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