TL;DR
Codex pricing is your ChatGPT plan: Free $0, Go $8/mo, Plus $20/mo, Pro $100, $200, or $500/mo, Business $20/user/mo annual, Enterprise custom. There is no separate Codex subscription. Plus gets 15-160 GPT-6.1 Sol messages per 5-hour window. An API key skips the limits and bills GPT-6.1 Sol at $2/$10 per million tokens.
Usage is metered in credits, and every credit rate equals the model's API price at 4 cents per credit. OpenAI publishes local message allowances per 5-hour period for each model: on Plus, 5-45 on GPT-6 Astra, 15-160 on GPT-6.1 Sol, 15-150 on GPT-6 Sol, and 350-3,000 on GPT-6 Luna. Weekly limits sit on top with no published numbers. Plus has the 5-hour window again since August 25, 2026. Pro plans have no five-hour limit for now. Pro $200 takes new subscribers again at a lower allowance, and Pro $500 adds GPT-6 Astra Ultrafast. A multi-file refactor costs about 90 cents on GPT-6 Sol, 5 cents on Luna, and $4.50 on Astra.
As of October 7: Pro $200 is open to new subscribers again with a lower allowance (grandfathered accounts keep the old one through October 29), Pro $500 is listed with GPT-6 Astra Ultrafast, and GPT-6.1 Sol is rolling out to Codex on Plus, Pro, Business, Enterprise, and Edu at $2/$10 per million tokens. September 22: GPT-6 Sol and GPT-6 Luna started rolling out to Codex for Plus, Pro, Business, Enterprise, and Edu. Free and Go get Luna in the desktop app. API prices are half of GPT-5.6: Sol $2/$10, Luna $0.10/$0.50 per million tokens. September 10: OpenAI paused new sign-ups and upgrades to Pro $200. September 14: GPT-5.3-Codex-Spark was removed from the Codex app, CLI, and IDE (gpt-5.3-codex stays on the API). September 5: the codex mcp-server command was removed from Codex CLI. September 3: GPT-6 Astra shipped at $10/$50 and draws from the same Codex allowance. August 25: the 5-hour window returned for Plus. Pro stays exempt for now. October 14: GPT-5.5 retires from Codex on all plans. Plan and credit figures come from OpenAI's pricing page at learn.chatgpt.com/docs/pricing (developers.openai.com/codex/pricing redirects there).
Codex Plans and Prices
Codex ships inside ChatGPT Free, Go, Plus, Pro, Business, and Enterprise. Six tiers, plus an API key that needs no plan at all:
| Plan | Price | Codex models | Key details |
|---|---|---|---|
| Free | $0/mo | GPT-6 Luna (Standard speed, desktop app) | Quick coding tasks. No CLI, no published allowance, no top-ups |
| Go | $8/mo | GPT-6 Luna (Standard speed, desktop app) | Lightweight coding tasks. No CLI, no top-ups |
| ChatGPT Plus | $20/mo | GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol, Luna | 15-160 GPT-6.1 Sol msgs / 5h. 5-hour window active. Can buy credits |
| ChatGPT Pro 100 (5x) | $100/mo | Everything in Plus | No 5-hour limit. Weekly limits apply |
| ChatGPT Pro 200 (20x) | $200/mo | Everything in Plus | Open again. New non-grandfathered subscriptions get a lower allowance |
| ChatGPT Pro 500 | $500/mo | Everything in Pro, plus GPT-6 Astra Ultrafast | Highest Pro usage. Ultrafast uses it at 8x the Standard rate |
| Business | $20/user/mo annual | GPT-6 Astra, Sol, Luna | $25 monthly. Premium seats $100/$125 with 5x usage |
| Enterprise / Edu | Custom | Everything in Business | Flexible pricing runs on credits, no fixed rate limits |
| API key | Per token | Any model your key can call | No 5-hour window, no weekly cap |
Plus and Pro users who reach a limit can buy additional credits. Business, Edu, and Enterprise workspaces on flexible pricing buy workspace credits. Free and Go cannot buy credits at all, which makes Plus the real floor for anyone who hits a limit mid-task.
Codex Plus: What $20 Per Month Buys (Plus vs Pro)
There is no product called Codex Plus. The tier is ChatGPT Plus at $20/month, and Codex is included in it. OpenAI's own pitch for the tier is that it will "power a few focused coding sessions each week." That is accurate.
