Skip to main content
GET
/
v3
/
fleet
/
latency
Get latency distribution across the fleet
curl --request GET \
  --url https://api.verlon.ai/v3/fleet/latency \
  --header 'Authorization: Bearer <token>'
{
  "error": "<string>",
  "message": "<string>",
  "details": "<unknown>"
}

Documentation Index

Fetch the complete documentation index at: https://docs.verlon.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

Layer API key (prefixed sk-). Generated from the dashboard under Settings → API Keys, or via layer key create in the CLI.

Query Parameters

​
projectId
string
​
days
integer
default:30
Required range: 1 <= x <= 90

Response

Latency overall percentiles + byGate + byModel breakdowns.