BentoML

aid: bentoml
name: BentoML
type: Index
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
url: https://raw.githubusercontent.com/api-evangelist/bentoml/refs/heads/main/apis.yml
created: 2026-06-12
modified: 2026-06-12
specificationVersion: '0.19'
description: '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.

  '
tags:
- machine learning
- model serving
- inference
- AI
- REST API
- MLOps
- deployment
- GPU
- LLM
- BentoCloud
apis:
- aid: bentoml:bentocloud-deployment-api
  name: BentoCloud Deployment API
  description: 'Python SDK and programmatic API for managing BentoCloud deployments. Provides operations to create, retrieve,
    list, update, apply, terminate, and delete inference deployments on BentoCloud infrastructure.

    '
  humanURL: https://docs.bentoml.com/en/latest/reference/bentocloud/bentocloud-api.html
  baseURL: https://cloud.bentoml.com
  tags:
  - deployment
  - BentoCloud
  - management
  properties:
  - type: Documentation
    url: https://docs.bentoml.com/en/latest/reference/bentocloud/bentocloud-api.html
  - type: OpenAPI
    url: https://raw.githubusercontent.com/api-evangelist/bentoml/refs/heads/main/openapi/bentoml-bentocloud-deployment-api-openapi.yml
- aid: bentoml:bentoml-service-api
  name: BentoML Service REST API
  description: '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, adaptive batching, async task queues, and context-aware
    request/response handling for model inference workloads.

    '
  humanURL: https://docs.bentoml.com/en/latest/build-with-bentoml/services.html
  baseURL: https://localhost:3000
  tags:
  - inference
  - REST API
  - model serving
  properties:
  - type: Documentation
    url: https://docs.bentoml.com/en/latest/build-with-bentoml/services.html
- aid: bentoml:bentoml-sdk
  name: BentoML Python SDK
  description: 'Core Python SDK for packaging models as Bentos, managing the model store, building container images, and interacting
    with BentoML services programmatically including client-side API calls to deployed inference endpoints.

    '
  humanURL: https://docs.bentoml.com/en/latest/reference/bentoml/index.html
  baseURL: https://pypi.org/project/bentoml/
  tags:
  - SDK
  - Python
  - model packaging
  properties:
  - type: Documentation
    url: https://docs.bentoml.com/en/latest/reference/bentoml/index.html
- aid: bentoml:bentocloud-token-api
  name: BentoCloud API Token Management
  description: 'API for creating, listing, retrieving, and deleting API tokens used to authenticate with BentoCloud services.
    Supports scoped tokens with granular permissions including API access, organization read/write, and cluster read/write.

    '
  humanURL: https://docs.bentoml.com/en/latest/reference/bentocloud/bentocloud-api.html
  baseURL: https://cloud.bentoml.com
  tags:
  - authentication
  - tokens
  - security
  properties:
  - type: Documentation
    url: https://docs.bentoml.com/en/latest/reference/bentocloud/bentocloud-api.html
common:
- type: Website
  url: https://www.bentoml.com/
- type: Documentation
  url: https://docs.bentoml.com/
- type: GitHubOrganization
  url: https://github.com/bentoml
- type: LinkedIn
  url: https://www.linkedin.com/company/bentoml
- type: Blog
  url: https://www.bentoml.com/blog
- type: Pricing
  url: https://www.bentoml.com/pricing
- type: StatusPage
  url: https://status.bentoml.com/
- type: X
  url: https://x.com/bentomlai
- type: CLI
  url: https://docs.bentoml.com/en/latest/reference/bentoml/cli.html
- type: Plans
  url: https://raw.githubusercontent.com/api-evangelist/bentoml/refs/heads/main/plans/bentoml-plans-pricing.yml
- type: RateLimits
  url: https://raw.githubusercontent.com/api-evangelist/bentoml/refs/heads/main/rate-limits/bentoml-rate-limits.yml
- type: FinOps
  url: https://raw.githubusercontent.com/api-evangelist/bentoml/refs/heads/main/finops/bentoml-finops.yml
- type: Vocabulary
  url: https://raw.githubusercontent.com/api-evangelist/bentoml/refs/heads/main/vocabulary/bentoml-vocabulary.yml
- type: JSONSchema
  url: https://raw.githubusercontent.com/api-evangelist/bentoml/refs/heads/main/json-schema/bentoml-schemas.json
- type: JSONLDContext
  url: https://raw.githubusercontent.com/api-evangelist/bentoml/refs/heads/main/json-ld/bentoml-context.jsonld
- type: Examples
  url: https://raw.githubusercontent.com/api-evangelist/bentoml/refs/heads/main/examples/bentoml-api-examples.json
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com