LADLE meters usage in tokens processed — input plus output, summed over a rolling 24-hour window. Every plan tier has a cap; when you approach it, sends are throttled (not blocked). The specific numbers per plan are below, plus how to check your dashboard, plus what the throttle actually does.
Per-plan caps (rolling 24h)
Numbers below are the hard cap. Base is generous for most workloads; Max tiers exist for heavy days.
What happens at the cap
When your rolling 24h consumption crosses ~85% of your cap, send latency increases by 500ms per message as a soft signal. At 100%, send latency increases further (typically 2-5s per message) and a visible mono banner appears in the composer: `RATE-LIMITED · RESUMES IN N MIN`. You keep working; you don't get blocked. Requests are queued and processed as your window rolls forward. No requests are dropped.
What counts toward the cap
Everything the model processes counts, including re-processing of persistent Project files on every message.
How to see current consumption
Settings → Usage shows your current rolling 24h consumption and where you sit relative to your cap. Broken down by chat, project, and time window. Real-time within ~30 seconds.
How to use less
The single biggest lever: attach files to Projects rather than chats. A project file attached to a 20-message chat costs ~1× the file's tokens; attached to 20 separate chats it costs ~20×. Second lever: interrupt bad responses early (Esc during streaming) — this stops the model mid-generation and reduces output tokens. Third: use ⌘R to regenerate rather than paraphrase your prompt, so the input tokens don't grow.
Which plan fits your usage
Base fits >90% of individual professional workloads. Max 5x is appropriate if you regularly attach large PDFs to multiple long-running chats. Max 20x is for people running the model constantly — several hours a day of active use with heavy file inputs. Try Base first; upgrade only if you actually hit the throttle multiple times a week.
Docs: File types and limits · Projects
Task guides in /help: What happens when you hit the cap. · Base vs Max 5x vs Max 20x.