Per-Function-Invocation Pricing: Examples & Companies

2 companies in the corpus Updated stub analysis
Definition

Per-Function-Invocation Pricing is a billing unit where customers are charged per serverless function invocation, often combined with a separate compute-time charge.

Also known as: Serverless Function PricingLambda-Style Pricing

What is it

Per-Function-Invocation Pricing is a billing unit where customers are charged per serverless function invocation, often combined with a separate compute-time charge.

It is the AWS Lambda-style billing unit, now standard across serverless platforms. The unit of work is a single function call: each time your code runs — triggered by an HTTP request, a queue message, a cron schedule, or another function — the platform counts it. The count itself is cheap (fractions of a cent per call), so the structural question is never the per-invocation rate. It is whether the vendor stops at the count or layers a separate compute-time charge on top — and that second charge is what makes the model variable for heavy workloads.

Vercel shows the two-part structure most clearly. Its Pro plan meters invocations at $0.60 per million (1M included), then bills the compute behind them separately as Active CPU hours ($0.128/CPU-hour) and Provisioned Memory GB-hours ($0.0106/GB-hour). The invocation line is deliberately one of the smallest on the bill because the platform’s real cost is the compute, not the call. Modal sits at the other end: it folds invocations into a pure-usage per-second model where the compute behind each call (GPU, CPU, and memory) is the entire cost, and a scaled-to-zero function between invocations costs nothing.

The model aligns the bill to actual work rather than provisioned capacity — you pay for calls that happened, not for servers waiting for calls. The trap: the headline per-invocation rate hides the compute-time charge underneath it, which is where the bill actually lives. For the mechanics of metering a usage event like this, see choosing the right usage metric.

The invocation line is the cheap part · Vercel Pro
The invocation count is cheap — the compute is the bill VERCEL PRO · 15M invocations / mo $9 $0.60/M calls INVOCATIONS $5 CPU-hr $32 Provisioned memory · $0.0106/GB-hr COMPUTE = $37 OF THE ~$46 BILL MODAL · pure per-second usage No itemized invocation fee. Each call bills only the compute it consumes — a 30s H100 job = 30 × $0.001097 = $0.033 . Scaled to zero between calls = $0 . MODEL THE COMPUTE BEHIND THE CALLS — NOT THE CALL COUNT.

How it works

The base mechanic is a simple count: invocation_charge = invocations × per-invocation rate. But on every platform that uses it, the invocation count is only one of two (or more) metered dimensions. The real bill is invocation_charge + compute_charge, and the compute charge is the one that scales with workload weight.

CompanyInvocation meteringCompute charge layered on topIncluded on entry paid tier
Vercel$0.60 per million invocationsActive CPU $0.128/CPU-hour + Memory $0.0106/GB-hour1M invocations (Pro)
ModalNot itemized — folded into pure-usagePer-second compute: GPU $0.000164–$0.001736/sec, CPU $0.0000131/core/sec, memory $0.00000222/GiB/sec$30/mo credits (Starter)

Worked example — Vercel. A medium-traffic Next.js app on Pro runs 15M function invocations in a month. The invocation line is 15M × $0.60/M = $9. The compute behind those calls is billed separately: roughly 40 Active-CPU-hours (40 × $0.128 = $5) plus ~3,000 GB-hours of memory (3,000 × $0.0106 = $32). The invocation count is $9 of a ~$46 function-execution subtotal — proof that the count is the cheap part and the attached compute is where the variable cost sits. Vercel’s Active CPU billing further cuts the compute side by charging $0 for I/O-wait time.

Worked example — Modal. Modal does not publish a separate per-invocation fee; each call’s cost is the per-second compute it consumes. A function that invokes an H100 for a 30-second batch job costs 30 × $0.001097 = $0.033 in GPU time, plus negligible CPU and memory. Because billing is per second and scale-to-zero is free, a function invoked 100 times a day for 30 seconds each costs only the 3,000 seconds it actually ran — there is no idle charge between invocations. This is the pure-usage end of the spectrum, where the invocation is real but the compute it triggers is the whole price.

The per-invocation rate is a rounding error next to the compute-time charge. When evaluating any per-invocation vendor, model the compute behind the calls — duration, hardware, and memory — not the invocation count. The usage-based pricing guide covers forecasting a metered bill like this, and you can model a real Vercel bill with the Vercel pricing calculator.


Companies using this

Two corpus companies meter function invocations, bracketing the model’s two ends. Vercel uses the explicit Lambda-style structure — a published $0.60-per-million invocation line on top of multi-dimensional compute metering. Modal folds invocations into a pure-usage per-second model where the compute behind each call is the entire cost.

Company Product Pricing modelBilling unitsFree tier Verified
ModalServerless compute and GPU platform — per-second billing for Python functions, batch jobs, and model servingYes2026-05-29
VercelFrontend cloud platformYes2026-07-06

Explore this theme in the knowledge graph

FAQ

What is per-function-invocation pricing?

Per-function-invocation pricing is a billing unit where customers are charged per serverless function call, usually combined with a separate compute-time charge. Vercel bills $0.60 per million invocations; Modal meters the per-second compute behind each call. The invocation count is cheap — the attached compute is the variable cost.

How is invocation count different from compute time?

Invocation count meters how many times a function ran; compute time meters how long it executed and on what hardware. Vercel separates the two explicitly — $0.60 per million invocations plus $0.128 per Active-CPU-hour — so a function called often but running briefly costs little, while a function running on a GPU for minutes costs more.

How much does a function invocation cost?

On Vercel, function invocations are $0.60 per million on Pro (1M included), making the invocation line one of the smallest on a typical bill. Modal does not itemize a per-invocation fee on its public rate card; the cost is dominated by the per-second compute behind each call (e.g., H100 at $0.001097/sec).

Why do serverless platforms meter invocations at all if compute dominates the bill?

The invocation count is the cleanest proxy for the fixed per-call overhead — scheduling, cold-start, and routing work the platform performs regardless of how long your code runs. A small per-invocation fee covers that overhead, while a separate compute-time charge captures the variable cost of actually executing your code.

Which companies use per-function-invocation pricing?

In this corpus, Vercel and Modal both meter function invocations. Vercel charges an explicit $0.60 per million on top of multi-dimensional compute metering; Modal folds invocations into its per-second pure-usage model across GPU, CPU, and memory.

Related billing units

Back to companies