BentoML is an open-source framework for packaging and serving machine-learning models as production APIs, with BentoCloud as the managed runtime. The Apache-licensed framework self-hosts anywhere; BentoCloud meters CPU and GPU instances per second with scale-to-zero, so idle deployments cost nothing. A free starter tier and signup credits cover evaluation, a flat-fee Pro tier gates priority access to high-end GPUs and multi-region deployment, and enterprise brings bring-your-own-cloud. Pricing is usage-based, so no fixed monthly entry price applies.
model-servingopen-sourceinference
Overview
- Founded
- 2019
- Pricing tier
- Mid
- Startup-friendly
- Yes
- Enterprise-ready
- Yes
ML platform
- Free tier
- Yes: Free Starter tier with per-second usage billing
- Open-source
- Yes
- Self-hostable
- Yes
- Managed training
- No
- Model hosting
- Yes
- Fine tuning
- No
- Notebooks
- No