Model Metadata

Metadata about a deployed model in an OIP-compliant inference server. Describes the model's name, available versions, serving platform, and input/output tensor specifications.

Artificial IntelligenceCNCFDeploymentInferenceKubernetesLLMMachine-LearningModel ServingMLOpsScalability

Properties

Name Type Description
name string Name of the model as registered in the inference server.
versions array List of available model versions. May be empty if versioning is not supported.
platform string Backend serving platform and framework.
inputs array Input tensor specifications for the model.
outputs array Output tensor specifications for the model.
View JSON Schema on GitHub

JSON Schema

kserve-model-metadata-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/scalable-inference-serving/main/json-schema/kserve-model-metadata-schema.json",
  "title": "Model Metadata",
  "description": "Metadata about a deployed model in an OIP-compliant inference server. Describes the model's name, available versions, serving platform, and input/output tensor specifications.",
  "type": "object",
  "required": ["name", "platform", "inputs", "outputs"],
  "properties": {
    "name": {
      "type": "string",
      "description": "Name of the model as registered in the inference server."
    },
    "versions": {
      "type": "array",
      "description": "List of available model versions. May be empty if versioning is not supported.",
      "items": {"type": "string"}
    },
    "platform": {
      "type": "string",
      "description": "Backend serving platform and framework.",
      "examples": [
        "tensorflow_savedmodel",
        "pytorch_libtorch",
        "sklearn_sklearn",
        "xgboost_xgboost",
        "onnxruntime_onnx",
        "ensemble",
        "vllm",
        "python"
      ]
    },
    "inputs": {
      "type": "array",
      "description": "Input tensor specifications for the model.",
      "items": {
        "$ref": "#/$defs/TensorMetadata"
      }
    },
    "outputs": {
      "type": "array",
      "description": "Output tensor specifications for the model.",
      "items": {
        "$ref": "#/$defs/TensorMetadata"
      }
    }
  },
  "$defs": {
    "TensorMetadata": {
      "type": "object",
      "title": "Tensor Metadata",
      "description": "Specification of a single input or output tensor.",
      "required": ["name", "datatype", "shape"],
      "properties": {
        "name": {
          "type": "string",
          "description": "Tensor name."
        },
        "datatype": {
          "type": "string",
          "description": "Data type (BOOL, INT32, FP32, BYTES, etc.)",
          "enum": ["BOOL", "UINT8", "UINT16", "UINT32", "UINT64", "INT8", "INT16", "INT32", "INT64", "FP16", "FP32", "FP64", "BYTES", "STRING"]
        },
        "shape": {
          "type": "array",
          "description": "Tensor shape. -1 indicates a dynamic dimension.",
          "items": {"type": "integer"},
          "example": [-1, 224, 224, 3]
        },
        "parameters": {
          "type": "object",
          "additionalProperties": true,
          "description": "Optional tensor-specific parameters."
        }
      }
    }
  }
}

Work with this as data

Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/kserve-model-metadata"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.