About Modal
Modal is a high-performance AI infrastructure platform that runs CPU, GPU, and data-intensive compute at scale for AI and data teams. It delivers serverless inference, batch processing, and sandboxed code execution to reduce infrastructure overhead while keeping a near-local developer experience for experimentation and production workloads.
Key Features
When teams design AI workloads, fast start times and scalable, isolated execution matter. Modal addresses this reality with near-immediate starts, autoscaling, and serverless deployment:
Sub-second Cold Starts
Enables near-immediate start of compute, reducing latency for inference and batch jobs.
Instant Autoscaling
Automatically adjusts compute resources to match workload, preserving performance while minimizing idle capacity.
Serverless Inference
Runs inference without managing servers, offering on-demand resources and simplified deployment.
Sandboxed Code Execution
Provides isolated environments for safe experimentation, training tasks, and secure code execution.
Summary
Best for AI and data teams, ML engineers, and product teams running inference, training, and batch processing at scale.
Pricing
View pricingStarter
$0 / month
- $30 / month free credits
- 3 workspace seats included
- 100 containers + 10 GPU concurrency
- Crons and web endpoints (limited)
- Real-time metrics and logs
- Region selection
Team
$250 / month
- $100 / month free credits
- Unlimited seats
- 1000 containers + 50 GPU concurrency
- Unlimited crons and web endpoints
- Custom domains
- Static IP proxy
- Deployment rollbacks
Enterprise
Custom / compute
- Volume-based discounts
- Unlimited seats
- Higher GPU concurrency
- Embedded ML engineering services
- Support via private Slack
- Audit logs, Okta SSO, and HIPAA
