{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://developer.nvidia.com/schemas/triton/inference-response.json",
  "title": "Triton Inference Response",
  "description": "An inference response returned by NVIDIA Triton Inference Server following the KServe V2 inference protocol. Contains the model identification, request correlation ID, and output tensors with their data.",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Unique identifier for the response, matching the corresponding request ID"
    },
    "model_name": {
      "type": "string",
      "description": "Name of the model that produced the inference results"
    },
    "model_version": {
      "type": "string",
      "description": "Version of the model that produced the inference results"
    },
    "parameters": {
      "type": "object",
      "description": "Response-level parameters returned by the server",
      "properties": {
        "sequence_id": {
          "oneOf": [
            { "type": "integer" },
            { "type": "string" }
          ],
          "description": "Sequence identifier if this response is part of a sequence"
        },
        "sequence_start": {
          "type": "boolean",
          "description": "Indicates this is the first response in a sequence"
        },
        "sequence_end": {
          "type": "boolean",
          "description": "Indicates this is the last response in a sequence"
        }
      },
      "additionalProperties": {
        "oneOf": [
          { "type": "string" },
          { "type": "boolean" },
          { "type": "integer" }
        ]
      }
    },
    "outputs": {
      "type": "array",
      "description": "Output tensors produced by the inference",
      "items": {
        "$ref": "#/$defs/OutputTensor"
      }
    }
  },
  "$defs": {
    "OutputTensor": {
      "type": "object",
      "description": "An output tensor returned by the model after inference",
      "properties": {
        "name": {
          "type": "string",
          "description": "Name of the output tensor"
        },
        "shape": {
          "type": "array",
          "description": "Shape of the output tensor",
          "items": {
            "type": "integer",
            "minimum": 0
          }
        },
        "datatype": {
          "type": "string",
          "description": "Data type of the tensor elements",
          "enum": [
            "BOOL",
            "UINT8",
            "UINT16",
            "UINT32",
            "UINT64",
            "INT8",
            "INT16",
            "INT32",
            "INT64",
            "FP16",
            "FP32",
            "FP64",
            "BYTES",
            "BF16"
          ]
        },
        "parameters": {
          "type": "object",
          "description": "Per-output parameters",
          "properties": {
            "binary_data_size": {
              "type": "integer",
              "minimum": 0,
              "description": "Size in bytes of binary data appended after the JSON response body"
            }
          },
          "additionalProperties": {
            "oneOf": [
              { "type": "string" },
              { "type": "boolean" },
              { "type": "integer" }
            ]
          }
        },
        "data": {
          "type": "array",
          "description": "Tensor data as a flattened row-major array of values"
        }
      }
    }
  }
}