- Local messages per 5 hours: 5-45 on GPT-6 Astra, 15-160 on GPT-6.1 Sol, 15-150 on GPT-6 Sol, 350-3,000 on GPT-6 Luna. Local messages and cloud chats share one allowance.
- Legacy models: 10-100 on GPT-5.6 Sol, 25-200 on GPT-5.6 Terra, 250-2,000 on GPT-5.6 Luna. GPT-5.5 leaves Codex on October 14, 2026.
- Credit top-ups: available. Plus is the cheapest plan that can pay to keep going instead of waiting for a reset.
- 5-hour window: active since August 25, 2026, with a weekly limit on top.
The ranges are wide because the limits are credit-based underneath. A one-line fix sits near the top of the range. An agentic run that reads thirty files and writes ten sits near the bottom. Plus vs Pro comes down to two things: Pro multiplies the allowance, and Pro currently has no 5-hour window at all.
Codex Pro: The $100, $200, and $500 Tiers
Pro now comes in three monthly plans, which OpenAI's help center calls Pro 100, Pro 200, and Pro 500. Pro 200 includes more usage than Pro 100, and Pro 500 has the highest included usage of the three. Pro is billed monthly only.
| Pro plan | Price | GPT-6 Astra Ultrafast | Status (October 7, 2026) |
|---|---|---|---|
| Pro 100 (5x) | $100/mo | Not included | Open |
| Pro 200 (20x) | $200/mo | Not included | Open again, lower allowance for new subscribers |
| Pro 500 | $500/mo | Included | Open |
OpenAI's pricing page now says Pro plans have no five-hour limit, and it no longer prints per-window message counts for Pro. The September tables listed 25-225 GPT-6 Astra and 70-700 GPT-6 Sol messages per 5 hours on Pro 5x, and 100-900 and 300-3,000 on Pro 20x. Treat those as history. Weekly limits still apply.
Pro 200 took a detour. On September 10, OpenAI paused new sign-ups and upgrades to it. It is open again, but new subscriptions that are not grandfathered get a lower included allowance than before at the same $200/month. Grandfathering covers anyone with an active Pro 200 subscription at any point from September 22 through 10 a.m. Pacific Time on September 29, 2026. Those accounts keep the previous allowance through October 29, 2026, then move to the lower one.
Pro 500 is the only Pro plan with GPT-6 Astra Ultrafast, which generates tokens up to 8x faster than GPT-6 Astra. Ultrafast uses included usage at 8x the Standard rate and then draws from credits. Buying credits on Pro 100 or Pro 200 does not unlock it. Fast mode on any plan uses included usage at 2.5x.
Pro also buys GPT-6 Pro in ChatGPT Chat. GPT-6 Pro is a ChatGPT name for GPT-6 Astra in Pro mode. There is no API model called GPT-6 Pro. It has weekly caps, even on the top plan: 200 per week on Pro $200 and 50 per week on Pro $100, shared with GPT-5.6 Sol Pro. Business Premium seats get 50 per week and Business Standard seats get 15 per month. Plus has no GPT-6 Pro in Chat, only Astra in Codex and Work.
Codex Usage Limits: 5-Hour Window and Weekly Cap
Codex usage is governed by two ceilings. A rolling 5-hour window (where it applies) and a weekly limit. OpenAI publishes estimated local messages per 5-hour period for each model and states that "weekly limits may also apply" with no numbers. The current GPT-6 tables:
| Plan | GPT-6 Astra / 5h | GPT-6.1 Sol / 5h | GPT-6 Sol / 5h | GPT-6 Luna / 5h |
|---|---|---|---|---|
| Plus ($20) | 5-45 | 15-160 | 15-150 | 350-3,000 |
| Business Standard ($20/user) | 5-45 | 15-160 | 15-150 | 350-3,000 |
| Pro ($100 / $200 / $500) | No 5-hour limit | No 5-hour limit | No 5-hour limit | No 5-hour limit |
| API key | Usage-based | Usage-based | Usage-based | Usage-based |
GPT-5.6 models are still listed on Plus at 10-100 (Sol), 25-200 (Terra), and 250-2,000 (Luna). GPT-6 Sol gets 50% more messages than GPT-5.6 Sol on the same plan and burns half the credits per token. GPT-5.4 and GPT-5.4 mini left Codex for ChatGPT sign-in on August 31, 2026, and GPT-5.3-Codex-Spark was removed on September 14.
