> ## Documentation Index
> Fetch the complete documentation index at: https://docs.infercrane.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Read bounded normalized inference and lifecycle evidence



## OpenAPI

````yaml /openapi.json get /api/v1/endpoints/{name}/monitoring
openapi: 3.1.0
info:
  description: >-
    Durable, authenticated control-plane operations. Mutation responses may
    outlive the requesting client.
  title: InferCrane Control API
  version: 2.0.0
servers:
  - description: Local InferCrane API and gateway
    url: http://127.0.0.1:18000
security: []
tags:
  - name: Admission
  - name: Adoption
  - name: Alerts
  - name: Async inference
  - name: Audit
  - name: Autopilot
  - name: Benchmarks
  - name: Burst Guard
  - name: Capacity intelligence
  - name: Context Passport
  - name: Deployments
  - name: Diagnostics
  - name: Endpoints
  - name: External capacity
  - name: FinOps
  - name: Identity
  - name: Inference
  - name: Inference Lab
  - name: Inference decisions
  - name: Infrastructure
  - name: Model artifacts
  - name: Model catalog
  - name: Monitoring
  - name: Operations
  - name: Providers
  - name: Recipes
  - name: Release Guard
  - name: Release evidence
  - name: Replay
  - name: Revisions
  - name: Routing
  - name: Sandboxes
  - name: Scaling
  - name: Secrets
  - name: System
  - name: Targets
  - name: Training lineage
paths:
  /api/v1/endpoints/{name}/monitoring:
    get:
      tags:
        - Monitoring
      summary: Read bounded normalized inference and lifecycle evidence
      operationId: getEndpointMonitoring
      parameters:
        - in: path
          name: name
          required: true
          schema:
            minLength: 1
            type: string
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EndpointMonitoring'
          description: Success
        default:
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorEnvelope'
          description: Typed API error
      security:
        - bearerAuth: []
components:
  schemas:
    EndpointMonitoring:
      additionalProperties: false
      properties:
        breakdowns:
          items:
            $ref: '#/components/schemas/MonitoringBreakdown'
          maxItems: 50
          type: array
        bucket_seconds:
          minimum: 60
          type: integer
        endpoint:
          type: string
        environment:
          type: string
        events:
          items:
            $ref: '#/components/schemas/MonitoringEvent'
          maxItems: 200
          type: array
        evidence:
          $ref: '#/components/schemas/MonitoringEvidence'
        logical_model:
          type: string
        series:
          items:
            $ref: '#/components/schemas/MonitoringBucket'
          maxItems: 500
          type: array
        summary:
          $ref: '#/components/schemas/MonitoringSummary'
        window_end:
          format: date-time
          type: string
        window_start:
          format: date-time
          type: string
      required:
        - endpoint
        - logical_model
        - environment
        - window_start
        - window_end
        - bucket_seconds
        - summary
        - series
        - breakdowns
        - events
        - evidence
      type: object
    ErrorEnvelope:
      properties:
        error:
          $ref: '#/components/schemas/Error'
      required:
        - error
      type: object
    MonitoringBreakdown:
      additionalProperties: false
      properties:
        binding:
          type: string
        deployment:
          type: string
        error_rate:
          type:
            - number
            - 'null'
        errors:
          minimum: 0
          type: integer
        fallbacks:
          minimum: 0
          type: integer
        last_seen_at:
          format: date-time
          type: string
        p95_latency_ms:
          type:
            - number
            - 'null'
        p95_ttft_ms:
          type:
            - number
            - 'null'
        provider:
          type: string
        requests:
          minimum: 0
          type: integer
        revision:
          type: string
        runtime:
          type: string
      type: object
    MonitoringEvent:
      additionalProperties: false
      properties:
        details:
          additionalProperties: true
          type: object
        kind:
          type: string
        occurred_at:
          format: date-time
          type: string
        summary:
          type: string
        type:
          type: string
      type: object
    MonitoringEvidence:
      additionalProperties: false
      properties:
        available:
          items:
            type: string
          type: array
        content_recorded:
          const: false
          type: boolean
        fresh:
          type: boolean
        latest_request_at:
          format: date-time
          type:
            - string
            - 'null'
        measurements:
          items:
            $ref: '#/components/schemas/MeasurementEvidence'
          maxItems: 32
          type: array
        sample_count:
          minimum: 0
          type: integer
        semantic_convention_schema:
          format: uri
          type: string
        source:
          type: string
        unavailable:
          items:
