ChatGPT and Codex share one usage allowance (December 2026)
As of 2026-11-12, OpenAI's help center says that starting in December, Plus, Pro, and Business plans' usage allowance will be shared across ChatGPT and Codex, measured in tokens, with Instant chat excluded; no exact date is published. The official pricing page already says ChatGPT Work and Codex share usage. Below: what changes per plan, where to check, and the options OpenAI lists.
Updated 2026-11-13
Prices change: on QCode, Claude, GPT and Chinese models are billed per token — live rates on /models.
- Billed per token — live rates on /models
- Pay by card (Visa / Mastercard), Apple Pay, Google Pay or crypto
- Self-service: top up and activate instantly
Four official points
When it starts
The official wording is Starting in December, with no exact date. It covers the Plus, Pro, and Business usage allowance.
How usage is measured
OpenAI says usage for ChatGPT and Codex will be measured in tokens, so how much allowance you use depends on the model and the task (more advanced models and complex tasks generally use more); Instant chat will not draw from your usage. It also says most users won't need to wait for a reset more often than they do now.
Where the combined allowance shows
From December, OpenAI says you will see your combined remaining usage and reset times in Settings → Usage. Today the usage dashboard shows current limits, and /status does it inside an active Codex CLI session.
The path that skips this allowance
The pricing page says all users may run extra local chats with an API key, charged at standard API rates; the Codex auth doc says an API key uses standard API pricing instead of included ChatGPT plan credits.
Before and after, plan by plan
As of 2026-11-12 the official pricing page says ChatGPT Work and Codex already share usage: Work usage inside ChatGPT uses the same pricing, credits, and usage limits as Codex; local messages and cloud chats share the plan's allowance and weekly limits may also apply, with Plus and Standard Business estimated per five-hour period while Pro plans currently have no five-hour limit; and usage limits are also shared with other agentic features, currently ChatGPT for Excel on Plus and Pro. From December the same allowance is shared with ChatGPT itself: ChatGPT and Codex usage on Plus, Pro and Business is measured in tokens and Instant chat is excluded. How large each plan's pool is, whether weekly windows continue, and whether Pro still has a five-hour limit after December are not stated on the official pages as of 2026-11-12.
The official wording
Help center: Starting in December, Plus, Pro, and Business plans’ usage allowance will be shared across ChatGPT and Codex as we bring the agentic capabilities of Work into the main ChatGPT experience. Your usage for ChatGPT and Codex will be measured in tokens. Instant chat will not draw from your usage. We expect most users won't need to wait for their usage to reset more often than they do now.
Timeline
OpenAI's What's new entry for the week of August 3–7 says ChatGPT Work and Codex continue to share the same usage limits and credits.
The help center page, captured that day, showed Updated: 4 days ago and said the shared allowance starts in December, is measured in tokens, and excludes Instant chat.
The pricing page checked that day still says ChatGPT Work and Codex share usage, and adds that usage limits are shared with other agentic features, currently ChatGPT for Excel on Plus and Pro.
Confirmed vs not published
Stated in the official wording
① From December, Plus, Pro, and Business share one allowance across ChatGPT and Codex (Starting in December; no exact date). ② It is measured in tokens and Instant chat is excluded. ③ Combined remaining usage and reset times appear in Settings → Usage. ④ When you hit the limit you can wait for a reset, upgrade, or buy credits; Plus and Pro users can buy additional credits without upgrading, and Business, Edu, and Enterprise plans with flexible pricing can buy workspace credits.
Not stated as of 2026-11-12
The official pages as of 2026-11-12 do not state: the exact December date; how large each plan's allowance is; whether weekly windows continue after December; whether Pro still has no five-hour limit after December. These cells stay blank rather than estimated.
Options when the allowance runs out
Stay on the subscription
OpenAI's options: wait for the reset, upgrade your plan, or buy credits. Plus and Pro users who hit the limit can buy additional credits without upgrading; Business, Edu, and Enterprise plans with flexible pricing can buy workspace credits.
Move to an API key billed per token
OpenAI says API key usage is billed at standard API rates, a separate path from the included allowance; you can also use the plan first and add an API key for extra local chats. QCode's OpenAI-compatible endpoint is that path: billed per token, per-model rates on /models. Pro's included API credits apply only to the linked API organization and are separate from the usage allowance; see /chatgpt-pro-api-credits-used-up.