How to Check Codex Usage: the Usage Dashboard and /status
The Codex usage dashboard lives at chatgpt.com/codex/settings/usage. It shows your current limits and when each one resets. In a running Codex CLI session, type /status to see the remaining limits without leaving the terminal. Credit balances and top-ups are under Settings, Usage in ChatGPT, or Usage & Billing in Codex.
OpenAI suggests checking the dashboard every week or two to learn your pace. When you do hit a limit, a turn already in progress keeps running to completion, subject to fair use. OpenAI Support cannot reset Codex limits, so the remaining moves are waiting for the reset, buying credits on Plus or Pro, or switching the CLI to an API key.
Where the 5-hour window applies today
| Plan | 5-hour window | Weekly limit |
|---|---|---|
| Plus | Yes, since Aug 25, 2026 | Yes |
| Pro $100 / $200 / $500 | No (OpenAI pricing page, October 7, 2026) | Yes |
| Business Standard | Yes | Yes |
| Business Premium | No | Yes |
| Enterprise / Edu (flexible) | No fixed rate limits | Credit-based |
OpenAI suspended the 5-hour window for Plus, Business, and Pro on July 12, 2026. On August 24, Thibault Sottiaux, who leads Codex at OpenAI, said it would return for Plus the next day. His reasoning, as reported by 9to5Mac: the window smooths compute load so the weekly allowance can stay generous, and casual Plus users were "accidentally" burning a whole week in one session. He also said the 5-hour limit stays off for Pro $100 and Pro $200 "for the upcoming months."
Banked resets and the September reset wave
OpenAI now issues banked Codex resets. A banked reset refreshes both the 5-hour and weekly windows when you choose to spend it, and it moves your weekly reset date. Plus, Pro, and Business accounts got banked resets during the GPT-6 Astra rollout on September 3 and 4, and Sottiaux announced a global reset for paid plans on September 7. If you have a banked reset, spend it at the start of a heavy week, not the end.
Users report quota draining faster than the tables suggest
The published ranges assume average sessions. The openai/codex issue tracker shows what happens at the edges. A Plus user on GPT-6 Astra Medium reported (#42987) the full 5-hour allowance gone in two turns: 100% to 42% in under five minutes, then to 0% in one or two more, on a 165-line diff in a Unity repo. Another Plus user logged (#44233) a weekly quota that dropped from 21% remaining to 0% while idle, with the weekly reset date jumping from September 15 to September 12. A meta tracker (#41220) collects dozens of similar accounting reports and is still open.
“GPT-6 Astra consumed essentially the entire 5-hour Codex allowance in two very short, ordinary coding turns.”
The arithmetic explains most of it. Astra burns 250 credits per million input tokens against Sol's 50. On Plus, one Astra message can cost as much as five Sol messages, which is why the Plus Astra range tops out at 45. Default to GPT-6 Sol and switch to Astra for the one hard step. Codex CLI v0.156.0, released September 22, 2026, turns /usage into an analytics dashboard with token totals and plugin and skill activity, so you can see which sessions ate the window. /status has shown estimated thread credits and cost since v0.148.0.
Codex Credits: Burn Rates Per Model
Credits are the unit Codex meters usage in. OpenAI publishes the burn rate per million tokens at Standard speed for every model:
| Model | Credits / 1M input | Credits / 1M cached input | Credits / 1M output |
|---|---|---|---|
| GPT-6 Astra | 250 | 25 | 1,250 |
| GPT-6.1 Sol | 50 | 2.5 | 250 |
| GPT-6 Sol | 50 | 5 | 250 |
| GPT-6 Luna | 2.5 | 0.25 | 12.5 |
| GPT-5.6 Sol | 100 | 10 | 500 |
| GPT-5.6 Terra | 50 | 5 | 300 |
| GPT-5.6 Luna | 5 | 0.5 | 30 |
| GPT-5.5 (retires Oct 14) | 125 | 12.5 | 750 |
Codex credits to USD: one credit equals 4 cents. OpenAI's pricing page does not print a per-credit dollar price, but every row divides cleanly into the API price list at $0.04. GPT-6 Sol costs $2.00 per million input tokens at the API and 50 credits in Codex. Astra costs $10.00 and 250 credits. Luna costs $0.10 and 2.5 credits. GPT-5.6 Sol costs $4.00 and 100 credits. Put the other way, 25 credits buy one API dollar. Credits are API token pricing in different units, with one difference: Codex credits carry no cache-write charge.
