{
  "opencollection": "1.0.0",
  "info": {
    "name": "KServe Open Inference Protocol API",
    "version": "v2"
  },
  "items": [
    {
      "info": {
        "name": "Health",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Check Server Liveness",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://inference.kserve.example.com/v2/health/live"
          },
          "docs": "The server liveness API indicates if the inference server is able to receive and respond to metadata and inference requests. Can be used directly to implement the Kubernetes livenessProbe."
        },
        {
          "info": {
            "name": "Check Server Readiness",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://inference.kserve.example.com/v2/health/ready"
          },
          "docs": "The server readiness API indicates if all the models are ready for inferencing. Can be used directly to implement the Kubernetes readinessProbe."
        },
        {
          "info": {
            "name": "Check Model Readiness",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://inference.kserve.example.com/v2/models/:model_name/ready",
            "params": [
              {
                "name": "model_name",
                "value": "bert-sentiment-classifier",
                "type": "path",
                "description": "Name of the model to check readiness for."
              }
            ]
          },
          "docs": "The model readiness API indicates if a specific model is ready for inferencing. Check this before submitting inference requests to a newly deployed model."
        },
        {
          "info": {
            "name": "Check Model Version Readiness",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://inference.kserve.example.com/v2/models/:model_name/versions/:model_version/ready",
            "params": [
              {
                "name": "model_name",
                "value": "bert-sentiment-classifier",
                "type": "path"
              },
              {
                "name": "model_version",
                "value": "2",
                "type": "path"
              }
            ]
          },
          "docs": "Check if a specific version of a model is ready for inference."
        }
      ]
    },
    {
      "info": {
        "name": "Metadata",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Get Server Metadata",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://inference.kserve.example.com/v2"
          },
          "docs": "Returns metadata about the inference server, including its name, version, and the extensions it supports."
        },
        {
          "info": {
            "name": "Get Model Metadata",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://inference.kserve.example.com/v2/models/:model_name",
            "params": [
              {
                "name": "model_name",
                "value": "resnet50-image-classifier",
                "type": "path",
                "description": "Name of the model."
              }
            ]
          },
          "docs": "Returns metadata about a model, including its name, versions, platform, inputs, and outputs. Use this to discover the input/output tensor shapes and data types before submitting inference requests."
        },
        {
          "info": {
            "name": "Get Model Version Metadata",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://inference.kserve.example.com/v2/models/:model_name/versions/:model_version",
            "params": [
              {
                "name": "model_name",
                "value": "resnet50-image-classifier",
                "type": "path"
              },
              {
                "name": "model_version",
                "value": "2",
                "type": "path"
              }
            ]
          },
          "docs": "Returns metadata for a specific version of a model."
        }
      ]
    },
    {
      "info": {
        "name": "Inference",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Run Model Inference",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://inference.kserve.example.com/v2/models/:model_name/infer",
            "params": [
              {
                "name": "model_name",
                "value": "bert-sentiment-classifier",
                "type": "path",
                "description": "Name of the model to run inference against."
              }
            ],
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Submit an inference request to a model. The request body contains the input tensors as JSON. Inputs are specified as an array of named tensors with shape, datatype, and data fields. The response contains the model's output tensors.\nFor large tensor payloads, the binary tensor data extension allows sending tensor data as binary in the request body alongside the JSON header."
        },
        {
          "info": {
            "name": "Run Model Version Inference",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://inference.kserve.example.com/v2/models/:model_name/versions/:model_version/infer",
            "params": [
              {
                "name": "model_name",
                "value": "resnet50-image-classifier",
                "type": "path"
              },
              {
                "name": "model_version",
                "value": "2",
                "type": "path"
              }
            ],
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Submit an inference request to a specific version of a model. Useful for A/B testing, canary rollouts, and version-pinned integrations."
        }
      ]
    }
  ],
  "bundled": true
}