DeployWhere

Modal

Serverless infrastructure for AI inference, training, batch processing, and sandboxes.

No reviews yet. Write the first.
Visit Modal

Modal is a GPU and AI hosting provider based in United States. It operates European infrastructure in Germany and Ireland. A free tier is available. As a US company it falls under the US CLOUD Act. Pricing on this page is published only after a human has reviewed it.

PricingPros and consSpecificationsAboutReviews
Company based in
United States
European regions
GermanyIreland
US CLOUD Act
US company
GDPR agreement
Available
Free tier
Starter costs $0 plus compute and includes $30 / month in free credits.
VAT
Shown excluding VAT
Modal website
Website image published by Modal.

Pricing

17 plans
  • Nvidia B300
    GPU Tasks resource cost.
    Monthly
    $0.001972 / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Nvidia B200
    GPU Tasks resource cost.
    Monthly
    $0.001736 / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Nvidia H200 SXM
    GPU Tasks resource cost.
    Monthly
    $0.001261 / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Nvidia H100 SXM5
    GPU Tasks resource cost.
    Monthly
    $0.001097 / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Nvidia RTX PRO 6000
    GPU Tasks resource cost.
    Monthly
    $0.000842 / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Nvidia A100, 80 GB
    GPU Tasks resource cost.
    Monthly
    $0.000694 / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Nvidia A100, 40 GB
    GPU Tasks resource cost.
    Monthly
    $0.000583 / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Nvidia L40S
    GPU Tasks resource cost.
    Monthly
    $0.000542 / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Nvidia A10
    GPU Tasks resource cost.
    Monthly
    $0.000306 / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Nvidia L4
    GPU Tasks resource cost.
    Monthly
    $0.000222 / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Nvidia T4
    GPU Tasks resource cost.
    Monthly
    $0.000164 / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Physical core
    CPU resource cost. 2 vCPU equivalent. Minimum of 0.125 cores per container.
    Monthly
    $0.0000131 / core / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Memory
    Memory resource cost.
    Monthly
    $0.00000222 / GiB / sec
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Volumes
    Includes 1 TiB / mo free.
    Monthly
    $0.09 / GiB / mo
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Starter
    Plus compute / month. Includes $30 / month free credits, up to 3 seats, 100 containers, and 10 GPU concurrency. Scheduled and Web Functions are limited.
    Monthly
    0 USD
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Team
    Plus compute / month. Includes $100 / month free credits, unlimited seats, 5000 containers, and 50 GPU concurrency.
    Monthly
    250 USD
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed
  • Enterprise
    Custom compute pricing. Includes volume-based discounts, higher GPU concurrency, private Slack support, and embedded ML engineering services.
    Monthly
    Custom
    vCPU
    Not listed
    Memory
    Not listed
    Storage
    Not listed

Pros and cons

What works

  • Pay-as-you-use compute pricing with no charge for idle resources.
  • Starter includes $30 / month in free compute credits.
  • Autoscaling from zero is stated, with GPU concurrency available on paid plans.
  • SOC 2 compliance and HIPAA compatibility are listed.

What to watch

  • Team has a $250 monthly fee in addition to compute charges.
  • Enterprise pricing is custom.
  • Starter has limited Scheduled and Web Functions.
  • Region selection costs 1.5 to 1.75 times base prices.
  • Non-preemptible execution costs 3 times base prices.

Specifications

Supported runtimes
Python
Certifications
SOC 2
Support
Starter and Team include access to Modal Community Slack; Enterprise includes support via private Slack.

About Modal

Modal provides serverless infrastructure for AI inference, training, batch processing, and sandboxes. It charges for compute and storage usage, with Starter, Team, and Enterprise workspace plans. The page states that workloads run across clouds and regions, with region selection available at 1.5 to 1.75 times base prices.

Reviews

None yet

No approved reviews yet. Every review is read by a person before it appears, and only approved reviews count toward a rating.

Other gpu and ai hosting

See all
DataCrunch
Finland
Exoscale GPU
Switzerland
IONOS AI
Germany
Nebius
Netherlands
OVHcloud AI
France
Scaleway GPU Instances
France

Something here out of date?

Every figure on this page was checked by a person, and providers change their plans without telling anybody. Say what moved and it gets checked again.

Work at Modal? Claim this listing to correct the description and add screenshots. Verification is a confirmation link to an address on your own domain. Pricing still goes through the same check as every other listing here.