Codex is a rate limit, not a rate. Plus gives 15 to 160 Sol messages per 5-hour window. Pro plans currently have no five-hour limit. Planner for Plus and Pro.
Codex has no price per task, and Plus still gives you 15 to 160 GPT-6.1 Sol messages per rolling 5-hour window, but Pro plans currently have no five-hour limit. OpenAI sells no separate Codex subscription. It is included in ChatGPT plans from $0 to $500 a month, so what you buy is an allowance, and what you plan is how fast you burn it.
Short answer: a solo developer who codes with Codex a few hours a day still fits on Plus at $20 if the five-hour window rarely trips, and moves to Pro at $100 for a larger included allowance and no five-hour wall. Move to Pro 500 only if Ultrafast is worth using included allowance at eight times the Standard rate. A five-person team is cheaper per head on Business at $20 a user billed annually than on five Pro 100 seats, but each Business seat still has the Plus-sized five-hour window. The API-key path is billed per token, has no window, and skips cloud features such as GitHub review and Slack. The numbers below come from OpenAI's pricing and help pages fetched on 17 November 2026; the planner recommendations are this guide's and are labelled as such.
A rate limit is not a rate
Per-token APIs price what you use. Codex plans price access to a pool. For Plus and Standard Business, OpenAI still meters that pool against a rolling 5-hour window, and weekly limits may also apply. The 5-hour window is the one Plus users feel: you hit it mid-afternoon, wait, and carry on. The weekly cap is the one that ends your Thursday.
That is no longer the Pro picture. OpenAI's Codex pricing page, which now lives at learn.chatgpt.com/docs/pricing (developers.openai.com/codex/pricing redirects there), says: "The estimates below show local messages per five-hour period for Plus and Standard Business. Pro plans currently have no five-hour limit." The help article on managing usage with GPT-6 Astra in Work and Codex repeats it in plan names: "Pro 100, Pro 200 and Pro 500 currently have no five-hour usage limit in Work and Codex. Your plan still has an included usage allowance." Check Settings → Usage for remaining allowance and reset times.
The message counts people quote are estimates, not guarantees. OpenAI publishes ranges per model, and the range is wide because a message that reads one file costs far less than a message that rewrites a module. Cloud tasks are the sharper edge: OpenAI says cloud chats may use more allowance than local messages, and you cannot change the default model for Codex cloud chats. OpenAI does not publish a weekly cap figure, or a current official multiplier of Pro versus Plus, on the pricing and help pages fetched for this update, so this guide does not give either.
When you run past the included allowance you can buy credits. OpenAI's pricing page does not list a single public purchase price; it says credit purchase prices and applicable discounts depend on your plan or agreement. Credits bought on Pro 100 or Pro 200 still do not unlock Ultrafast. The Pro tiers help page says: "At launch, buying credits on Pro 100 or Pro 200 does not unlock Ultrafast."
The plans and what a window buys
| Plan | Price | Five-hour window | Notes |
|---|---|---|---|
| Free | $0 | Not published as a message range | Entry access |
| Go | $8 a month | Not published as a message range | Entry paid tier |
| Plus | $20 a month | Yes; official local-message ranges below | Cloud floor; Linear and Slack integrations need a paid plan |
| Pro 100 | $100 a month | Currently none | Still has an included allowance. The Pro tiers help page says Pro 100 and Pro 500 now include twice their previous Work and Codex allowance. Official pages do not publish a current multiplier versus Plus |
| Pro 200 | $200 a month | Currently none | Available again for new subscriptions; more usage than Pro 100; Ultrafast not included |
| Pro 500 | $500 a month | Currently none | Highest included usage of the three Pro plans; includes Ultrafast |
| Business | $20 per user a month annual, $25 monthly | Standard Business uses the same official ranges as Plus | Two or more users |
The official pricing page, fetched on 17 November 2026, puts the Plus and Standard Business 5-hour window at these local-message ranges. Pro is not in this table, because those pages no longer give Pro a five-hour message count.
