GPT-6 Astra does not have one universal prompt limit. In Work and Codex, usage depends on your plan and the work performed, with a shared Work/Codex allowance and plan-dependent limits. Pro currently has no five-hour Work/Codex limit; Plus can have five-hour and weekly limits. GPT-6 Pro in Chat uses a separate message allowance. API usage is billed separately.
We ran two bounded Astra coding tasks and recorded real account readings. Both passed their acceptance checks. The account’s weekly used meter moved from 56% to 57% during the observation period, but other Codex work was active. That movement cannot be attributed solely to our test.
Current model, price and limit guidance checked September 29, 2026. The task observations were recorded September 27 UTC (September 26 Pacific). The experiment lasted about 2 minutes 18 seconds between its first and last meter readings. It is a short session, not a week-long usage diary.
First identify where you are using Astra
On a narrow screen, scroll tables sideways to see every column.
| Surface | What you select | How to interpret the limit |
|---|---|---|
| Work or local Codex | GPT-6 Astra | Work/Codex shared allowance; consumption varies with the task |
| ChatGPT Chat | GPT-6 Pro, powered by Astra | Separate Chat message rules; do not substitute Codex estimates |
| OpenAI API | An available API model under your API account | Metered API billing and account limits; no ordinary subscription message pool |
Sources: Astra usage in Work and Codex, GPT-6 Pro in Chat and OpenAI pricing and billing.
Plus users can access Astra in Work and Codex; that does not grant GPT-6 Pro in Chat. Also check the execution surface: OpenAI’s model table lists Astra for local Codex surfaces but not Codex cloud. CLI access requires a sufficiently recent client; OpenAI specifies 0.153.0 or later. Model availability; Access and CLI version guidance.
Astra limits by individual ChatGPT plan
| Plan | Monthly US web price | Work/Codex five-hour rule |
|---|---|---|
| ChatGPT Plus | $20 | 5–45 estimated local Astra messages; weekly limits may also apply |
| ChatGPT Pro $100 | $100 | No five-hour limit; check applicable account allowances |
| ChatGPT Pro $200 | $200 | No five-hour limit; account limits still apply |
| ChatGPT Pro $500 | $500 | No five-hour limit; includes Astra Ultrafast access |
Source: OpenAI’s current pricing and usage guidance. Context, reasoning, tools and workload affect consumption. The Plus range is not an entitlement to its upper endpoint. Pro’s lack of a five-hour limit does not mean unlimited use. Currency, tax and regional checkout differences matter.
The Astra help article still displays older Pro five-hour estimates, which conflict with the current pricing page. We have removed those Pro figures here. Check your account’s allowance and reset times rather than relying on an earlier table. Astra help guidance.
Pro $200 is available for new subscriptions again. Pro 200’s planned reduction is canceled. Pro $500 adds Astra Ultrafast; buying credits on Pro $100 or $200 does not unlock it. Source: OpenAI’s current Pro tiers and allowance eligibility. For the buying decision, see ChatGPT Pro vs Claude Max.
Plan-dependent windows, resets and shared usage
Where a five-hour window applies, it begins with your first Work or Codex message after the previous window ends. A weekly window can also apply. When both apply, capacity in one does not override an exhausted other window. OpenAI’s current pricing page exempts Pro from the five-hour limit; read the applicable limits and reset times shown for your account. Source: OpenAI’s current pricing and usage guidance.
Work and Codex draw on shared capacity, including local and cloud tasks. Other eligible features, including Excel use described in OpenAI’s pricing guidance, can also draw on this pool. Opening another task, changing interface or switching models does not replenish it. A less demanding model may stretch the remaining allowance; it does not start a fresh balance. Shared usage rules.
Check the signed-in Codex usage dashboard or /status in the CLI. An unavailable meter is missing information, not proof of unlimited use. Read whether a display shows used or remaining before recording it.
Our actual task-and-allowance records
We used Codex CLI 0.155.0-alpha.16.4, selected gpt-6-astra, requested low effort and left speed at its default; Fast was not requested. Authentication used the ChatGPT subscription. The account meter reported pro but did not expose whether it was the $100 or $200 tier. We therefore cannot assign these results to either tier.
Both tasks used synthetic Python code, with requirements and acceptance tests frozen before any model request. We instructed the agent to fix the implementation without changing tests, installing dependencies, accessing the network or using subagents. Each task had one run and no human correction prompt.
| Task | CLI start → finish | CLI wall time | Acceptance | Weekly used readings* |
|---|---|---|---|---|
| Repair interval merging and validation | 04:25:28.521 → 04:25:55.322 | 26.730 seconds | 13/13 passed | 56% → 57% |
| Repair decimal ledger totals and command-line errors | 04:26:20.544 → 04:27:01.126 | 40.415 seconds | 10/10 passed | 57% → 57% |
*These are account readings surrounding each task, not attributable task costs. We read 56% at 04:25:24.733, 57% at 04:26:16.471 and 57% at 04:27:42.381. The reported weekly reset was October 3, 2026 at 16:58:30 UTC. The five-hour reading was unavailable. No reset occurred between these readings.
