# BentoML

Python serving framework for packaging AI models and custom inference pipelines into deployable services.

- Company: BentoML
- Category: Platforms & Infrastructure
- Business model: Open (open weights/source)
- Availability: unknown
- Launched: Not recorded
- Tags: infer, developer-tools
- Website: https://www.bentoml.com/
- Documentation: https://docs.bentoml.com/
- Pricing page: Not recorded
- License: Not recorded
- Canonical URL: https://globalaiproductindex.com/products/bentoml/
- Record updated: 2026-11-03

Typical uses include Serving AI models to applications; Deployment of production inference endpoints. Documented capabilities: Build inference APIs and compose multiple models; Package dependencies and models into reproducible containers; Adaptive batching and asynchronous task queues.

## Key features

- Build inference APIs and compose multiple models
- Package dependencies and models into reproducible containers
- Adaptive batching and asynchronous task queues

## Use cases

- Serving AI models to applications
- Deployment of production inference endpoints

## Pricing

Self-hosting the open-source project and buying the hosted platform are separate choices. The hosted service has its own plans and usage limits; self-hosting still requires infrastructure and any model-provider charges.

## FAQ

**Where does BentoML fit in a workflow?**

Python serving framework for packaging AI models and custom inference pipelines into deployable services. Build inference APIs and compose multiple models.

**What costs and limits should I compare before choosing BentoML?**

Self-hosting the open-source project and buying the hosted platform are separate choices. The hosted service has its own plans and usage limits; self-hosting still requires infrastructure and any model-provider charges.

## Sources

- [BentoML — official product](https://www.bentoml.com/)
- [BentoML — official documentation and terms](https://docs.bentoml.com/)

---
Data from the [Global AI Product Index](https://globalaiproductindex.com/), licensed CC BY 4.0.