AI budget capacity planner
Daily API Budget Planner
Turn a monthly AI API budget and estimated request cost into safe daily, monthly, and per-user request limits.
Daily API budget plan
Safe request limits after budget reserve
$425.00
$14.17
85,000
2,833
2
Calculation basis
- Original monthly budget
- $500.00
- Reserved buffer amount
- $75.00
- Estimated cost per request
- $0.005
Formula
How API request limits are calculated
The reserve percentage is removed from the monthly budget before request limits are calculated from the estimated cost per request.
Safe monthly budget = monthly budget × (1 − reserve %)
Daily budget = safe monthly budget ÷ days per month
Requests per active user = floor(daily budget ÷ request cost ÷ active users)
export function requestLimits(input: {
monthlyBudget: number;
costPerRequest: number;
activeUsersPerDay: number;
daysPerMonth: number;
reservePercent: number;
}) {
const safeBudget =
input.monthlyBudget * (1 - input.reservePercent / 100);
const dailyBudget = safeBudget / input.daysPerMonth;
const requestsPerDay =
Math.floor(dailyBudget / input.costPerRequest);
return {
safeBudget,
dailyBudget,
requestsPerDay,
requestsPerUser:
Math.floor(requestsPerDay / input.activeUsersPerDay),
};
}Example API budget plan
A $500 monthly budget with a 15% reserve leaves $425 available for planned usage. At half a cent per request, that supports about 85,000 requests per month.
Use observed production request cost when available. Average request cost can change with prompt length, outputs, caching, retries, and tool calls.
What this estimate includes
- Reserved and spendable monthly budget
- Daily budget based on selected month length
- Monthly and daily request capacity
- Per-active-user daily request allowance
Frequently asked questions
Why reserve part of the API budget?
A reserve reduces the chance that traffic spikes, longer outputs, retries, or pricing changes exhaust the full monthly budget.
Where do I get cost per request?
Use the text-token, image, or audio calculator with a representative workload, then copy the estimated per-request or per-run cost.
Should request limits be rounded down?
Yes. Capacity limits use whole requests and round down so the estimate does not intentionally exceed the safe budget.
Does this replace provider billing limits?
No. Configure provider budgets, alerts, quotas, and application-side rate limits in addition to this planning estimate.
Related calculators
Related glossary terms
Input tokens
Input tokens are the tokenized units sent to a model, including instructions, user content, conversation history, retrieved context, and tool definitions.
OpenRequests per day
Requests per day is the number of billable API calls made during a day. TokenMath commonly derives it from requests per active user multiplied by active users.
OpenCost per request
Cost per request is the sum of all billable usage generated by one API call, commonly input token cost plus output token cost for a text model.
Open