Sold by: Modal
Deployed on AWS
Modal is a serverless compute platform for AI, ML, and data teams.
4.1
Overview
Modal is a serverless compute platform for AI, ML, and data teams. We make it easy for developers to run workloads like ML inference, fine-tuning, and batch data jobs in the cloud. Our custom infrastructure allows us to spin up GPU-enabled containers in as little as one second, helping you iterate fast and scale up to large production workloads. We scale resources up and down for you so you only ever pay for what you use.
For custom pricing options and private offer please contact here .
Please contact sales@modal.com to discuss pricing before purchasing Modal.
Highlights
- Autoscale to hundreds of GPUs and back down to zero in seconds, without managing and configuring boilerplate infra.
- Deploy Python functions to the cloud using infrastructure-as-code to define custom container images and hardware requirements.
- Pay as you go and only pay for the resource time you use.
Details
Sold by
Delivery method
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Trust Center
Access real-time vendor security and compliance information through their Trust Center powered by Drata or Vanta. Review certifications and security standards before purchase.
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on the duration and terms of your contract with the vendor, and additional usage. You pay upfront or in installments according to your contract terms with the vendor. This entitles you to a specified quantity of use for the contract duration. Usage-based pricing is in effect for overages or additional usage not covered in the contract. These charges are applied on top of the contract price. If you choose not to renew or replace your contract before the contract end date, access to your entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/month |
|---|---|---|
Enterprise Platform Fee | The Enterprise tier monthly platform fee covers access to the full enterprise feature set, including >50 GPU concurrency, region selection, a private support channel, SSO, HIPAA BAAs, and more. This is separate from the usage component of billing, which is described in detail below. Usage pricing can be discounted based on volume commits. | $1,000,000.00 |
Dimension | Description | Cost/unit |
|---|---|---|
Modal Add-ons | Add-ons | $0.01 |
Modal Usage | Usage | $0.01 |
Vendor refund policy
All fees are non-refundable and non-cancellable except as required by law.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Resources
Vendor resources
Support
Vendor support
Private Slack channel with the Modal team.
support@modal.com
support@modal.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Updated weekly
Top
10
In Serverless Workloads
Top
10
In High Performance Computing
Top
50
In High Performance Computing
Sentiment is AI generated from actual customer reviews on AWS and G2
Functionality
Ease of use
Customer service
Cost effectiveness
Positive reviews
Mixed reviews
Negative reviews
AI generated from product descriptions
GPU Container Provisioning
Spin up GPU-enabled containers in as little as one second with custom infrastructure for rapid iteration and scaling.
Autoscaling Capability
Automatically scale resources from zero to hundreds of GPUs and back down based on workload demands without manual infrastructure management.
Infrastructure as Code Deployment
Deploy Python functions to the cloud using infrastructure-as-code to define custom container images and hardware requirements.
Serverless Compute Architecture
Serverless compute platform that abstracts infrastructure management for ML inference, fine-tuning, and batch data processing workloads.
Pay-Per-Use Resource Billing
Resource-based billing model that charges only for the actual compute time consumed during workload execution.
Distributed Computing Runtime
Unified runtime that distributes Python code and AI libraries across thousands of CPUs, GPUs, or both, scaling from single machine to large clusters
Multi-Framework Support
Support for distributed execution of XGBoost, PyTorch, vLLM, and other AI libraries within a single platform
Infrastructure Deployment Flexibility
Deployment options including fully managed Anyscale-hosted experience, bring-your-own-cloud (BYOC) into customer VPC, VM-based infrastructure (EC2), and Kubernetes environments (AWS EKS and SageMaker HyperPod)
Enterprise Security Integration
Native integration with AWS security frameworks including AWS Identity and Access Management (IAM) with inherited access controls, policies, and governance standards
Workload Optimization and Resilience
Built-in head node resilience, intelligent autoscaling, advanced scheduling, GPU sharing capabilities, and safe rollout mechanisms to maximize resource utilization and prevent cost overruns
Workflow Orchestration Framework
Open-source Metaflow framework for designing and developing data science and ML/AI applications
Managed Kubernetes Infrastructure
Scalable, cost-optimized, fully managed Kubernetes cluster specifically tuned for data-intensive batch workloads and GPU-accelerated computing
High Availability Management
Enterprise-grade infrastructure with managed high availability for business-critical ML and data workloads
Data Isolation and Compliance
SOC2 compliant security architecture ensuring no data or code leaves the customer's account
GPU Compute Support
Native support for demanding GPU requirements of modern AI and machine learning workloads
Standard contract
No
Customer reviews
LOKESH G.
Simple Serverless GPU Deployments with an Excellent Python Developer Experience
Reviewed on Jul 29, 2026
Review provided by G2
What do you like best about the product?
Modal Labs offers a simple serverless deployment workflow for Python applications and AI workloads. It makes it easy to run GPU-intensive jobs without having to manage infrastructure, scales automatically with demand, and delivers fast startup times. The developer experience is excellent, with smooth integration into existing Python projects and a straightforward way to deploy machine learning models, batch jobs, and APIs.
What do you dislike about the product?
One downside of Modal Labs is that some of the more advanced configuration and debugging options can take time to learn, especially for users who are new to serverless infrastructure. For long-running or highly customized workloads, it may also take extra experimentation to fully understand resource limits and figure out how to optimize costs.
What problems is the product solving and how is that benefiting you?
Modal Labs addresses the challenge of deploying and scaling AI, machine learning, and Python workloads without having to manage servers or GPU infrastructure. It makes it easy to deploy APIs, batch jobs, and model inference quickly, while automatically taking care of scaling and resource provisioning. As a result, it cuts down on operational overhead, accelerates development, and lets me focus on building and improving my applications rather than spending time maintaining infrastructure.
