Quadrillion Latency Distribution API

The Latency Distribution API from Quadrillion — 1 operation(s) for latency distribution.

OpenAPI Specification

quadrillion-latency-distribution-api-openapi.yml Raw ↑
openapi: 3.1.0
info:
  title: Quadrillion Cloud account Latency Distribution API
  description: Public cloud API service for cloud-safe backend endpoints
  version: 0.1.0
tags:
- name: Latency Distribution
paths:
  /api/latency_distribution:
    get:
      summary: Get Latency Distribution
      description: 'Get latency distribution with percentiles (p1, p5, p10, p25, p50, p75, p90, p95, p99)

        aggregated by day and model.


        Returns latency percentiles for:

        - proxy_latency: Time from request received to upstream call initiated

        - ttft_latency: Time from upstream call to first byte received (Time To First Token)


        Defaults to the caller''s own data. Admin users (with @quadrillion.io email)

        may opt into cross-user data by passing user_id (specific user) or

        all_users=true (everyone). Non-admin requests for other users'' data are

        silently scoped to the caller.'
      operationId: get_latency_distribution_api_latency_distribution_get
      parameters:
      - name: user_id
        in: query
        required: false
        schema:
          anyOf:
          - type: integer
          - type: 'null'
          description: Filter by user ID (admin only)
          title: User Id
        description: Filter by user ID (admin only)
      - name: all_users
        in: query
        required: false
        schema:
          type: boolean
          description: Return data for all users (admin only opt-in)
          default: false
          title: All Users
        description: Return data for all users (admin only opt-in)
      - name: model
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Filter by model name
          title: Model
        description: Filter by model name
      - name: start_date
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          description: Start date (ISO 8601)
          title: Start Date
        description: Start date (ISO 8601)
      - name: end_date
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          description: End date (ISO 8601)
          title: End Date
        description: End date (ISO 8601)
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/LatencyDistributionResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Latency Distribution
components:
  schemas:
    LatencyPercentiles:
      properties:
        p1:
          anyOf:
          - type: number
          - type: 'null'
          title: P1
          description: 1st percentile
        p5:
          anyOf:
          - type: number
          - type: 'null'
          title: P5
          description: 5th percentile
        p10:
          anyOf:
          - type: number
          - type: 'null'
          title: P10
          description: 10th percentile
        p25:
          anyOf:
          - type: number
          - type: 'null'
          title: P25
          description: 25th percentile
        p50:
          anyOf:
          - type: number
          - type: 'null'
          title: P50
          description: 50th percentile (median)
        p75:
          anyOf:
          - type: number
          - type: 'null'
          title: P75
          description: 75th percentile
        p90:
          anyOf:
          - type: number
          - type: 'null'
          title: P90
          description: 90th percentile
        p95:
          anyOf:
          - type: number
          - type: 'null'
          title: P95
          description: 95th percentile
        p99:
          anyOf:
          - type: number
          - type: 'null'
          title: P99
          description: 99th percentile
        count:
          type: integer
          title: Count
          description: Number of samples
      type: object
      required:
      - count
      title: LatencyPercentiles
      description: Percentile values for a latency metric (in milliseconds).
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    LatencyDistributionResponse:
      properties:
        buckets:
          items:
            $ref: '#/components/schemas/LatencyDistributionBucket'
          type: array
          title: Buckets
          description: Latency distributions by day and model
      type: object
      required:
      - buckets
      title: LatencyDistributionResponse
      description: Response model for latency distribution query.
    LatencyDistributionBucket:
      properties:
        date:
          type: string
          format: date
          title: Date
          description: The date for this bucket
        model:
          anyOf:
          - type: string
          - type: 'null'
          title: Model
          description: Model name
        proxy_latency:
          $ref: '#/components/schemas/LatencyPercentiles'
          description: Proxy latency percentiles (request to upstream)
        ttft_latency:
          $ref: '#/components/schemas/LatencyPercentiles'
          description: TTFT latency percentiles (upstream to first byte)
      type: object
      required:
      - date
      - proxy_latency
      - ttft_latency
      title: LatencyDistributionBucket
      description: Latency distribution for a model on a specific day.