Four consequences follow from the table:
- GPT-6 Luna burns a twentieth of GPT-6 Sol, and GPT-6 Astra burns 5x Sol. That is why Plus gets 350-3,000 Luna messages against 5-45 Astra messages.
- Output burns 5x the input rate on GPT-6 models and 6x on GPT-5.6 Terra and Luna. Test generation and scaffolding drain a window faster than debugging and code review.
- Cached input burns a tenth of fresh input. Long sessions in one repo benefit. Jumping between repos resets the advantage.
- Fast mode (called priority processing until July 30, 2026) burns 2.5x the Standard credit rate on GPT-6 models. On the API, Fast mode costs 2x Standard, so GPT-6 Astra Fast is $20/$100, and both
service_tier: "priority"and"fast"still work.
What a Codex Session Costs
The credit arithmetic is exact, so per-task cost falls out of token volume. Input tokens times 50 plus output tokens times 250, per million, at 4 cents per credit, gives the GPT-6 Sol figure:
| Task | Tokens (in / out) | Sol credits | GPT-6 Sol | GPT-6 Luna | GPT-6 Astra |
|---|---|---|---|---|---|
| Small bug fix | 50k / 5k | 3.75 | $0.15 | under $0.01 | $0.75 |
| Feature in 3-5 files | 150k / 15k | 11.25 | $0.45 | $0.02 | $2.25 |
| Multi-file refactor | 300k / 30k | 22.5 | $0.90 | $0.05 | $4.50 |
| Test generation pass | 100k / 40k | 15 | $0.60 | $0.03 | $3.00 |
Token volumes are estimates. The arithmetic is not. The same refactor that cost $2.40 on GPT-5.6 Sol at its July price costs 90 cents on GPT-6 Sol. Model choice is still the largest lever on a Codex bill: Astra costs 100x Luna for the same tokens.
This also explains why two developers on the same plan report different experiences. One running small fixes on Sol gets 150 messages per window. One running 300k-token agentic refactors on Astra gets 5.
Codex API Pricing
Running Codex with an API key, or calling the models directly, bills per token with no subscription. Standard rates from OpenAI's API pricing page as of October 7, 2026:
| Model | Input / 1M | Cached input / 1M | Output / 1M |
|---|---|---|---|
| gpt-6-astra | $10.00 | $1.00 | $50.00 |
| gpt-6.1-sol | $2.00 | $0.10 | $10.00 |
| gpt-6-sol | $2.00 | $0.20 | $10.00 |
| gpt-6-luna | $0.10 | $0.01 | $0.50 |
| gpt-5.6-sol (promo) | $4.00 | $0.40 | $20.00 |
| gpt-5.6-terra | $2.00 | $0.20 | $12.00 |
| gpt-5.6-luna | $0.20 | $0.02 | $1.20 |
| gpt-5.3-codex | $1.75 | $0.175 | $14.00 |
GPT-6 Sol and Luna cost half of GPT-5.6 Sol and Luna on input. Luna output drops from $1.20 to $0.50. GPT-5.6 Sol's $4/$20 rate is promotional and runs at least through November 21, 2026. Cache writes bill at 1.25x input on the 5.6 and 6 generations ($2.50 per million on GPT-6 Sol). Long-context requests bill at a higher tier: $4/$15 on GPT-6 Sol and $20/$75 on Astra. Fast mode on gpt-5.3-codex costs $3.50/$28.00, double Standard.
Codex CLI Pricing
Codex CLI is free, open-source software. The latest release is v0.156.0 (September 22, 2026). You pay through one of two channels:
- ChatGPT sign-in: included on Plus, Pro, Business, and Enterprise. Free and Go do not include Codex in the CLI. CLI usage draws from the same allowance as the desktop app, web, and IDE, so a heavy CLI session and a heavy app session compete for one budget. Run
/usage(an analytics dashboard since v0.156.0) or/statusto see token totals and estimated credits. - API key: per-token billing at the rates above. No 5-hour window and no weekly cap. Cost scales linearly with usage.
The CLI also supports custom model providers through config.toml (base_url, env_key, wire_api), so it can point at any Responses-compatible endpoint. Setup is in our Codex provider configuration guide. One removal to know: codex mcp-server and the standalone codex-mcp-server binary were removed on September 5, 2026. Integrations now go through the app server, which is still experimental. codex mcp, which connects Codex to external MCP servers, still works.
