Models & providers

Model usage dashboard: cost control in practice

Break usage down by provider / model / vault — spot AI-field black holes and long-context abuse.

Kition Team·May 3, 2026·5 min read

What the dashboard shows

  • Today / this week / this month spend per provider
  • Top 10 most expensive agent sessions
  • AI Field fires + costs
  • Cumulative cost per vault

Common runaway patterns

  • A 1000-row AI field without manual-refresh
  • Long-context (>100K) jobs on the priciest model
  • Subagent recursion too deep (keep ≤ 2)
  • PostToolUse hook missing throttle, fires constantly

Ready when you are.

Kition is a local-first AI workspace. Markdown documents, structured tables, and an AI agent — running on your own machine, against the model provider you choose.