Shape a single request, project it across a month of traffic, and see whether it fits your budget — plus the cache hit rate that would make it fit, and where a Direct lane crosses its Microsoft Foundry counterpart. Every figure traces to the same rate resolver the compare page uses.
Shape one request, then say how often it runs. Every number below updates immediately.
Interactive
Workload cost calculator
4K
800
50%
Share of input tokens served from cache. Applied only to models with a cache meter.
Time
Rows with a rate that changes by time of day, promo window or service tier are priced for this scenario instead of their flat listed rate; a brand-colored label under the model name names which one applies. Context size for band-priced rows uses the input-token count below.
Picking a specific hour also previews time-of-day rates that are scheduled but have not started billing yet; those rows are labelled · preview with their start instant. Now only ever shows rates that are billable at this moment.
%
USD
Projection
One representative month
Kimi K3, at 10.5K requests/day after growth — a single projected month, not a compounding multi-month forecast.
10.5K
Effective requests/day (after growth)
1260M
Monthly input tokens
252M
Monthly output tokens
$5859.00
Monthly spend · CHF 4716.49
1.8K / day
Affordable requests/day at this budget
This projection overruns your $1,000 budget by $4859.00 (CHF 3911.50).
Break-even
Cache hit rate needed to hit budget
The cache hit rate Kimi K3 would need, holding volume and growth fixed, to spend no more than your $1,000 monthly budget.
Out of reach at this volume: even 100% cache hit would still cost $4158.00, $3158.00 over your $1,000 budget.
Direct vs Foundry
Where deployment lanes cross over
The cache hit rate where a Microsoft Foundry lane for the same model as Kimi K3 becomes cheaper or stays pricier.