Plans and pricing

Personal

For individuals just getting started

Free

Included in Personal:

1 user, 1 model, 1 application
Model performance metrics
Public sharing
Data connections
API keys
1 vCPU and 2 GiB memory per version
Get started
Team

For small teams starting to scale

$400/mo

Everything in Personal, plus:

3 users, 3 models, 3 applications
Model version management
Autoscaling
Draft environments
GitHub sync
Add GPU, CPU, and memory
Contact sales
Business

For teams with production-level use cases

Custom

Everything in Team, plus:

More users, models, and applications
On-premise deployment
Multi-tenant & data segregation
Dedicated forward-deployed engineer
Contact sales

Trusted by top data science and machine learning teams

Compare plans

Personal
Team
Business
Workspace
Users
1
3
Custom
Role-based access control
Model deployment
Deployed models
1
3
Custom
Model performance metrics
Version management
Draft models
Memory and CPU
1 vCPU and 2 GiB per version

1 vCPU and 2 GiB per version

Pay for additional resources
1 vCPU and 2 GiB per version

Pay for additional resources
GPU
Pay for usage
Pay for usage
Autoscaling
Applications
Applications
Applications are interactive webapps you create, hosted on Baseten. Learn more.
1
3
Custom
Public sharing
CRON scheduling
Draft environments
Update your existing applications and merge changes when you're ready.
GitHub sync
Import external code
Data
Data connections
Postgres data tables
Security and Privacy
API keys
SOC 2 Type I
Multi-tenant & data segregation
On-premise deployment
Support
Email support
Dedicated forward-deployed engineer
Custom proof-of-concept

Commonly asked questions

What does Baseten do?

Baseten is the simplest way to put a model behind an API or webapp hosted on fully managed, scalable infrastructure.

What is a deployed model?

Deployed models are models you've deployed to Baseten. Pre-trained models available out of the box on Baseten do not count toward this quota.

What GPUs are available?

By default our GPUs are: NVIDIA T4. For more power, additional options are available. Contact us to learn more.

What is the latency?

Our servers are located on the U.S. west coast in AWS data centers. More regions are being added to reduce global latency.

Can I change/cancel my plan anytime?

Yes, we bill by the month. If you cancel at any time during the month, your bill will be pro-rated based on the number of days you used.

Can I run my models on my own infrastructure?

Yes. We offer on-premise deployments on our Enterprise plan. Contact us to learn more.

Is Baseten secure? Where are my models hosted?

Data and workloads are hosted in AWS. All user workloads are run in isolated environments. We have isolation at hardware & network levels.

Do you offer yearly discounts?

Yes, buy yearly to get 10% off. Contact us for yearly plans.

Do you offer education and non-profit discounts?

Yes, we are happy to support ML efforts for education and non-profit organizations. Contact us to learn more.