Jeni J.
Deploying AI Workloads Has Never Been Easier
Reviewed on Jul 28, 2026
Review provided by G2
What do you like best about the product?
I love using Modal Labs because it simplifies deploying GPU-powered AI workloads. The developer experience is excellent, allowing me to turn Python functions into scalable cloud services with very little code. Automatic scaling works seamlessly, and the fast startup times make it easier to build, test, and deploy AI applications without worrying about infrastructure. I really appreciate how well Modal Labs handles GPU provisioning and batch workloads behind the scenes. The integrations with popular Python AI frameworks are smooth, logs and monitoring are easy to follow, and the ability to scale from a small prototype to production without changing much code makes the development workflow much more efficient. Also, the initial setup was very easy.
What do you dislike about the product?
One area that could be improved is cost visibility and monitoring for GPU-intensive workloads, especially as projects scale. I'd also like to see more built-in debugging and profiling tools for long-running jobs, along with additional deployment templates and examples for common AI use cases to help new users get started even faster. One improvement would be a real-time cost dashboard that breaks down GPU usage and estimated spending by deployment, batch job, or individual function, making it easier to spot expensive workloads before costs grow unexpectedly. For debugging, I'd like more detailed execution traces, GPU utilization metrics, memory usage graphs, and easier access to logs from failed or long-running jobs, along with built-in recommendations for optimizing performance and reducing resource consumption.
What problems is the product solving and how is that benefiting you?
I use Modal Labs to deploy and scale AI applications without managing cloud infrastructure. It eliminates the complexity of provisioning and managing GPU infrastructure, allowing me to deploy models, run batch jobs, and serve inference with minimal setup. This speeds up development and focuses on building AI applications.
Computer Software
Revolutionizing AI Workloads with Ease
Reviewed on Jul 16, 2026
Review provided by G2
What do you like best about the product?
I like how Modal Labs completely eliminates the infrastructure tax since we don't have to manage Kubernetes, configure CUDA drivers, or manually build Docker containers just to run a Python script on a GPU. Their custom container runtime boots up in seconds, allowing us to run local code on cloud GPUs almost instantly. I appreciate defining the GPU environment directly in Python with simple decorators, avoiding the headache of Docker, Kubernetes, and CUDA. I also enjoy Modal's shared storage volumes and network file systems for machine learning, which let us persist heavy model weights and training datasets across separate runs. The parallel mapping feature is particularly beneficial, enabling us to effortlessly scale a single Python function across hundreds of parallel CPU or GPU containers to process large datasets in minutes rather than hours. Additionally, the initial setup was straightforward with just pip commands.
What do you dislike about the product?
I find the lack of self-hosting or private VPC options to be a dealbreaker for enterprises with strict compliance requirements, and the proprietary Python SDK can lead to vendor lock-in. Additionally, running steady, 24/7 GPU workloads on their serverless model is much more expensive than renting dedicated instances from traditional cloud providers.
What problems is the product solving and how is that benefiting you?
I use Modal Labs to eliminate infrastructure tax and idle GPU costs, run tasks using simple Python decorators, and scale functions efficiently. It simplifies our workflow by managing serverless GPU and CPU compute tasks without the need to handle complex cloud infrastructure.
Uri G.
Solid Service, Unexpected Charges
Reviewed on Jul 07, 2026
Review provided by G2
What do you like best about the product?
Solid offering, a lot of unexpected payments that lead us to switch to another provider
What do you dislike about the product?
Got unexpected payments, even after closing the account
What problems is the product solving and how is that benefiting you?
Modal has a GPU as a service that is generally more cost effective than aws/gcp
reviewer2855421
Low-friction compute has accelerated my prototyping and supports fast code evaluation runs
Reviewed on Jun 22, 2026
Review provided by PeerSpot
What is our primary use case?
My main use case for Modal Labs is to accelerate my prototypes because I find it effective.
A specific example of a prototype I accelerated using Modal Labs is when I wanted to run evaluations for code generation models, so I used Modal Labs to deploy containers to run them on a specific environment.
How has it helped my organization?
Modal Labs has positively impacted my organization and my work because I don't think there is any other provider that lets me attach it as functions, and I think it fits my workflow more naturally.
What is most valuable?
The best features Modal Labs offers are how quick it is to provision containers and the fact that you can attach compute as functions.
The speed of provisioning containers and the attached compute function are valuable to me because it makes it efficient and fast to use.
What needs improvement?
Modal Labs could be improved by not charging for the building of containers, as it turns out to be more expensive for certain use cases like mine where I have to try out many different containers.
I chose an eight because if they made their free tier a bit more generous and also did not charge for building containers, I would give it a nine.
For how long have I used the solution?
I have been using Modal Labs on and off for around a year.
What other advice do I have?
I don't have anything else to add about my main use case or how Modal Labs fits into my workflow.
I don't want to add anything else about the features.
I don't measure my outcomes with Modal Labs, but my experience has been pretty good for use cases where other providers, which usually involve renting out the full VM, is too much of a high-friction option. This being low-friction is valuable.
I have no comments regarding Modal Labs's AI capabilities, specifically about its governance and security because I haven't used it in that context.
Regarding Modal Labs's AI capabilities, I find its accuracy and reliability of output to be extremely reliable. I don't think there is anything to improve regarding accuracy because it is a provider.
I use Modal Labs for experimentation on and off, and I do not properly deploy it.
I did not purchase Modal Labs through the AWS Marketplace. I used the free tier.
My advice to others looking into using Modal Labs is to try it, as they have thirty dollars of free credits every month.
I give Modal Labs an overall rating of eight.