Plans and pricing
For individuals just getting started
Included in Personal:
For small teams starting to scale
Everything in Personal, plus:
For teams with production-level use cases
Everything in Team, plus:
Trusted by top data science and machine learning teams

Commonly asked questions
Baseten is the simplest way to put a model behind an API or webapp hosted on fully managed, scalable infrastructure.
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.
By default our GPUs are: NVIDIA T4. For more power, additional options are available. Contact us to learn more.
Our servers are located on the U.S. west coast in AWS data centers. More regions are being added to reduce global latency.
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.
Yes. We offer on-premise deployments on our Enterprise plan. Contact us to learn more.
Data and workloads are hosted in AWS. All user workloads are run in isolated environments. We have isolation at hardware & network levels.
Yes, buy yearly to get 10% off. Contact us for yearly plans.
Yes, we are happy to support ML efforts for education and non-profit organizations. Contact us to learn more.