Business and Enterprise
Business Standard seats are $20/user/month on annual billing, or $25/user/month monthly. The per-seat Codex allowance matches Plus: 15-150 GPT-6 Sol local messages per 5 hours, 350-3,000 on Luna.
Premium seats launched in August 2026 at $100/user/month annual or $125 monthly. They carry 5x the Standard usage and no 5-hour limit, so only the weekly reset applies. A workspace can mix Standard and Premium seats and reassign them, which is the cheapest way to give two heavy Codex users on a ten-person team Pro-level headroom. Business, Edu, and Enterprise workspaces on flexible pricing can buy workspace credits. Enterprise and Edu on flexible pricing have no fixed rate limits; usage draws on credits.
Is Codex Free? Free and Go Plan Limits
Yes. Codex is included in ChatGPT Free at $0/month. Free and Go both get GPT-6 Luna at Standard speed in the ChatGPT desktop app, subject to rollout. Neither plan includes Codex in the CLI, so the CLI starts at Plus.
Two caveats. OpenAI publishes no message counts for Free or Go, and neither plan can buy credits, so hitting a limit means waiting for the reset. Go at $8/month is described as suitable for lightweight coding tasks. Codex Go vs Plus comes down to this: Plus at $20/month adds the CLI, web, IDE extension, and iOS, GPT-6 Sol and Astra, a published 15-150 Sol messages per 5 hours, and credit top-ups mid-task.
There is no separate student price for Codex. Students use the same Free, Go, or Plus plans. Edu pricing covers institutions.
Codex vs Claude Code Pricing
As of September 2026 the two ladders match almost price for price, at both the subscription and the API level:
| Tier | Codex (OpenAI) | Claude Code (Anthropic) |
|---|---|---|
| Entry | Plus $20/mo | Pro $20/mo |
| Heavy use | Pro $100, $200, or $500/mo | Max from $100/mo (5x or 20x) |
| Team seats | Business $20/$25, Premium $100/$125 | Team $20/$25, Premium $100/$125 |
| Top API model (in / out per 1M) | GPT-6 Astra $10 / $50 | Fable 5.1 $10 / $50 |
| Workhorse API model | GPT-6 Sol $2 / $10 | Sonnet 5 $2 / $10 |
| $4 / $20 tier | GPT-5.6 Sol $4 / $20 (promo) | Opus 5.5 $4 / $20 (launched Sep 22) |
At matching sticker prices the decision comes down to capability per dollar and how each vendor meters. The cheapest model on either side is GPT-6 Luna at $0.10/$0.50. Anthropic has no model priced near it; its cheapest current model is Haiku 4.5 at $1/$5. Both vendors moved on September 22: OpenAI shipped GPT-6 Sol and Luna, and Anthropic shipped Claude Opus 5.5 and said it is raising 5-hour usage limits on Pro, Max, Team, and seat-based Enterprise plans. Full breakdowns are in Claude Code pricing, Codex vs Claude Code, and Claude vs ChatGPT.
Codex Subscription vs API Key
A Codex subscription buys a flat monthly bill and a hard ceiling. An API key buys no ceiling and a variable bill. The crossover depends on the model.
- On GPT-6 Sol: sessions cost $0.15 to $0.90, so Plus ($20/mo) breaks even at roughly 22 to 133 sessions a month and Pro 5x ($100/mo) at roughly 110 to 670.
- On GPT-6 Luna: sessions cost under a cent to 5 cents. Plus does not break even until several hundred sessions a month.
- On GPT-6 Astra: sessions cost $0.75 to $4.50. Plus breaks even at 4 to 27 sessions, which is why Astra users feel the subscription limits first.
The GPT-6 price cut moved the crossover. The API route fits developers who batch work into occasional deep sessions, teams building products on the models, and anyone running Luna for high-volume simple work. What you give up is cloud features, integrations, and the flat bill. What you gain is no 5-hour window and no weekly cap.
Which Codex Plan to Pick
Free or Go ($0-$8/mo)
You want to evaluate Codex or use it a few times a week. Both run GPT-6 Luna in the desktop app only, with no CLI. Neither can buy credits when a limit lands.
Plus ($20/mo)
You code regularly but not in all-day agentic sprints. 15-150 GPT-6 Sol messages per 5 hours covers most individual workflows. Expect the 5-hour window to bite on long sessions. Credit top-ups handle the occasional overage.