            type: string
          type: array
      required:
        - source
        - semantic_convention_schema
        - sample_count
        - latest_request_at
        - fresh
        - content_recorded
        - available
        - unavailable
        - measurements
      type: object
    MonitoringBucket:
      additionalProperties: false
      properties:
        error_rate:
          type:
            - number
            - 'null'
        errors:
          minimum: 0
          type: integer
        fallback_rate:
          type:
            - number
            - 'null'
        fallbacks:
          minimum: 0
          type: integer
        input_token_samples:
          minimum: 0
          type: integer
        input_tokens:
          minimum: 0
          type: integer
        input_tokens_per_second:
          type:
            - number
            - 'null'
        output_token_samples:
          minimum: 0
          type: integer
        output_tokens:
          minimum: 0
          type: integer
        output_tokens_per_second:
          type:
            - number
            - 'null'
        p50_latency_ms:
          type:
            - number
            - 'null'
        p50_ttft_ms:
          type:
            - number
            - 'null'
        p95_generation_ms:
          type:
            - number
            - 'null'
        p95_latency_ms:
          type:
            - number
            - 'null'
        p95_queue_ms:
          type:
            - number
            - 'null'
        p95_ttft_ms:
          type:
            - number
            - 'null'
        requests:
          minimum: 0
          type: integer
        requests_per_second:
          minimum: 0
          type: number
        retried:
          minimum: 0
          type: integer
        started_at:
          format: date-time
          type: string
        streaming:
          minimum: 0
          type: integer
        token_usage_samples:
          minimum: 0
          type: integer
      type: object
    MonitoringSummary:
      additionalProperties: false
      properties:
        error_rate:
          type:
            - number
            - 'null'
        errors:
          minimum: 0
          type: integer
        fallback_rate:
          type:
            - number
            - 'null'
        fallbacks:
          minimum: 0
          type: integer
        input_token_samples:
          minimum: 0
          type: integer
        input_tokens:
          minimum: 0
          type: integer
        input_tokens_per_second:
          type:
            - number
            - 'null'
        output_token_samples:
          minimum: 0
          type: integer
        output_tokens:
          minimum: 0
          type: integer
        output_tokens_per_second:
          type:
            - number
            - 'null'
        p50_latency_ms:
          type:
            - number
            - 'null'
        p50_ttft_ms:
          type:
            - number
            - 'null'
        p95_generation_ms:
          type:
            - number
            - 'null'
        p95_latency_ms:
          type:
            - number
            - 'null'
        p95_queue_ms:
          type:
            - number
            - 'null'
        p95_ttft_ms:
          type:
            - number
            - 'null'
        requests:
          minimum: 0
          type: integer
        requests_per_second:
          minimum: 0
          type: number
        retried:
          minimum: 0
          type: integer
        retry_rate:
          type:
            - number
            - 'null'
        streaming:
          minimum: 0
          type: integer
        token_usage_samples:
          minimum: 0
          type: integer
      type: object
    Error:
      properties:
        category:
          type: string
        code:
          type: string
        message:
          type: string
        remediation:
          type: string
        request_id:
          type: string
        retryable:
          type: boolean
      required:
        - code
        - message
      type: object
    MeasurementEvidence:
      additionalProperties: false
      properties:
        availability:
          enum:
            - available
            - unavailable
            - stale
            - not_observed
            - unsupported
          type: string
        evidence_class:
          enum:
            - measured
            - provider_reported
            - modeled
            - estimated
          type: string
        fresh_until:
          format: date-time
          type:
            - string
            - 'null'
        name:
          type: string
        observed_at:
          format: date-time
          type:
            - string
            - 'null'
        reason:
          type: string
        sample_count:
          minimum: 0
          type: integer
        source:
          type: string
        unit:
          type: string
        value:
          type:
            - number
            - 'null'
      required:
        - name
        - value
        - unit
        - availability
        - evidence_class
        - source
        - observed_at
        - fresh_until
        - sample_count
      type: object
  securitySchemes:
    bearerAuth:
      scheme: bearer
      type: http

````