Model Hosting Cost Calculator
Cost a serving endpoint, with the idle hours shown separately.
In short
Formula: C = i x (ha + hi) x R + Storage + Fee
What this calculator does
Instance-hours times rate. Serving and idle hours are costed at the same rate but reported separately, because a provisioned endpoint bills whether or not traffic arrives, and the split is what makes idle cost visible.
Use it to turn Currency, Price per instance-hour, Instances held, Hours serving traffic, and the other shown inputs into a checked result you can compare, copy, or rerun with different assumptions.
The page shows the formula, a numeric worked example, and the assumptions that affect this professional & industry calculation.
Inputs and what they mean
- Currency
- — Amounts are shown in the currency you pick. No exchange rate is applied..
- Price per instance-hour
- — Take this from your own bill or the provider's price page. No provider price is built in..
- Instances held
- — Serving instances or replicas kept up..
- Hours serving traffic
- — Hours the endpoint handled requests..
- Hours idle but still billed (optional)
- — Optional component. Leave at 0 to exclude it from the result. Hours the endpoint was up with no traffic..
- Model storage cost (optional)
- — Optional component. Leave at 0 to exclude it from the result..
- Fixed platform fee (optional)
- — Optional component. Leave at 0 to exclude it from the result..
- Price as of (optional)
- — The date you took these prices. It is shown with the result so the figure is never read as a current vendor price..
- Price source (optional)
- — Where the prices came from. Shown with the result..
How to use it
- Enter your own figures — the calculator never fills in a rate, price or benchmark for you.
- Press Calculate to see the result.
- Read the formula, variables, assumptions and source below the result before you rely on it.
Formula
C = i x (ha + hi) x R + Storage + Fee.
Inputs used: Currency, Price per instance-hour, Instances held, Hours serving traffic, Hours idle but still billed (optional), Model storage cost (optional), Fixed platform fee (optional), Price as of (optional), and other shown inputs.
Edge handling: Price per instance-hour is required.; Price per instance-hour cannot be negative.; Price per instance-hour must be no more than 1000000000.; Instances held is required.; Instances held cannot be negative..
Worked example
Two instances up for 600 serving hours and 120 idle hours
- Start with Currency: USD, Price per instance-hour: 4.10, Instances held: 2, Hours serving traffic: 600, Hours idle but still billed (optional): 120, Model storage cost (optional): 0.
- Apply the method: C = i x (ha + hi) x R + Storage + Fee.
- Idle time is shown separately because it is billed just the same.
Reading the result
The headline figure is the main answer. Any breakdown underneath shows the parts that make it up, so you can check the working and see what changes when you adjust an input.
Limitations and assumptions
- Inputs outside the supported range are rejected rather than forced into a result.
- The result depends on the values you enter for this model hosting cost calculator; it does not supply missing rates, rules, prices, dates, or assumptions for you.
Reference: The Linux Foundation — Unit economics — FinOps Framework
Last reviewed:
Common questions
Where does this formula come from?
FinOps Framework capability: unit economics — cost per business unit is total cost for a period divided by the units delivered in the same period; a workload's cost is the sum of its metered components charged at the rates the organisation actually pays. See the source link on this page.
What kind of calculation is this?
Instance-hours held, serving and idle, priced at the user's per-instance-hour rate. Check the formula, example, and limitations on this page before using the result for a real professional & industry decision.
What are its limits?
Arithmetic over the figures entered — it cannot tell whether the metering, logs or invoices behind them are complete. The result is only as current as the rates entered; a rate taken months ago is not a current price. Tiered, committed-use, cached-input and minimum-spend pricing are not modelled unless the user has already reduced them to the rates entered. Autoscaling means the instance count changes through the period; a single count is an average the user has chosen. Per-token charges on a hosted endpoint are not included here — cost those with the inference calculator.
How do I use the Model Hosting Cost Calculator?
Enter the required values for Currency, Price per instance-hour, Instances held, Hours serving traffic, Hours idle but still billed (optional), and the other fields shown. The calculator applies the formula on this page and shows the main result with any supporting breakdown so you can check the arithmetic.
