Skip to main content
When you use chat and agents, your usage is measured based on underlying model provider costs. More expensive models consume your limit faster than lightweight ones.

Usage windows

Your usage is tracked across two time windows:
WindowDurationHow it works
Session5 hoursStarts when you send your first message. Resets after 5 hours.
WeeklyMonday to MondayFixed weekly window. Resets every Monday.
Both windows have their own limit. If you reach either one, your messages are routed to GPT-5.2 until that window resets.

Checking your usage

You can see your current usage in Settings > Account > Usage. The page shows progress bars for both your session and weekly usage, along with the time until each window resets.
Personal usage page showing session and weekly progress bars with percentages and reset times

Tips to get the most out of your usage

Since usage is tied to model costs, you can make your limits go further with a few simple habits:
  • Start with efficient models. For everyday tasks, models like Haiku 4.5 or GPT-5.4 Mini use a fraction of the cost of premium models. Switch to Sonnet, GPT-5.4, or Opus when you need deeper reasoning.
    • Opus models typically use two to three times more of your limit than Sonnet models, so try Sonnet first.
    • GPT-5.2 Pro is exceptionally expensive and not recommended.
  • Start new conversations. Long conversations accumulate context, and the model processes the full conversation history with every message. Starting a new chat for a new topic keeps costs down.
  • Be mindful of large documents. Uploading or referencing large files adds significantly to the tokens processed per message. When possible, reference specific sections rather than entire documents.

What happens when you reach a limit

When you hit your session or weekly limit, your messages are automatically routed to GPT-5.2 until that window resets. You can continue working without interruption, just on a different model. If your admin has enabled usage requests, you will see a Request higher limits button in the chat. Your admin will be notified and can increase your limits or upgrade your plan.
If you reach a limit while the model is working, it is allowed to finish its response before switching. You won’t see a reply cut off halfway. Your next message will use GPT-5.2.

Increasing your limits

Your usage limits depend on the plan you are on. If you regularly hit your limits, your admin can:
There is also a spam protection limit of 250 messages per 3 hours, regardless of model cost. This limit exists to prevent automated abuse and does not affect normal usage. Last updated: April 2026