allowances have fluctuated with promo boosts (the $100 Pro tier was promo-boosted toward 10x Plus through May 2026). Treat it as order-of-magnitude guidance, not a contractual limit. OpenAI publishes no estimate for Go, and Pro plans currently have no five-hour limit. Each tier can also face a longer secondary cap on top; that secondary window is plan-dependent and may be weekly or monthly.
Pro 200 changed on 29 September 2026: new subscriptions get a lower included allowance than before, at the same $200, and anyone who held Pro 200 between 22 and 29 September keeps the old allowance through 29 October (OpenAI's Pro tiers article). Whether Pro pays off for your own Codex use, and how GPT-6 Sol and Luna change the Plus math: is ChatGPT Pro worth it for Codex.
How the April 2026 Token Rate Card Changed the Math
Before April 2026, Codex limits were framed loosely as a number of messages. Since then, OpenAI meters Codex by tokens consumed, against a five-hour limit on Plus and Standard Business (none on Pro for now), with weekly limits that may also apply. This matters because your subscription dollar cost did not change, but what those dollars buy did.
OpenAI's Codex pricing page (checked 17 October 2026) says how much you can send depends on the model and on the size and complexity of your tasks, and that tasks that look similar can consume different amounts of your allowance. Long agent sessions, where Codex edits files, runs tools and reads a large context, are where that shows: a plan that feels generous for chat can run out mid-task.
In other words: under the token model, your effective cost per useful Codex hour depends entirely on your workflow. Light chat-style prompting stretches the Plus plan a long way. Heavy agentic coding can exhaust even Pro allowances and push you toward the API. For more on how the window itself behaves, see our Codex rate limits guide.
The Pay-Per-Token API Option
Instead of a subscription, you can run Codex against the OpenAI API and pay only for what you use. No monthly fee, no rate-limit window – just metered tokens. Here are the published API rates for the relevant models (USD per million tokens):
| Model | Input / M | Output / M | Cached Input / M |
|---|---|---|---|
| GPT-6.1 Sol | $2.00 | $10.00 | $0.10 |
| GPT-5.3 Codex | $1.75 | $14.00 | $0.175 |
| GPT-5 | $1.25 | $10.00 | $0.125 |
| GPT-5 mini | $0.25 | $2.00 | $0.025 |
Output tokens cost 5–8x more than input, and cached input costs a tenth of the input price or less. Codex sessions are output-heavy when generating code, which is why API bills add up faster than the input rate alone suggests.
Worked Examples
Let's put real numbers on it. These use GPT-5.3 Codex API rates ($1.75 input / $14 output per million), assuming a typical agentic split of about 80% input / 20% output before caching.
Example 1: A single feature task (~200K tokens)
160K input + 40K output. That's roughly 160K × $1.75/M = $0.28 input, plus 40K × $14/M = $0.56 output ≈ $0.84 per task on the API. Caching frequently-read context can cut the input portion meaningfully.
Example 2: A heavy 1-hour agentic session (~300K tokens)
240K input + 60K output ≈ $0.42 + $0.84 = roughly $1.26 per hour at the mid case, climbing toward $5–$10/hour on context-heavy fullstack work where the same large files are re-read. Over a 6-hour coding day that's anywhere from ~$8 to $50+ in API spend.
Example 3: Subscription vs API break-even
If your API spend regularly exceeds ~$20/month, ChatGPT Plus is cheaper (until you hit its token window). If it regularly exceeds ~$100–$200/month, a Pro subscription almost always wins on raw cost – provided your usage fits inside the rate-limit windows. The crossover point is entirely a function of how many tokens you burn, which is exactly why you need to measure it. Plug your own workflow into the free plan calculator to see which path is cheapest for you.
SessionWatcher
Stop guessing your Codex spend.
Track every token in real time.
Native app for the Mac menu bar and the Windows taskbar. Track Claude, Codex and 20 more tools' usage, costs, and rate limits in real time.
“Fast, simple, and does exactly what it should. Definitely worth it.”
@nicojerome on GitHub
macOS 14+. Free for 7 days, no credit card.