The elapsed meter observation was 137.648 seconds. Other Codex tasks and the editorial coordination task were running on the same account. The meter reports whole percentages. Consequently, the first row does not establish that interval merging costs one percentage point, and the second does not establish that ledger work is free. Neither row supports a conversion into tokens, dollars or a universal prompts-per-plan figure.
Both intentionally broken baselines failed; the final implementations passed all 23 supplied checks with tests and requirements unchanged. These are two small fixtures, not 23 independent projects. The timing includes CLI startup and tool execution, and should not be treated as general model latency. Fixture design and execution were assisted by Codex.
Download the reproducible evidence pack (ZIP): starting files, prompts, final implementations, source patches, acceptance output, timestamps, sanitized meter readings and SHA-256 manifest. To check a final implementation, enter either task’s after folder and run python3 -m unittest -v.
We did not purchase credits or run paid API tests for this observation. We later ran three paired coding fixtures using existing ChatGPT Pro and Claude Pro subscriptions; Codex CLI and Claude Code each passed six of six scored attempts on the frozen checks. The later runs also lacked isolated account meters, and Claude Max was not tested. Neither test set measures per-task Astra allowance or cross-provider subscription endurance. The Codex vs Claude Code comparison links the paired evidence packs.
Why two prompts can consume different amounts
A short question about one function and a repository-wide investigation can require very different amounts of reading, reasoning and tool work. Higher effort, larger context and longer tasks can increase consumption. Fast mode also has a usage multiplier. OpenAI currently documents 2.5x usage for Fast on its GPT-6 models. Source: model rates and Fast mode.
Use Astra when the task warrants it. OpenAI’s model lineup also includes GPT-6.1 Sol, rolling out to eligible accounts and clients, GPT-6 Sol and GPT-6 Luna. An editorial workflow worth trying is to give bounded formatting or straightforward edits to a lighter model, then reserve Astra for a difficult investigation. That is a recommendation to test against your work, not a measured saving from our experiment. Current model guidance.
Do not confuse a long-context problem with a quota problem. Compaction can summarize earlier work so a task can continue within context constraints. It does not reset any applicable usage allowance. A task that needs fewer irrelevant files may become easier to handle, but there is no fixed percentage saving promised here.
GPT-6 Pro in Chat has different limits
GPT-6 Pro in Chat has plan-dependent limits separate from Work/Codex. On Pro $100, GPT-6 Pro and GPT-5.6 Sol Pro share one weekly allowance. On Pro $200, GPT-5.6 Sol Pro has a daily allowance and a combined daily allowance; reaching the GPT-6 Pro weekly limit switches Chat to GPT-5.6 Thinking at Medium. Selecting GPT-5.6 Sol Pro can continue only while its applicable allowances remain.
OpenAI’s updated Chat guide no longer publishes the exact numerical counts previously shown here. Check your account for current allowances and reset times; Work/Codex rules do not replace Chat rules. Source: OpenAI’s current Chat model-limit rules.
What to check when Astra stops working
- Identify the surface and model. GPT-6 Pro in Chat, Astra in local Codex and a hosted Codex job can have different availability and limits.
- Read every applicable usage window. Record whether each meter shows used or remaining, plus its reset time. A weekly limit can remain exhausted after a shorter window resets.
- Check simultaneous activity. Other tasks can consume the same account allowance. Closing a tab does not prove every remote task has stopped.
- Check client version and account. Update an older CLI through the supported channel and confirm the intended subscription is signed in.
- Distinguish a limit from an execution failure. A denied command, missing dependency or unavailable model is not automatically a quota problem.
- Choose a supported next step. Wait for the displayed reset, reduce unnecessary work or use a suitable available model if capacity remains. Eligible paid credits are an additional purchase, not included unlimited access.
For broader distinctions between quota, context, credits and billing, see our AI coding plan limits guide. Check any older examples there against the current provider rules linked here.
Frequently asked questions
How many Astra prompts do I get?
There is no single guaranteed count in Work/Codex. OpenAI publishes a Plus estimate, while Pro currently has no five-hour Work/Codex limit. Workload and other applicable account allowances determine actual availability.
Does starting a new task reset my allowance?
No. A new task can reduce irrelevant conversation context, but it does not create a new subscription pool.
Can I use the API to keep working?
API access is a separate billing route with its own limits. Confirm model availability and the charges before using it. A ChatGPT subscription is not a general API credit balance.
Does Kingy’s experiment show the cost of one Astra task?
No. It shows two completed tasks and the actual surrounding account readings. Rounded meters and concurrent work prevent a defensible per-task usage calculation. A stronger follow-up would use a quiet account, a verified tier and repeated observations across complete usage windows.
Limit Watch · Reader reports · unverified
What readers get before hitting Codex and ChatGPT limits
Readers report how much they used before hitting a limit. Kingy shows the typical value once 5 readers report the same plan and limit. Unverified reports, not official figures.
Loading reader reports…