AICloudCompareNederlands

Provider guide · Code on demand

Modal

Serverless Python compute for inference, training, and batch jobs.

Source checked 11 Oct 2026 · partial product record

We currently earn no commission from these links. How we fund this site

View Modal pricing (opens in a new tab)Explore 4 price records ↓
Good for
Run AI code when you need compute, with platform scheduling.
You manage
Application code, data and scaling settings.
GPUs listed
H100 SXM · H200 SXM · L40S PCIe · A100 (form factor unconfirmed)
Price basis
4 current compute rates · checked 14 Oct 2026
Not confirmed here
Live GPU availability, capacity in your region and your complete bill (storage, transfer, tax).

Understand the price

4 recorded configurations. Pick the one that fits.

Compare operating models →

Recorded compute prices help you estimate a workload. Availability and a complete bill still need checking with Modal.

We currently earn no commission from these links. How we fund this site

H100 SXM5 GPU task

1 GPU · Serverless GPU time

NVIDIA H100 SXM 80GB · serverless
Region not confirmed · Availability not checked

Price checked 14 Oct 2026 · valid until 21 Oct 2026, 00:39 UTC

$3.949 / hour

USD · 1 GPU · GPU resource rate

GPU only · CPU + memory extra

1 hour$3.95

8-hour day$31.59

Compute only. Estimate: a billing rule is not published.
Estimate my monthly cost →Check this price at Modal (opens in a new tab)
Configuration notes & source

Included

GPU resource only

Costs to check

CPU; Memory; Storage; Network egress above plan allowance; Paid plan subscriptions; Applicable taxes

Source notes

Hourly equivalents use exactly 3,600 seconds. A GPU-resource rate is not a complete application bill.

Modal lists region selection at 1.15–1.75× and non-preemptible execution at 3× base prices; those multipliers are not applied here.

CPU (minimum 0.125 core) and memory (minimum 128 MiB) are billed separately per container, as are load time and the 60-second idle keep-alive.

Official pricing source ↗

H200 SXM GPU task

1 GPU · Serverless GPU time

NVIDIA H200 SXM 141GB · serverless
Region not confirmed · Availability not checked

Price checked 14 Oct 2026 · valid until 21 Oct 2026, 00:39 UTC

$4.54 / hour

USD · 1 GPU · GPU resource rate

GPU only · CPU + memory extra

1 hour$4.54

8-hour day$36.32

Compute only. Estimate: a billing rule is not published.
Estimate my monthly cost →Check this price at Modal (opens in a new tab)
Configuration notes & source

Included

GPU resource only

Costs to check

CPU; Memory; Storage; Network egress above plan allowance; Paid plan subscriptions; Applicable taxes

Source notes

Hourly equivalents use exactly 3,600 seconds. A GPU-resource rate is not a complete application bill.

Modal lists region selection at 1.15–1.75× and non-preemptible execution at 3× base prices; those multipliers are not applied here.

CPU (minimum 0.125 core) and memory (minimum 128 MiB) are billed separately per container, as are load time and the 60-second idle keep-alive.

Official pricing source ↗

L40S GPU task

1 GPU · Serverless GPU time

NVIDIA L40S 48GB · serverless
Region not confirmed · Availability not checked

Price checked 14 Oct 2026 · valid until 21 Oct 2026, 00:39 UTC

$1.951 / hour

USD · 1 GPU · GPU resource rate

GPU only · CPU + memory extra

1 hour$1.95

8-hour day$15.61

Compute only. Estimate: a billing rule is not published.
Estimate my monthly cost →Check this price at Modal (opens in a new tab)
Configuration notes & source

Included

GPU resource only

Costs to check

CPU; Memory; Storage; Network egress above plan allowance; Paid plan subscriptions; Applicable taxes

Source notes

Hourly equivalents use exactly 3,600 seconds. A GPU-resource rate is not a complete application bill.

Modal lists region selection at 1.15–1.75× and non-preemptible execution at 3× base prices; those multipliers are not applied here.

CPU (minimum 0.125 core) and memory (minimum 128 MiB) are billed separately per container, as are load time and the 60-second idle keep-alive.

Official pricing source ↗

A100 80GB GPU task

1 GPU · Serverless GPU time

NVIDIA A100 80GB · form factor unconfirmed · serverless
Region not confirmed · Availability not checked

Price checked 14 Oct 2026 · valid until 21 Oct 2026, 00:39 UTC
Form factor not published by the provider

$2.498 / hour

USD · 1 GPU · GPU resource rate

GPU only · CPU + memory extra

1 hour$2.50

8-hour day$19.99

Compute only. Estimate: a billing rule is not published.
Estimate my monthly cost →Check this price at Modal (opens in a new tab)
Configuration notes & source

Included

GPU resource only

Costs to check

CPU; Memory; Storage; Network egress above plan allowance; Paid plan subscriptions; Applicable taxes

Source notes

Hourly equivalents use exactly 3,600 seconds. A GPU-resource rate is not a complete application bill.

Modal lists region selection at 1.15–1.75× and non-preemptible execution at 3× base prices; those multipliers are not applied here.

CPU (minimum 0.125 core) and memory (minimum 128 MiB) are billed separately per container, as are load time and the 60-second idle keep-alive.

Modal lists “A100, 80 GB” without a form factor.

Official pricing source ↗

Know when the meter is running.

GPU resource rates exclude separately metered CPU, memory, storage and paid plan charges.

Image/video pipelines and agent code execution are documented capabilities (reviewed 12 October 2026). You still configure the model, workflow and agent tools; external model APIs can cost extra.

Explore the setup

Check the product behind the name.

Products in this directory
Modal serverless computeCode on demandView product (opens in a new tab)
GPU hardware in this catalogue
H100 SXM · H200 SXM · L40S PCIe · A100 Unconfirmed
Region and availability
Confirm your selected product and region directly. Live capacity has not been checked.

Sources: official product information ↗ · official pricing ↗
Source review does not establish live availability or a commercial partnership.