Seldon

aid: seldon
name: Seldon
type: Index
image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/apis.yml
created: 2026-06-12
modified: 2026-06-12
specificationVersion: "0.19"
description: >
  Seldon is a Kubernetes-native MLOps platform that enables enterprises to deploy, monitor,
  manage, and explain machine learning models at scale. The platform provides REST and gRPC
  inference APIs that follow the Open Inference Protocol, enabling standardized model serving
  across frameworks including TensorFlow, PyTorch, and scikit-learn. Seldon Core 2 supports
  advanced deployment strategies such as A/B testing, canary rollouts, and shadow deployments
  through its Kubernetes-native architecture. The Seldon Enterprise Platform extends the open
  source core with a comprehensive REST API for managing deployments programmatically,
  including model drift detection via Alibi-Detect and explainability via the Alibi library.
  Seldon Deploy SDK provides a Python client for integrating with the platform API using
  OIDC and session-based authentication workflows.
tags:
  - MLOps
  - Machine Learning
  - Model Serving
  - Inference
  - Kubernetes
  - AI Operations
  - Drift Detection
  - Explainability
  - Canary Deployment
  - A/B Testing
  - LLMOps

apis:

  - aid: seldon:seldon-inference-api
    name: Seldon Inference API
    description: >
      The Seldon Inference API provides REST and gRPC endpoints for serving machine learning
      model predictions at scale. Following the Open Inference Protocol (V2), the API exposes
      standardized endpoints for model health checks, metadata queries, and prediction requests.
      Deployed models are accessible via REST at /seldon/{namespace}/{deployment}/api/v1.0/predictions
      and support multiple ML frameworks through pre-packaged inference servers.
    image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
    humanURL: https://docs.seldon.ai/seldon-core-2/user-guide/inference/inference
    baseURL: https://docs.seldon.ai
    tags:
      - Inference
      - Model Serving
      - REST
      - gRPC
      - Open Inference Protocol
    properties:
      - type: Documentation
        url: https://docs.seldon.ai/seldon-core-2/user-guide/inference/inference
      - type: OpenAPI
        url: https://github.com/SeldonIO/seldon-core/blob/master/openapi/engine.oas3.json
      - type: OpenAPI
        url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/openapi/seldon-inference-api-openapi.yml
      - type: OpenAPI
        url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/openapi/seldon-inference-api-v2-openapi.yml
      - type: OpenAPI
        url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/openapi/seldon-wrapper-api-openapi.yml

  - aid: seldon:seldon-enterprise-platform-api
    name: Seldon Enterprise Platform REST API
    description: >
      The Seldon Enterprise Platform REST API enables programmatic interaction with machine
      learning deployment management, providing endpoints to create, update, and monitor
      SeldonDeployments. The interactive API reference is accessible via Swagger UI at
      $ML_PLATFORM_HOST/seldon-deploy/swagger/ and supports authentication via OIDC and
      session-based methods. The API supports complex deployment pipeline integrations with
      upstream services.
    image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
    humanURL: https://deploy.seldon.io/en/v2.3/contents/product-tour/api/index.html
    baseURL: https://deploy.seldon.io
    tags:
      - Enterprise
      - Deployment Management
      - REST
      - Swagger
    properties:
      - type: Documentation
        url: https://deploy.seldon.io/en/v2.3/contents/product-tour/api/index.html
      - type: OpenAPI
        url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/openapi/seldon-enterprise-platform-api-openapi.yml

  - aid: seldon:seldon-drift-detection-api
    name: Seldon Drift Detection API
    description: >
      Seldon integrates Alibi-Detect drift detection models that can be deployed as standard
      Seldon models, providing REST endpoints for monitoring incoming request distribution
      against reference training data distributions. Drift detectors are configured and managed
      via the Seldon Core 2 deployment API and expose detection results through standard
      inference endpoints.
    image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
    humanURL: https://docs.seldon.ai/seldon-core-2/user-guide/data-science-monitoring/drift
    baseURL: https://docs.seldon.ai
    tags:
      - Drift Detection
      - Monitoring
      - Alibi-Detect
    properties:
      - type: Documentation
        url: https://docs.seldon.ai/seldon-core-2/user-guide/data-science-monitoring/drift

  - aid: seldon:seldon-explainability-api
    name: Seldon Explainability API
    description: >
      Seldon provides a dedicated /explain REST endpoint alongside each deployed model,
      powered by the Alibi explainability library. The endpoint supports multiple explanation
      algorithms including SHAP, integrated gradients, and anchor-based methods, allowing
      users to request human-interpretable explanations for individual model predictions
      in production.
    image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
    humanURL: https://docs.seldon.io/projects/seldon-core/en/latest/analytics/drift_detection.html
    baseURL: https://docs.seldon.io
    tags:
      - Explainability
      - SHAP
      - Alibi
      - Model Interpretability
    properties:
      - type: Documentation
        url: https://docs.seldon.io/projects/seldon-core/en/latest/reference/apis/v2-protocol.html

common:

  - type: Website
    url: https://www.seldon.io

  - type: Documentation
    url: https://docs.seldon.ai/home

  - type: GitHubOrganization
    url: https://github.com/SeldonIO

  - type: LinkedIn
    url: https://www.linkedin.com/company/seldon

  - type: X
    url: https://x.com/seldon_io

  - type: Blog
    url: https://www.seldon.io/resources/blog/

  - type: Pricing
    url: https://www.seldon.io/pricing/

  - type: StatusPage
    url: https://status.seldon.io

  - type: SDK
    url: https://github.com/SeldonIO/seldon-deploy-sdk

  - type: Plans
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/plans/seldon-plans-pricing.yml

  - type: RateLimits
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/rate-limits/seldon-rate-limits.yml

  - type: FinOps
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/finops/seldon-finops.yml

  - type: Vocabulary
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/vocabulary/seldon-vocabulary.yml

  - type: JSONLDContext
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/json-ld/seldon-context.jsonld

  - type: JSONSchema
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/json-schema/seldon-inference-request.json

  - type: JSONSchema
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/json-schema/seldon-inference-response.json

  - type: JSONSchema
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/json-schema/seldon-deployment.json

  - type: Example
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/examples/seldon-inference-request-example.json

  - type: Example
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/examples/seldon-v2-inference-request-example.json

  - type: Example
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/examples/seldon-deployment-canary-example.json

  - type: Example
    url: https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/examples/seldon-explainability-request-example.json

maintainers:
  - FN: Kin Lane
    email: [email protected]