Pro 100 ($100/mo)
You hit Plus limits weekly. Pro has no 5-hour window for now, only weekly limits, which makes this the cheapest way to stop watching the 5-hour clock.
Pro 200 ($200/mo)
You run parallel agents or lean on Astra. New subscribers get a lower allowance than the September plan carried, so compare plans on the ChatGPT pricing page before upgrading. Grandfathered accounts keep the old allowance through October 29, 2026.
Pro 500 ($500/mo)
You want GPT-6 Astra at Ultrafast speed, or more included usage than Pro 200 gives. Ultrafast spends the allowance at 8x, so expect to buy credits if you leave it on.
Business or Enterprise
Your team needs admin controls and shared billing. Standard seats at $20/user/month annual match Plus. Premium seats at $100 give heavy users 5x and drop the 5-hour window. Enterprise adds custom contracts and credit-based usage.
API key
You run fewer than 20-odd Sol sessions a month, you want Luna at $0.10/$0.50 for bulk work, or you need programmatic access with no window limits.
Pricing History
| Date | Event |
|---|---|
| July 12, 2026 | OpenAI temporarily removed the 5-hour usage window for Plus, Business, and Pro; weekly limits unchanged |
| July 30, 2026 | GPT-5.6 price cut: Terra $2.50/$15 to $2/$12, Luna $1/$6 to $0.20/$1.20. Priority processing renamed Fast mode |
| August 21, 2026 | GPT-5.6 Sol cut from $5/$30 to a promotional $4/$20, running at least through November 21, 2026 |
| August 2026 | Business Premium seats: $100/user/mo annual, $125 monthly, 5x usage, no 5-hour limit |
| August 25, 2026 | 5-hour window restored for Plus; Pro $100 and $200 stay exempt for the upcoming months |
| September 3, 2026 | GPT-6 Astra released at $10/$50, sharing the Codex allowance; banked resets granted Sep 3-4 |
| August 31, 2026 | GPT-5.4 and GPT-5.4 mini removed from Codex for ChatGPT sign-in (API keys still work) |
| September 5, 2026 | codex mcp-server and the standalone codex-mcp-server binary removed from Codex CLI |
| September 7, 2026 | Global Codex usage reset for paid plans |
| September 10, 2026 | New sign-ups and upgrades to Pro $200 paused; existing subscriptions unaffected |
| September 14, 2026 | GPT-5.3-Codex-Spark deprecated and removed from the Codex app, CLI, and IDE; GPT-5.5 retirement announced |
| September 22, 2026 | GPT-6 Sol ($2/$10) and GPT-6 Luna ($0.10/$0.50) roll out to Codex; Codex CLI v0.156.0 turns /usage into an analytics dashboard |
| September 29, 2026 | Pro $200 grandfathering cutoff (10 a.m. PT). Later Pro $200 subscriptions get a lower allowance at the same price |
| By October 7, 2026 | Pro $200 open to new subscribers again; Pro $500 listed with GPT-6 Astra Ultrafast; GPT-6.1 Sol rolling out to Codex at $2/$10 |
| October 14, 2026 | GPT-5.5 retires from ChatGPT, ChatGPT Work, and Codex on all plans (stays on the API) |
| October 29, 2026 | Grandfathered Pro $200 accounts move to the lower allowance |
Skip the Usage Cap: Pay-Per-Token Open Models
If the recurring pain is the cap and not the price, the fix is a per-token API with no 5-hour window and no weekly cap. Morph serves open-weight coding models on custom kernels through an OpenAI-compatible endpoint at https://api.morphllm.com/v1. You pay for the tokens you use, and nothing throttles a long refactor mid-session.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| GLM-5.3 (morph-glm53-744b) | $1.19 | $6 | 1M |
| DeepSeek V4.1 Flash (morph-dsv41flash) | $0.12 | $0.8 | 1M |
| DeepSeek V4 Flash (morph-dsv4flash) | $0.141953125 | $0.399625 | 1M |
Each of these swaps into an existing Codex CLI or any OpenAI-SDK client by pointing base_url at the endpoint above and sending a Morph API key (setup in our Codex provider configuration guide). The tradeoff is plain. You give up OpenAI's cloud features, managed integrations, and the GPT-6 weights. You keep uncapped throughput and per-token billing. See the model lineup, full pricing, and the best open-source LLMs for coding.