What formula does the Model Hosting Cost Calculator use?
C = i x (ha + hi) x R + Storage + Fee The visible formula section above lists the calculation path and the edge cases the page handles, so the result can be checked without relying on the form alone. Check the formula, example, and limitations on this page before using the result for a real professional & industry decision.
Can the Model Hosting Cost Calculator be used for exact decisions?
Use it as a calculation aid, not as a substitute for checking the underlying rule, contract, policy, or professional advice that applies to your situation. When a result depends on local rules, personal details, prices, or dates, enter those values yourself and confirm them before acting.
Formula, source and verification
Instance-hours held, serving and idle, priced at the user's per-instance-hour rate.
The question it answers: What did training this model cost, including the restarts, and what does the endpoint cost to keep up?
The formula
C = i x (ha + hi) x R + Storage + Fee
- i — Instances
- (instances). Serving instances or replicas kept up.
- ha — Hours serving traffic
- (h). Hours the endpoint handled requests.
- hi — Hours idle but billed
- (h). Optional; excluded at zero.
- R — Price per instance-hour
- (currency). From the user's own bill or price page.
- S — Model storage cost
- (currency). Optional; excluded at zero.
- F — Fixed platform fee
- (currency). Optional; excluded at zero.
Units: Instances and hours in, currency out.
What kind of calculation this is
Business input model. The answer depends on business figures only you can supply, such as your own costs, rates or volumes. No market or benchmark values are assumed for you.
Method
Instance-hours times rate. Serving and idle hours are costed at the same rate but reported separately, because a provisioned endpoint bills whether or not traffic arrives, and the split is what makes idle cost visible.
Assumptions built into the result
- Mathematical: All the figures entered cover the same measurement period.
- Mathematical: Token counts, requests and hours are taken from the user's own logs or bill.
- Mathematical: Instances were billed for every hour they were up.
- Mathematical: Serving and idle hours are charged at the same rate.
Figures this calculator will never guess for you
- No target, benchmark, industry average or typical figure is supplied for any value.
- A definition is never presented as a goal: a cost per request is not a target cost per request, and a contribution margin is not a target margin.
- No model price, GPU price, rate card or list price is built in; every amount is entered by the user.
- No token count, context length or output length is assumed on the user's behalf.
- No currency conversion is applied; amounts stay in the currency selected.
- No traffic pattern, autoscaling behaviour or acceptable idle share is assumed.
Limitations
- Arithmetic over the figures entered — it cannot tell whether the metering, logs or invoices behind them are complete.
- The result is only as current as the rates entered; a rate taken months ago is not a current price.
- Tiered, committed-use, cached-input and minimum-spend pricing are not modelled unless the user has already reduced them to the rates entered.
- Autoscaling means the instance count changes through the period; a single count is an average the user has chosen.
- Per-token charges on a hosted endpoint are not included here — cost those with the inference calculator.
Source and version
- Standard or reference
- FinOps Framework — unit economics and workload cost — FinOps Foundation (FinOps Framework capability: unit economics — cost per business unit is total cost for a period divided by the units delivered in the same period; a workload's cost is the sum of its metered components charged at the rates the organisation actually pays.)
- Published source
- The Linux Foundation — FinOps Framework
- Formula version
- Version 1
- Verification
- Reviewed against the cited source on
- How much weight the source carries
- Standards or government
- Applies to
- Currency
- Amounts stay in the currency you choose; no exchange rate is applied.
Related tools
Work out the hourly rate to charge a client so that target margin is met after overhead and non-billable time.
Find the true hourly cost of an employee once benefits, payroll cost and overhead are included.
Size a software application from its data and transaction functions before estimating effort or cost.
Estimate development effort, schedule and average team size for a software project of a known size.
Express cloud spend as a cost per customer, per transaction or per other business unit.
Set the rate used to apply manufacturing overhead to jobs for the coming period.