| Model | Messages per 5-hour window (Plus and Standard Business) |
|---|---|
| GPT-6 Astra | 5 to 45 |
| GPT-6.1 Sol | 15 to 160 |
| GPT-6.1 Terra | 35 to 285 |
| GPT-6 Sol | 15 to 150 |
| GPT-6 Luna | 350 to 3,000 |
Treat those ranges as planning numbers, not a guaranteed message cap. Older Sol, Terra and Luna generation estimates were 10 to 100, 25 to 200 and 250 to 2,000 for Plus, which shows how much these ranges move when the models change. The earlier version of this post also multiplied the Plus window by five and called that Pro 100. That derived column is withdrawn: official pages now say Pro has no five-hour limit, and they no longer quote a current Pro-versus-Plus multiplier that can be used to derive a Pro window. Re-read the help page each quarter.
Pro 500 and Ultrafast: speed you pay for in allowance
Pro 500 costs $500 a month, has the highest included usage of the Pro plans, and includes Ultrafast for GPT-6 Astra and GPT-6.1 Sol. OpenAI's speed page says GPT-6 Astra Ultrafast generates tokens up to eight times faster than GPT-6 Astra in Standard mode in Codex. On included subscription usage, Ultrafast bills at eight times the Standard rate for the selected model; after that allowance is used, purchased credits are billed at six times the Standard credit rate. Those are official consumption rates. Fast mode, for comparison, uses included limits at 2.5 times the Standard rate and purchased credits at two times.
Read that against the price. If you run Ultrafast all day, you burn included allowance eight times faster than Standard. The product is for people whose bottleneck is waiting for tokens, not running out of them: a founder in a live debugging session, a consultant on an hourly rate where lower latency pays for itself. If your bottleneck is thinking time, spend $100 on Pro 100, which currently has no five-hour wall and does not include Ultrafast.
The API-key path for the same model family is different again. The official API pricing page (platform.openai.com/docs/pricing, which redirects to developers.openai.com/api/docs/pricing), fetched on 17 November 2026, lists GPT-6.1 Sol Standard short-context rates at $2.00 per million input tokens, $0.10 cached input and $10.00 per million output. A task that sends 200K input tokens (160K of them cached) and returns 20K output costs about $0.30 on those prices: $0.08 uncached input, $0.016 cached input and $0.20 output. This guide assumes those token counts. At roughly thirty cents a task, a $20 Plus plan equals about 67 such tasks by API, and the plan gives you a recurring window instead. The API path also has no 5-hour wall, and it excludes the cloud features: GitHub review and Slack are plan-only.
Planner: a solo developer and a five-person team
Pick by how often you exhaust the limit that actually applies to your plan, not by how many hours you code. A good habit: for one week, note every time Codex tells you the allowance is spent, and check Settings → Usage for which limit it was. On Plus or Standard Business, zero five-hour window hits means you are on the right plan or an oversized one. Twice a week means you are near the edge. Daily means move up a tier. On Pro, watch the included allowance and any weekly reset, because there is currently no five-hour window to hit.
| Profile | Plan | Monthly cost | Reasoning |
|---|---|---|---|
| Solo, part-time, local edits | Plus | $20 | Cloud floor; Luna-class models stretch to 350 to 3,000 messages a window |
| Solo, full-time, heavy cloud tasks | Pro 100 | $100 | Larger included allowance than Plus, and currently no five-hour wall; one account |
| Solo, latency-bound, billable by the hour | Pro 500 | $500 | Only if Ultrafast's lower latency, at 8x included-usage burn, pays for itself |
| Solo with a pipeline script | API key | Metered | No window, no cloud features |
| Team of five, mixed use | Business, annual | $100 ($20 x 5) | Plus-sized five-hour window per seat; $125 billed monthly |
| Team of five, one heavy user | Business for four, plus a personal Pro 100 | $180 | Heavy user gets a Pro allowance with no five-hour wall; others stay at seat price |
The five-person Business plan costs the same $100 as one Pro 100 seat, and gives each person a Plus-sized five-hour window. If usage is spread evenly and nobody is bumping that window, five separate Plus-sized seats are the better fit. If one person uses 80% of the team's Codex time, that person still hits a Plus-sized five-hour wall on a Business seat, while a Pro seat currently has no five-hour limit. Fix it with a Pro seat for them, not with a bigger plan for everyone.
