Jump to

• Request
• Response

(Preview) Get model deployment inference summary

get

/20260430/aiDataPlatforms/{aiDataPlatformId}/mlops/api/2.0/model-deployments/{deploymentId}/monitoring/inferences/summary

(Preview) Returns aggregate metrics for correlated request and response inference events within the requested timestamp range. Query parameters `timeStart` and `timeEnd` are optional; when omitted, the API uses the previous 24 hours. Any requested range must be within the most recent 14 days.

Request

Path Parameters

• aiDataPlatformId(required): string
  Minimum Length: 1

  Maximum Length: 500

  The [OCID](/iaas/Content/General/Concepts/identifiers.htm) of the AI Data Platform (Data Lake) instance.
• deploymentId(required): string
  Minimum Length: 32

  Maximum Length: 32

  Pattern: ^[0-9a-f]{32}$

  The unique 32-character hexadecimal ID of the model deployment.

Query Parameters

• timeEnd: string(date-time)
  Inclusive end of the request timestamp range. The range must be within the most recent 14 days. Example: 2026-09-15T00:00:00Z.
• timeStart: string(date-time)
  Inclusive start of the request timestamp range. The range must be within the most recent 14 days. Example: 2026-09-01T00:00:00Z.

Header Parameters

• opc-request-id: string
  Maximum Length: 255

  Unique Oracle-assigned identifier for the request. If you need to contact Oracle about a particular request, please provide the request ID. The only valid characters for request IDs are letters, numbers, underscore, and dash.

Back to Top

Response

Supported Media Types

• application/json

200 Response

Successful operation. Inference summary is returned.

Headers

• opc-request-id: string
  Unique Oracle-assigned ID for the request. If you need to contact Oracle about a particular request, please provide the request ID.

Body ()

Root Schema : InferenceInvocationSummaryResponse

Type: object

Aggregate metrics for a model deployment's inference invocations.

Show Source

• summary(required): object InferenceInvocationSummaryMetrics
  Aggregate metrics for the correlated invocation rows matching the request filters.
• timeEnd(required): string(date-time)
  Inclusive end time resolved for this summary query.
• timeStart(required): string(date-time)
  Inclusive start time resolved for this summary query.

{
    "description":"Aggregate metrics for a model deployment's inference invocations.",
    "type":"object",
    "required":[
        "timeStart",
        "timeEnd",
        "summary"
    ],
    "properties":{
        "timeStart":{
            "description":"Inclusive start time resolved for this summary query.",
            "type":"string",
            "format":"date-time"
        },
        "timeEnd":{
            "description":"Inclusive end time resolved for this summary query.",
            "type":"string",
            "format":"date-time"
        },
        "summary":{
            "$ref":"#/definitions/InferenceInvocationSummaryMetrics"
        }
    }
}

Nested Schema : InferenceInvocationSummaryMetrics

Type: object

Aggregate metrics for the correlated invocation rows matching the request filters.

Show Source

• averageResponseTimeMs(required): number(double)
  Minimum Value: 0

  Mean response latency in milliseconds across the correlated invocations.
• failedRequests(required): integer(int64)
  Minimum Value: 0

  Number of correlated invocations whose inference response status is 5xx.
• malformedRequests(required): integer(int64)
  Minimum Value: 0

  Number of correlated requests whose inference response status is 4xx.
• successfulRequests(required): integer(int64)
  Minimum Value: 0

  Number of correlated invocations whose inference response status is 2xx.
• successRatePercent(required): number(double)
  Minimum Value: 0

  Maximum Value: 100

  Percentage of correlated invocations that succeeded, between 0 and 100.
• totalRequests(required): integer(int64)
  Minimum Value: 0

  Total number of correlated inference invocations in the resolved time range.

{
    "description":"Aggregate metrics for the correlated invocation rows matching the request filters.",
    "type":"object",
    "required":[
        "totalRequests",
        "successfulRequests",
        "failedRequests",
        "successRatePercent",
        "malformedRequests",
        "averageResponseTimeMs"
    ],
    "properties":{
        "totalRequests":{
            "description":"Total number of correlated inference invocations in the resolved time range.",
            "type":"integer",
            "format":"int64",
            "minimum":0
        },
        "successfulRequests":{
            "description":"Number of correlated invocations whose inference response status is 2xx.",
            "type":"integer",
            "format":"int64",
            "minimum":0
        },
        "failedRequests":{
            "description":"Number of correlated invocations whose inference response status is 5xx.",
            "type":"integer",
            "format":"int64",
            "minimum":0
        },
        "successRatePercent":{
            "description":"Percentage of correlated invocations that succeeded, between 0 and 100.",
            "type":"number",
            "format":"double",
            "minimum":0,
            "maximum":100
        },
        "malformedRequests":{
            "description":"Number of correlated requests whose inference response status is 4xx.",
            "type":"integer",
            "format":"int64",
            "minimum":0
        },
        "averageResponseTimeMs":{
            "description":"Mean response latency in milliseconds across the correlated invocations.",
            "type":"number",
            "format":"double",
            "minimum":0
        }
    }
}

400 Response

Bad Request (invalid query parameters, malformed headers, and so on).

