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.
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.
| Company | Invocation metering | Compute charge layered on top | Included on entry paid tier |
|---|---|---|---|
| Vercel | $0.60 per million invocations | Active CPU $0.128/CPU-hour + Memory $0.0106/GB-hour | 1M invocations (Pro) |
| Modal | Not itemized — folded into pure-usage | Per-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.
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
- Credit-Based BillingA billing unit where customers pre-purchase or are allocated a pool of credits that deplete as they use the product, often at variable rates per feature.
- Token-Based PricingA billing unit common in LLM and AI products, where customers are charged per input and output token processed.
- Per-Seat PricingA billing unit where the vendor charges a fixed fee per named user, regardless of how much each user consumes.
- Per-Resolution PricingA billing unit unique to AI customer-support products, where the vendor charges only when an AI agent resolves a customer issue without escalation.
- Bandwidth-Based PricingA billing unit where customers are charged per gigabyte of data transferred out of the platform.
- CPU-Hour PricingA billing unit where customers are charged for the CPU time their workloads consume, typically measured in vCPU-seconds or vCPU-hours.
- GB-Hour PricingA billing unit where customers are charged for the memory their workloads consume over time, measured in gigabyte-hours.
- GPU-Hour PricingA billing unit where customers are charged for GPU time consumed, typically measured per-second or per-hour by GPU type.
- Per-API-Call PricingA billing unit where customers are charged per API request, regardless of payload size or processing time.
- Per-GB Storage PricingA billing unit where customers are charged per gigabyte of data stored on the platform per month.
- Media-Minute PricingA billing unit where customers are charged per minute of audio or video processed — used by speech, voice, and video AI vendors.
- Per-Request PricingA billing unit where customers are charged per request served — the generic meter for inference endpoints, search, scraping, and browser infrastructure.
- Per-Event PricingA billing unit where customers are charged per event ingested — the native meter of observability and billing-infrastructure platforms.
- Vector Storage PricingA billing unit where customers are charged for vectors stored or indexed — the storage dimension of vector database pricing.
- Per-Character PricingA billing unit where customers are charged per character of text processed — the standard meter for text-to-speech and translation.
- Per-Document PricingA billing unit where customers are charged per document processed or generated — common in AI writing, SEO, and document-intelligence tools.
- Per-Page PricingA billing unit where customers are charged per page crawled, parsed, or rendered — the meter for web scraping and document parsing.
- Per-Transaction PricingA billing unit where customers are charged per financial or billing transaction processed — the meter of billing and accounting platforms.
- Active-User PricingA billing unit where customers are charged per monthly or daily active user rather than per provisioned seat.
- Per-Task PricingA billing unit where customers are charged per task an automation or agent executes — Zapier's historical unit, now spreading to AI agents.
- Per-Unit PricingA billing unit used by robotics, hardware AI, and some SaaS companies where the metered object is a physical or abstract 'unit' — a robot deployed, a device sold, or a defined deliverable.
- Workflow Execution PricingA billing unit where each end-to-end workflow or automation run is metered and billed, regardless of the compute steps it contains.
- Per-Message PricingA billing unit where each individual message or reply in a conversation is metered, common in AI chat and voice platforms.
- Per-Invoice PricingA billing unit used by billing infrastructure platforms where each invoice generated or processed is metered as the primary cost driver.
- Per-Action PricingA billing unit where each discrete action taken by an AI agent or automation is metered — common in browser automation and agentic workflow tools.
- Per-Image PricingA billing unit where each AI-generated image is metered, common in image generation APIs and multimodal AI platforms.
- Per-Conversation PricingA billing unit where each complete customer conversation — from first message to resolution — is metered as a single chargeable event.
- Per-Record PricingA billing unit where each data record processed, labeled, or extracted is metered — common in data platforms and web scraping services.
- Per-Word PricingA billing unit common in translation and localization platforms where the metered object is the word count of content processed.
- Per-Video PricingA billing unit where each AI-generated video is metered, common in video generation and synthetic media platforms.
- Milestone-Based PricingA billing unit used in drug discovery and biotech AI where payment is tied to achieving defined research milestones rather than time or compute consumed.
- Per-Outcome PricingA billing unit where payment is triggered by verified outcomes delivered — distinct from outcome-based pricing models, this refers specifically to 'outcomes' as a countable billing unit.
- Per-Datapoint PricingA billing unit where each individual data measurement or signal ingested is metered — common in cloud cost intelligence and ML evaluation platforms.
- Per-Interaction PricingA billing unit where each patient-agent or user-agent interaction is metered, common in healthcare AI and customer engagement platforms.
- Data Licensing PricingA pricing structure where access to proprietary datasets or data assets is licensed separately from the software or services, common in AI training data and clinical data platforms.
- Robot-Hour PricingA billing unit where each hour a robot or autonomous system operates is metered — the robotics equivalent of a GPU-hour.
- Per-Contact PricingA billing unit where each contact or lead in the database is metered, common in AI sales development and outbound automation platforms.
- Per-Mailbox PricingA billing unit where each connected email mailbox or sending account is metered, common in AI outbound sales and email automation platforms.
- Browser-Hour PricingA billing unit where each hour of headless browser compute time is metered, common in web scraping and browser automation platforms.
- Per-Generation PricingA billing unit where each AI-generated creative asset — image, video, or design — is counted as a 'generation' and metered accordingly.
- Per-Ticket PricingA billing unit where each customer support ticket handled by an AI agent is metered — common in AI customer service platforms.
- Per-Log PricingA billing unit where each LLM request log ingested or stored is metered — common in AI observability and evaluation platforms.
- Per-Trace PricingA billing unit where each distributed trace — a complete record of an LLM request chain — is metered, common in AI observability platforms.
- Per-IP PricingA billing unit where each IP address or proxy endpoint allocated is metered — used by web scraping proxy providers.
- Per-Device PricingA billing unit where each hardware device or endpoint connected to the AI platform is metered.
- Per-Case PricingA billing unit used in legal AI platforms where each case or matter processed by the AI is metered.
- Per-Report PricingA billing unit where each AI-generated report or analysis document is metered as a discrete output.