Model your own mix on the Agent Run Cost Simulator, and price API-key work on the AI Prompt Cost Calculator. For the cheaper end of the model market, the Haiku 5.5 pricing breakdown shows what a per-token budget looks like at $0.10 and $0.50.
Three signals say you are on the wrong plan. If you are on Plus or Standard Business and you hit the 5-hour window more than twice a week, the window is your bottleneck and a higher tier or credits pay back. If you never hit your limit and your usage sits well under what you expect the weekly cap to be, you are paying for headroom you do not use, and you can drop a tier. If your overflow credits regularly cost more than the gap to the next plan, upgrade. Run that arithmetic from the purchase price shown on your usage page, not from a single published dollar-per-credit figure: the official pricing page says that price depends on your plan or agreement.
The verdict for most readers of this blog: start on Plus, track five-hour window hits for two weeks, and move to Pro 100 when you hit it twice a week. Skip Pro 500 unless you can name the hourly value of lower latency, knowing Astra Ultrafast is quoted as up to eight times faster and burns included allowance at eight times the Standard rate. Skip the API-key path unless you run Codex from scripts and do not need the cloud features. Re-read the pricing page when you next review the plan. On 17 November 2026 it said Pro plans currently have no five-hour limit, which is a change from the October window math this post originally used.
Burning the window slower
You cannot raise the published Plus or Business window, but you can lower the burn per task. Three habits matter more than the plan tier.
Keep instructions short and stable. Every message carries your standing instructions. A bloated AGENTS.md or CLAUDE.md-style file costs every call, and a stable prefix is what caching rewards. The CLAUDE.md Starter Templates Pack shows tight versions of those files that also carry over to Codex-style agents.
Scope tasks before you send them. A vague request makes the agent explore. A request that names the file, the function and the test it must pass costs a fraction. Cloud tasks suffer most from vagueness, because they spin up an environment each time.
Watch spend as an operations metric. The AI Agent Ops Bundle includes the logging and budget-guard patterns that turn another limit hit into a chart. When the chart says you hit the window on Tuesdays after a particular kind of task, you change the task, not the plan.
Quick answers
How much does Codex cost?
There is no separate subscription. Codex is included in ChatGPT plans: Free $0, Go $8, Plus $20, Pro from $100 and Business at $20 per user a month billed annually or $25 monthly. The API-key path bills per token instead.
How many Codex messages are in a 5-hour window?
On Plus and Standard Business, the official ranges fetched on 17 November 2026 are 15 to 160 for GPT-6.1 Sol, 35 to 285 for GPT-6.1 Terra, 15 to 150 for GPT-6 Sol, 5 to 45 for GPT-6 Astra and 350 to 3,000 for GPT-6 Luna. Pro 100, Pro 200 and Pro 500 currently have no five-hour usage limit in Work and Codex.
What does Pro 500 add?
$500 a month buys the highest included usage of the Pro plans and access to Ultrafast on GPT-6 Astra and GPT-6.1 Sol. Astra Ultrafast is quoted as generating tokens up to eight times faster than Standard, and Ultrafast burns included allowance at eight times the Standard rate, then purchased credits at six times. Credits bought on Pro 100 or 200 do not unlock it.
Every product mentioned is available at wowhow.cloud — pay once, ship forever.
Written by
WOWHOW
The WOWHOW team brings 14+ years of production engineering experience. Every tool and product in the catalog is built, tested, and curated in-house.
Monday memo · free
One insight, every Monday. 7am IST.
1 field report, 3 links, 1 tool we actually use. No fluff, no spam.
Beyond the writing
Need production-ready templates?
Free browser tools with no signup, plus premium dev templates and starter kits.
Comments · 0
Beta: comments are stored locally on your device and not visible to other readers.
No comments yet. Be the first to share your thoughts.