The Hidden Cost: Rate-Limit Lockouts
On a subscription, the headline price is only half the story. The token-based metering means heavy Codex users hit the five-hour limit on Plus and Standard Business (none on Pro for now), or a weekly limit where one applies, and get locked out mid-task, with no advance warning and no clear ETA. That lost time is a real cost that never shows up on an invoice.
The math is brutal. If your time is worth $75/hour and you lose just 2 hours/week to Codex lockouts:
2 hours/week × $75/hour = $150/week in lost productivity
$150/week × 4 weeks = $600/month in lost productivity
That $600 dwarfs the gap between the $20 Plus and $200 Pro plans. The way to avoid paying it is to see your token burn climbing before you hit the wall, so you can pace your work or wrap up the current task.
How to Track Your Actual Codex Cost
There are two practical ways to know what you're really spending:
1. The OpenAI usage dashboard: shows historical token usage and API spend, but with a delay. It won't tell you where you stand in your current weekly Codex cap or warn you before a lockout.
2. SessionWatcher: SessionWatcher for Codex sits in your Mac menu bar or Windows taskbar and shows token usage, estimated dollar cost, your percentage of the rate limit, and the weekly usage cap countdown – all in real time. You see the number tick up as you work, so you always know whether you're about to get locked out or burn an unexpected API bill.
SessionWatcher Pricing (Separate From OpenAI)
To be explicit: everything above is what you pay OpenAI for Codex. SessionWatcher is a separate, independent tool that simply tracks that usage. It is a one-time purchase, not a subscription:
| SessionWatcher | Price | What You Get |
|---|---|---|
| For Codex | $8.99 one-time | Real-time Codex usage, cost, and weekly usage cap tracking |
| Bundle | $19.99 one-time | Claude Code, Codex, and Cursor |
| Pro | $79 one-time or $24/year | All tools plus advanced features |
One licence key works on Mac and Windows: the $8.99 and Bundle licences cover 1 device, and Pro covers up to 5 devices, any mix of Macs and Windows PCs. If your company is paying for it, Pro for Teams is $40 per seat per year (or $4 per seat per month, 3-seat minimum) and gives each teammate their own Pro licence; it covers Macs only for now, and there is no central team dashboard, since each person sees their own usage.
All purchases come with a 14-day refund. At $8.99 once, SessionWatcher pays for itself the first time it helps you avoid a lockout or catch a runaway API bill – a fraction of a single month of any OpenAI plan.
SessionWatcherKnow your real Codex cost.
$8.99 once. Pays for itself day one.
Native app for the Mac menu bar and the Windows taskbar. Track Claude, Codex and 20 more tools' usage, costs, and rate limits in real time.
“Fast, simple, and does exactly what it should. Definitely worth it.”
@nicojerome on GitHub
macOS 14+. Free for 7 days, no credit card.
Frequently Asked Questions
How much does Codex cost per month?
Codex is bundled with a ChatGPT subscription. ChatGPT Go is $8/month for lightweight coding tasks, ChatGPT Plus is $20/month with the smaller token allowance, and ChatGPT Pro is $100, $200 or $500/month: OpenAI says Pro 200 includes more usage than Pro 100 and Pro 500 the most, without stating a multiple of Plus. Pro plans currently have no five-hour limit. You can also skip subscriptions and pay per token through the OpenAI API.
How did the April 2026 token rate card change Codex cost?
OpenAI now meters Codex by tokens consumed, against a five-hour limit on Plus and Standard Business (none on Pro for now) with weekly limits that may also apply, instead of a fixed message count. Your subscription dollar cost is unchanged; how much work fits under the limit depends on the model and on the size and complexity of your tasks (OpenAI's Codex pricing page, checked 17 October 2026).
What does Codex cost per token on the API?
GPT-5.3 Codex is $1.75 per million input tokens and $14 per million output tokens, with cached input at $0.175 (OpenAI's API pricing page, checked 18 October 2026). What an hour costs depends on how many tokens your sessions send and receive, so price a few days of your own usage before comparing it with a subscription.
How can I track my Codex costs?
SessionWatcher for Codex ($8.99 one-time, for Mac and Windows) tracks token usage, estimated dollar cost, rate-limit percentage, and the weekly usage cap in real time from your Mac menu bar or Windows taskbar. The OpenAI dashboard shows historical spend but with a delay.