Only pay for the compute you use by seconds. No more wasted idle resources.
compute/month
Access to A100
100 Bentos included
10 workspace seats included
Up to 10 GPU concurrent jobs
Access to BentoML Slack community
Access to more GPU types
Unlimited Bentos
Unlimited workspace seats
Unlimited GPU concurrent jobs
Technical support
Everything in Pro
Custom GPU types
Self-hosted models in your cloud account
Custom integrations
Feature requests priority
Dedicated support
$/sec
$/hr
$/sec
$/hr