Understanding Billing & Credits
Bothive meters AI work in credits. This guide explains what you're paying for and how to stretch it.
What a credit is
AI and Bot steps consume credits from your plan's monthly pool (roughly tracking tokens used). Simple steps cost little; long reasoning over big context costs more. Check Usage in the dashboard to see where credits are going.
What's metered
- Running a bot (via the dashboard, API, or a workflow).
- AI nodes and Bot nodes inside a workflow.
- Anything that calls a model on your behalf.
Pure logic, delays, and passing data between steps don't burn model credits.
Rate limits & quota
Requests are rate-limited (requests per minute) and capped by a monthly quota, both scaled by your plan and billed to the key's owner. Hit a limit and you'll get a 429; metered responses also include an X-Quota-Remaining header.
Keep costs down
- Put a Fast model on routine steps (classify, route, short replies) and reserve Smart for hard reasoning.
- Cap output length on steps that only need a sentence.
- Keep knowledge bases focused so retrieval pulls less, cheaper context.
- Chain specialized bots instead of one giant do-everything prompt.
Upgrading
When sustained traffic outgrows your plan, upgrade under Billing. Higher tiers raise both the rate limit and the monthly quota.
Use the test pane to iterate quickly. Every change you make is live — no need to save first.
API keys are shown only once. Store them securely and never commit them to version control.
Test your bot with edge cases before deployment. Try empty inputs, long messages, and special characters.
Chain multiple specialized bots in a workflow for better results than one general-purpose bot.