# BentoML

**Canonical:** https://apis.io/providers/bentoml/  
**Website:** https://www.bentoml.com/  
**APIs profiled:** 62

BentoML is an open-source unified inference platform for building, packaging, and deploying machine learning models as scalable REST API services. Developers define services using Python class decorators that automatically expose model inference logic as HTTP endpoints. BentoCloud, the managed cloud offering, provides autoscaling infrastructure, GPU instance provisioning, scale-to-zero cost optimization, and a control-plane API for programmatic deployment lifecycle management. The platform supports all major ML frameworks including PyTorch, TensorFlow, Transformers, ONNX, XGBoost, and Scikit-Learn, and is licensed under Apache 2.0.

## Kin Score — 43.8 / 100 (developing)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 43.8).

| Facet | Score |
|---|---|
| Discoverability | 59.3 |
| Contract Quality | 52.9 |
| Governance | 25.0 |
| Contract Governance | 25.0 |
| Operational Transparency | 50.0 |
| Developer Ergonomics | 31.0 |
| Commercial Clarity | 44.7 |
| Access Clarity | 44.7 |

## Agent readiness — 32.6 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| Reversibility Documented | documented |
| MCP Server | no |
| Auth Clarity | yes |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | documented |
| Rate Limit Signal | documented |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Paid · Self-serve signup — onboarding: self-serve, pricing: paid, trial: no (confidence: high).

## APIs (62)

- **BentoML Service REST API** — Auto-generated REST API endpoints produced when BentoML services are deployed. Each decorated service method becomes an HTTP POST endpoint. Supports custom routes, path prefixes...
- **BentoML Python SDK** — Core Python SDK for packaging models as Bentos, managing the model store, building container images, and interacting with BentoML services programmatically including client-side...
- **BentoCloud API Token Management** — API for creating, listing, retrieving, and deleting API tokens used to authenticate with BentoCloud services. Supports scoped tokens with granular permissions including API acce...
- **BentoML admin api v1 API** — admin api v1
- **BentoML admin deployment resource API** — admin deployment resource
- **BentoML api token resource API** — api token resource
- **BentoML api tokens API** — api tokens
- **BentoML api v1 API** — api v1
- **BentoML auth API** — auth api
- **BentoML bento repositories API** — bento repositories
- **BentoML bento repositories statistics API** — bento repositories statistics
- **BentoML bento repository resource API** — bento repository resource
- **BentoML bento resource API** — bento resource
- **BentoML bentos API** — bentos
- **BentoML certified bento repositories API** — certified bento repositories
- **BentoML cluster deployments API** — cluster deployments
- **BentoML cluster resource API** — cluster resource
- **BentoML cluster resource for admin panel API** — cluster resource for admin panel
- **BentoML clusters API** — clusters
- **BentoML clusters for admin panel API** — clusters for admin panel
- **BentoML current organization resource API** — current organization resource
- **BentoML customer resource API** — customer resource
- **BentoML customers API** — customers api
- **BentoML deployment resource API** — deployment resource
- **BentoML deployment revision resource API** — deployment revision resource
- **BentoML deployment revisions API** — deployment revisions
- **BentoML deployment v2 revision resource API** — deployment revision resource
- **BentoML deployment v2 revisions API** — deployment revisions
- **BentoML endpoint resource API** — endpoint resource
- **BentoML gpu config resource API** — gpu config resource
- **BentoML gpu configs API** — gpu configs
- **BentoML host cluster resource API** — host cluster resource
- **BentoML host_clusters API** — host_clusters
- **BentoML instance_types API** — instance_types
- **BentoML labels API** — labels
- **BentoML lago billable metrics API** — lago billable metrics api
- **BentoML lago customer API** — lago customer api
- **BentoML lago plan API** — lago plan api
- **BentoML limit group resource API** — limit group resource
- **BentoML limit groups API** — limit groups
- …and 22 more, listed in full on the page.

## Agentic access (1)

- **Bentoml Agentic Access** — 222 operations · 106 acting · 4 human-in-the-loop

## Security (2)

- **Bentoml Authentication** — apiKey · 1 scheme
- **Bentoml Domain Security** — TLSv1.3 · HSTS · DMARC

## Plans (1)

- **Bentoml Plans Pricing**

## Tags

Machine-Learning, Model Serving, Inference, Artificial Intelligence, REST API, MLOps, Deployment, GPU, LLM, BentoCloud

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/bentoml/). Scores are computed from the provider's own public artifacts under a published rubric.