This is the fine-print version of /docs/usage-limits. Same numbers, more precision about how they're measured.
Per-tier daily message caps
How the cap is measured
- Not fixed at midnight — a rolling 24-hour window from your first message.
- The number is a soft target based on average message input size (~1,000 tokens combined input+output per message). Very long chats with large attached files consume more per-message budget.
- The true underlying meter is input+output tokens per rolling 24h, not message count. Message count is the human-friendly approximation.
- Base tier true budget: ~600,000 tokens/24h. Plus: ~1.8M. Business: ~3.6M.
What counts toward the cap
- Your prompt text — input tokens.
- Attached file contents — input tokens (this is the big one; a 100K-token attached file eats 100K of your daily budget every time you send a message with it attached).
- System instructions from custom instructions or project instructions — input tokens.
- The model's response — output tokens.
- Chat history sent back to the model with each new message — input tokens (grows over long chats).
What doesn't count
- Failed messages that error out server-side (we don't charge for our own failures).
- Messages you sent but the model didn't complete (network dropped, etc.).
- Reading past chats or scrolling — no model calls involved.
- File uploads themselves (upload doesn't call the model; only sending a message that includes the file does).
What happens when you hit the cap
The UI shows a “you've reached your daily limit” state with the time your budget resets (the top of the rolling window). You can still open past chats, read them, and search. You cannot send new messages until the window rolls forward. There is no overage billing; caps are hard.
If you consistently hit caps
- First: check whether large attached files are the driver — Projects with heavy attached files eat budget fast.
- Second: consider upgrading to the next tier.
- Third: if Plus isn't enough for one person, that's genuinely unusual — email help@ladle.chat with what you're doing and we'll help figure out whether Business fits or whether the workflow needs restructuring.
Fair-use enforcement
Caps are self-enforcing (you hit them, you stop). We do not throttle preemptively or slow down based on load. Automation that generates messages programmatically (bots, scripts) against the web UI violates the AUP (see /legal/aup) even if under the cap — the caps assume a human at the keyboard.