BentoML
by BentoML · freemium · Last verified 2026-04-24
BentoML is an open-source platform for building and deploying production-grade AI services. It provides a Pythonic framework for packaging ML models into containerized APIs with support for batching, async serving, and distributed inference. BentoCloud offers managed hosting, and BentoML integrates with vLLM and TensorRT for LLM serving.
https://bentoml.com ↗C
C—Below Average
Adoption: C+Quality: B+Freshness: ACitations: CEngagement: F
Specifications
- License
- Proprietary
- Pricing
- freemium
- Capabilities
- Integrations
- Use Cases
- API Available
- No
- SDK Languages
- python
- Deployment
- self-hosted, bentocloud, docker, kubernetes
- Rate Limits
- N/A (self-hosted); BentoCloud: plan-based
- Data Privacy
- Self-hosted by default; BentoCloud SOC 2 compliant
- Tags
- inference, open-source, python, containerized, production, llm, api-framework
- Added
- 2026-04-24
- Completeness
- 60%
Index Score
44Adoption
50
Quality
70
Freshness
80
Citations
40
Engagement
0