Run coding models with no weekly cap
Open-weight models on custom kernels, OpenAI-compatible API, pay per token. GLM-5.3, DeepSeek V4.1 Flash, and DeepSeek V4 Flash at api.morphllm.com/v1.
Frequently Asked Questions
Is Codex free?
Yes. Codex is included in the ChatGPT Free plan at $0/month, and OpenAI describes that tier as enough to explore Codex on quick coding tasks. Free and Go ($8/month) both get GPT-6 Luna at Standard speed in the ChatGPT desktop app, subject to rollout. Neither plan includes Codex in the CLI. OpenAI publishes no message counts for Free or Go. Neither plan can buy credit top-ups. Plus at $20/month is the first tier that can purchase additional credits when a limit is reached.
How much does Codex cost?
Codex is included in every ChatGPT plan: Free $0/month, Go $8/month, Plus $20/month, Pro at $100, $200, or $500/month, Business $20/user/month on annual billing ($25 monthly), and Enterprise or Edu at custom pricing. There is no separate Codex subscription. An API key bills per token instead: GPT-6.1 Sol and GPT-6 Sol are $2 per million input tokens and $10 per million output tokens, and GPT-6 Luna is $0.10 and $0.50.
What are the Codex plans?
Six tiers. Free ($0), Go ($8/month), Plus ($20/month), Pro ($100, $200, or $500/month), Business ($20/user/month annual, $25 monthly, with $100/$125 Premium seats), and Enterprise/Edu (custom). An API key is a seventh path that bills per token with no plan. Pro $200 is open to new subscribers again with a lower allowance than before, and Pro $500 is the only Pro plan with GPT-6 Astra Ultrafast.
How do Codex credits work?
Credits are the unit Codex meters usage in. Each model burns a published number of credits per million tokens: GPT-6 Astra is 250 input / 25 cached / 1,250 output, GPT-6.1 Sol is 50 / 2.5 / 250, GPT-6 Sol is 50 / 5 / 250, and GPT-6 Luna is 2.5 / 0.25 / 12.5. Cached input burns a tenth of fresh input, or a twentieth on GPT-6.1 Sol. Every row is 25x the model's API dollar price, which works out to exactly $0.04 per credit, so credits are API pricing in different units. Codex credits have no cache-write charge.
How much is one Codex credit in dollars?
OpenAI's Codex pricing page does not print a dollar price per credit, but every model's credit rate equals its API price divided by $0.04. GPT-6 Sol costs $2.00 per million input tokens at the API and 50 credits in Codex. GPT-6 Astra costs $10.00 and 250 credits. GPT-6 Luna costs $0.10 and 2.5 credits. So 1 credit is 4 cents, and 100 credits is $4 of API-equivalent usage.
What does Codex Plus include?
Codex Plus is ChatGPT Plus at $20/month. It covers Codex on the web, in the CLI, in the IDE extension, on iOS, and in the desktop app, with GPT-6.1 Sol, GPT-6 Sol, and Luna (plus GPT-6 Astra in Codex and Work). OpenAI's published allowance is 5-45 local messages per 5-hour window on GPT-6 Astra, 15-160 on GPT-6.1 Sol, 15-150 on GPT-6 Sol, and 350-3,000 on GPT-6 Luna. Weekly limits apply on top. The 5-hour window returned for Plus on August 25, 2026. Plus is the cheapest tier that can buy additional credits.
What are the Codex usage limits?
OpenAI publishes per-model estimates of local messages per 5-hour period, plus weekly limits with no published numbers. On Plus and Business Standard seats the window allows 5-45 GPT-6 Astra messages, 15-160 on GPT-6.1 Sol, 15-150 on GPT-6 Sol, and 350-3,000 on GPT-6 Luna. OpenAI's pricing page says Pro plans currently have no five-hour limit. Live limits and reset times are on the usage dashboard at chatgpt.com/codex/settings/usage, and /status shows them inside a Codex CLI session.
Does Codex have a 5-hour limit?
On Plus and Business Standard seats, yes. OpenAI suspended the 5-hour window for Plus, Business, and Pro on July 12, 2026 and restored it for Plus on August 25, 2026. Thibault Sottiaux said Pro $100 and Pro $200 would keep the 5-hour limit disabled for the upcoming months, and as of October 7, 2026, OpenAI's pricing page says Pro plans have no five-hour limit. Business Premium seats ($100/user/month annual) have no 5-hour limit. Weekly limits apply on every plan.
