Skip to Content
⏱️ Usage & Rate Limits

How Token Usage Works

Every message you send to Tesseract consumes tokens — small units that represent the text processed by the AI. Both your input (the message you send) and the output (the response you receive) count toward your usage.

Your token allowance resets on a rolling 5-hour window schedule.


Checking Your Usage

Open Settings → Billing to see your current token usage:

  • Progress bar — Visual indicator of how much of your allowance you’ve used
  • Tokens used / total — Exact numbers (e.g., 42,500 / 200,000)
  • Reset time — When your current usage window ends and your allowance refreshes

Token Limits by Plan

PlanToken limitWindow
Free200,000 tokens5 hours
Plus2,000,000 tokens5 hours

What Happens When You Hit the Limit

When you’ve used all your tokens for the current window:

  • You’ll see a warning as you approach the limit (at 80% usage).
  • Once the limit is reached, you’ll need to wait for the next window to continue chatting.
  • A fallback model may be available with a separate token allowance, allowing you to continue with a different model while you wait.
💡

Tip: Need more tokens? Upgrade to Plus for 10x the allowance — 2,000,000 tokens per window instead of 200,000.


Reset Schedule

Token windows reset at fixed 5-hour intervals in UTC:

  • 00:00, 05:00, 10:00, 15:00, 20:00 UTC The exact reset time for your current window is displayed in the Billing tab under your usage bar.

Model Access by Plan

Different plans have access to different AI models:

  • Free — A curated selection of default models
  • Plus — All available models, including larger and more capable options You can change your model at any time using the model selector in the composer area. If you select a model that isn’t available on your plan, you’ll be prompted to upgrade.