Kaizen

Usage & Limits

Your plan's monthly allowance is a single usage wallet shared across every AI feature in Kaizen. This page explains what counts as usage, how to monitor it, and the per-plan rate limits.

What counts as usage

All AI-powered actions draw from the same monthly allowance:

  • Workflow executions — the $0.001 base execution charge plus any AI model token cost (see Cost Calculation)
  • Zensei assistant — chat turns with Kaizen's AI assistant
  • AI game generation — generating games with AI
  • AI field generation — the wand / AI-assisted field and content generation

There are no per-feature micro-budgets for cost — everything shares one balance. Model token costs use a 1.5x multiplier on hosted (Kaizen-provided) API keys; bringing your own API key (BYOK) removes the markup and you pay only the base execution charge. See Cost Calculation for the full formula.

Non-AI actions — creating todos, editing buckets, running workflows that contain no AI blocks — only incur the tiny base execution charge (for workflows) or nothing at all.

How to monitor usage

In the app: open Settings → Subscription to see real-time usage for the current period, your limit with progress indicators, projected charges, and billing history.

Programmatically: query the usage API with your API key:

curl -X GET -H "X-API-Key: YOUR_API_KEY" -H "Content-Type: application/json" \
  https://kaizenseason.com/api/users/me/usage-limits

The response includes usage.currentPeriodCost, your usage.limit, your plan, and current rate-limit token buckets. See Cost Calculation → Programmatic Usage Tracking for the full response shape.

Rate limits

Rate limits protect the platform from abuse and are separate from your dollar usage allowance. They cap how many requests per minute you can make, using a token-bucket algorithm (you can briefly burst above the sustained rate when you've been idle).

PlanSync (per minute)Async (per minute)
Free1050
Pro25200
Squad75500
  • Sync limits apply to synchronous requests (e.g. interactive API calls).
  • Async limits apply to background/asynchronous workflow executions.

When you exceed a rate limit, requests receive a 429 response with a Retry-After header. This is independent of your usage allowance — hitting a rate limit does not consume your monthly budget.

When you reach your allowance

  • Free: at the $10 cap, AI actions pause until the next monthly period. Upgrade to Pro to continue.
  • Pro / Squad: usage continues past the included amount as billed overage (if you've raised your cap), or pauses at your cap if you haven't. See How Billing Works.
On this page

On this page

Start building today
Trusted by over 60,000 builders.
Build Agentic workflows visually on a drag-and-drop canvas or with natural language.
Get started