What is the difference between Codex Plus and Pro?
Plus is $20/month. Pro is $100, $200, or $500/month, and each step includes more usage than the one below it. On GPT-6.1 Sol, Plus allows 15-160 local messages per 5-hour period. OpenAI no longer prints per-window counts for Pro because Pro plans currently have no five-hour limit, so only weekly limits apply. Pro $500 is the only plan with GPT-6 Astra Ultrafast.
Can I still buy ChatGPT Pro $200 for Codex?
Yes, again. OpenAI paused new Pro $200 sign-ups on September 10, 2026, and has since reopened them. New subscriptions that are not grandfathered get a lower included allowance than Pro $200 had before, at the same $200/month. Anyone with an active Pro $200 subscription at any point from September 22 through 10 a.m. Pacific Time on September 29, 2026 keeps the previous allowance through October 29, 2026.
What is ChatGPT Pro 500?
Pro 500 is a $500/month ChatGPT Pro plan with the highest included usage of the three Pro tiers. It is the only Pro plan with GPT-6 Astra Ultrafast, which generates tokens up to 8x faster than GPT-6 Astra and uses included usage at 8x the Standard rate before drawing on credits. Buying credits on Pro 100 or Pro 200 does not unlock Ultrafast.
How do I check my Codex usage?
Open the Codex usage dashboard at chatgpt.com/codex/settings/usage. It shows your current limits and reset times. Inside a Codex CLI session, run /status to see what is left. Credit balances and purchases are under Settings, Usage in ChatGPT, or Usage & Billing in Codex. OpenAI Support cannot reset Codex limits.
Does ChatGPT Pro include GPT-6 Pro?
Yes, with weekly caps. GPT-6 Pro is ChatGPT's name for GPT-6 Astra in Pro mode, and there is no API model called GPT-6 Pro. In ChatGPT Chat, Pro $200 gets 200 GPT-6 Pro messages per week and Pro $100 gets 50 per week, shared with GPT-5.6 Sol Pro. Business Premium seats get 50 per week and Business Standard seats get 15 per month. Plus gets GPT-6 Astra in Codex and Work, not GPT-6 Pro in Chat.
How much does a Codex session cost?
On GPT-6 Sol, a small bug fix (50k input, 5k output tokens) burns 3.75 credits, or 15 cents. A multi-file refactor (300k input, 30k output) burns 22.5 credits, or 90 cents. The same refactor costs about 5 cents on GPT-6 Luna and $4.50 on GPT-6 Astra. Output burns 5x the input rate on GPT-6 models, so test generation and scaffolding cost more per task than debugging.
How much does Codex CLI cost?
Codex CLI is free, open-source software. With ChatGPT sign-in it is included on Plus ($20/month) and higher. Free and Go do not include Codex in the CLI; they get GPT-6 Luna in the desktop app only. CLI usage draws from the same allowance as Codex in the desktop app, web, and IDE. The alternative is running the CLI with an OpenAI API key and paying per token: GPT-6 Sol costs $2.00/M input and $10.00/M output, with no 5-hour window and no weekly cap.
How does the Codex Business plan work?
Business Standard seats are $20/user/month on annual billing, or $25/user/month monthly, with the Plus allowance per seat. Premium seats launched in August 2026 at $100/user/month annual or $125 monthly, with 5x the Standard usage and no 5-hour limit. Teams can mix both seat types in one workspace. Business, Edu, and Enterprise workspaces on flexible pricing can buy workspace credits.
Is the Codex API cheaper than a subscription?
For light users, yes. On GPT-6 Sol a session runs 15 to 90 cents at API rates, so the $20/month Plus plan breaks even at roughly 22 to 133 sessions a month. On GPT-6 Luna a session costs under 5 cents, and the API stays cheaper for several hundred sessions a month. Daily heavy users still come out ahead on a subscription. The API route removes the 5-hour window and weekly limits.
How does Codex pricing compare to Claude Code?
The ladders now match almost line for line. Both have a $20/month entry plan, a tier from $100/month (Codex Pro now also has a $500 step), and team seats at $20/$25 Standard and $100/$125 Premium. At the API, GPT-6 Astra and Claude Fable 5.1 both cost $10/$50 per million tokens, GPT-6 Sol and Claude Sonnet 5 both cost $2/$10, and GPT-5.6 Sol matches Claude Opus 5.5 at $4/$20.