Where to check what is left
Today: the usage dashboard shows current limits and reset times, and /status shows the remaining allowance inside an active Codex CLI session. From December, OpenAI says Settings → Usage shows the combined remaining usage and reset times. OpenAI suggests checking the dashboard every week or two to understand your pace.
The per-token route on QCode
As of 2026-11-12, QCode's /models includes gpt-6.1-sol, gpt-6.1-terra, gpt-6-sol, gpt-5.6-sol, gpt-5.6-terra and gpt-6-astra, among others, in the OpenAI / Codex series. One QCode key works on both the Anthropic-compatible and the OpenAI-compatible endpoints, billed per token with per-model rates on /models. Codex uses the OpenAI Responses protocol: set base_url = "https://api.qcode.cc/openai", wire_api = "responses" and requires_openai_auth = true in ~/.codex/config.toml; the path is /openai/v1/responses, with the full configuration on the Codex page at docs.qcode.cc.
Frequently asked questions
Do Codex and ChatGPT share the same usage limit?
From December, yes. OpenAI says Plus, Pro, and Business plans' usage allowance is shared across ChatGPT and Codex, measured in tokens, with Instant chat excluded; what already shares usage today is ChatGPT Work and Codex.
When does it start?
OpenAI says only Starting in December and gives no exact date; neither the pricing page nor the help center names a day. OpenAI adds that it is preparing carefully for the transition to help prevent disruption to your workflows.
How much do Plus and Pro each get?
OpenAI does not express it as a fixed number of messages: your allowance does not correspond to a fixed number of messages or tasks. Its estimates cover only local messages per five-hour period for Plus and Standard Business: GPT-6 Astra 5–45, GPT-6.1 Sol 15–160, GPT-6.1 Terra 35–285, GPT-6 Sol 15–150, GPT-6 Luna 350–3,000, described as estimates, not fixed limits. Pro plans currently have no five-hour limit but still include an allowance.
How do I see what is left?
Today the usage dashboard shows current limits and reset times, and /status shows the remaining allowance inside an active Codex CLI session. From December, OpenAI says Settings → Usage shows the combined remaining usage and reset times.
What can I do when I hit the limit?
OpenAI's options: wait for the reset, upgrade your plan, or buy credits. Plus and Pro users can buy additional credits without upgrading; Business, Edu, and Enterprise plans with flexible pricing can buy workspace credits. OpenAI also says a turn already in progress can keep working when you hit the limit, subject to fair use limits.
Does an API key still count against this limit?
No. OpenAI says API key usage is billed at standard API rates, and that signing in to Codex with an API key uses standard API pricing instead of included ChatGPT plan credits; the CLI command is printenv OPENAI_API_KEY | codex login --with-api-key. For the two sign-in and billing paths without a ChatGPT subscription, see /codex-without-chatgpt-subscription.
Sources
OpenAI: the ChatGPT and Codex pricing and usage page (including the five-hour estimate table), the Codex authentication doc and What's new; the December paragraph quotes the help center article Understanding ChatGPT and Codex usage limits. QCode: the models listed on /models and the docs.qcode.cc endpoints and Codex quick start pages. All checked on 2026-11-12.
Need Codex beyond your plan's allowance?
Create a QCode key and pay per token on the OpenAI-compatible endpoint, with no monthly plan needed. Pay-as-you-go Packs start at $4 for a one-time quota you use within 7 days; if you already have a Personal Plan, add a booster pack when you need more quota.
Related
One-time quota packs: no monthly plan, valid 7 days
One-time quota packs valid for 7 days, no subscription; per-model rates are on /models.
ChatGPT Pro vs Plus Codex limits
How the five-hour window and the included allowance differ by plan, and how to choose.
Codex five-hour limit estimates
How the five-hour window works, plus the official per-model estimate ranges.
Crypto payment guide
Nine coins, 56 networks, zero platform fee for AI coding API credits.
Official statements checked on 2026-11-12 against the OpenAI help center, pricing page and Codex auth doc; model availability and rates follow qcode.cc/models.