Seldon Inference API
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.
Documentation
Specifications
OpenAPI
https://github.com/SeldonIO/seldon-core/blob/master/openapi/engine.oas3.json
OpenAPI
https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/openapi/seldon-inference-api-openapi.yml
OpenAPI
https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/openapi/seldon-inference-api-v2-openapi.yml
OpenAPI
https://raw.githubusercontent.com/api-evangelist/seldon/refs/heads/main/openapi/seldon-wrapper-api-openapi.yml