Headers

• opc-request-id: string
  Unique Oracle-assigned ID for the request. If you need to contact Oracle about a particular request, please provide the request ID.

Body ()

Root Schema : Error

Type: object

Error information.

Show Source

• code(required): string
  A short error code that defines the error, meant for programmatic parsing.
• message(required): string
  A human-readable error message.

{
    "description":"Error information.",
    "required":[
        "code",
        "message"
    ],
    "properties":{
        "code":{
            "description":"A short error code that defines the error, meant for programmatic parsing.",
            "type":"string"
        },
        "message":{
            "description":"A human-readable error message.",
            "type":"string"
        }
    }
}

401 Response

Unauthorized (missing or expired credentials, and so on).

Headers

• opc-request-id: string
  Unique Oracle-assigned ID for the request. If you need to contact Oracle about a particular request, please provide the request ID.

Body ()

Root Schema : Error

Type: object

Error information.

Show Source

• code(required): string
  A short error code that defines the error, meant for programmatic parsing.
• message(required): string
  A human-readable error message.

{
    "description":"Error information.",
    "required":[
        "code",
        "message"
    ],
    "properties":{
        "code":{
            "description":"A short error code that defines the error, meant for programmatic parsing.",
            "type":"string"
        },
        "message":{
            "description":"A human-readable error message.",
            "type":"string"
        }
    }
}

404 Response

Not Found. The requested resource was not found.

Headers

• opc-request-id: string
  Unique Oracle-assigned ID for the request. If you need to contact Oracle about a particular request, please provide the request ID.

Body ()

Root Schema : Error

Type: object

Error information.

Show Source

• code(required): string
  A short error code that defines the error, meant for programmatic parsing.
• message(required): string
  A human-readable error message.

{
    "description":"Error information.",
    "required":[
        "code",
        "message"
    ],
    "properties":{
        "code":{
            "description":"A short error code that defines the error, meant for programmatic parsing.",
            "type":"string"
        },
        "message":{
            "description":"A human-readable error message.",
            "type":"string"
        }
    }
}

429 Response

Too Many Requests. Too many requests sent to the server in a short period.

Headers

• opc-request-id: string
  Unique Oracle-assigned ID for the request. If you need to contact Oracle about a particular request, please provide the request ID.

Body ()

Root Schema : Error

Type: object

Error information.

Show Source

• code(required): string
  A short error code that defines the error, meant for programmatic parsing.
• message(required): string
  A human-readable error message.

{
    "description":"Error information.",
    "required":[
        "code",
        "message"
    ],
    "properties":{
        "code":{
            "description":"A short error code that defines the error, meant for programmatic parsing.",
            "type":"string"
        },
        "message":{
            "description":"A human-readable error message.",
            "type":"string"
        }
    }
}

500 Response

Internal Server Error. The server encountered an unexpected condition preventing fulfilment of the request.

Headers

• opc-request-id: string
  Unique Oracle-assigned ID for the request. If you need to contact Oracle about a particular request, please provide the request ID.

Body ()

Root Schema : Error

Type: object

Error information.

Show Source

• code(required): string
  A short error code that defines the error, meant for programmatic parsing.
• message(required): string
  A human-readable error message.

{
    "description":"Error information.",
    "required":[
        "code",
        "message"
    ],
    "properties":{
        "code":{
            "description":"A short error code that defines the error, meant for programmatic parsing.",
            "type":"string"
        },
        "message":{
            "description":"A human-readable error message.",
            "type":"string"
        }
    }
}

Default Response

Unknown Error. Error is not recognized by the system.

Headers

• opc-request-id: string
  Unique Oracle-assigned ID for the request. If you need to contact Oracle about a particular request, please provide the request ID.

Body ()

Root Schema : Error

Type: object

Error information.

Show Source

• code(required): string
  A short error code that defines the error, meant for programmatic parsing.
• message(required): string
  A human-readable error message.

{
    "description":"Error information.",
    "required":[
        "code",
        "message"
    ],
    "properties":{
        "code":{
            "description":"A short error code that defines the error, meant for programmatic parsing.",
            "type":"string"
        },
        "message":{
            "description":"A human-readable error message.",
            "type":"string"
        }
    }
}

Back to Top