About Modal
Modal is AI infrastructure that developers love, enabling you to run inference, training, and batch processing with sub-second cold starts and instant autoscaling. It’s built for developers and ML teams seeking a fast, local-like development experience and cloud-backed performance for AI workloads.
Key Features
For teams shipping AI apps, Modal coordinates inference, training, and batch jobs with near-instant scaling and a familiar development flow:
Sub-second cold starts
Starts inference or training jobs in under a second, reducing wait times during development and deployment.
Instant autoscaling
Scales compute up or down automatically as demand fluctuates, minimizing idle resources.
Local-like developer experience
A familiar development flow that feels like running on your laptop, but with cloud-backed resources.
Unified AI workloads
Run inference, training, and batch processing from a single platform without switching tools.
Summary
Best for ML engineers, data science teams, and product teams integrating AI features into apps.
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
