Skip to content
OpenRelay is in early access, and the /v1 API is stable. New capabilities ship in the changelog.
Skip to Content
PricingDashboard
GuidesAPI ReferenceCLI
API ReferenceBilling and usageUsage

Get current-month usage

Returns the cents and hours used so far this month by GPU model and tier, plus the live burn per hour and the projected hours until the auto-stop floor.

Required permission

Requires the usage.read permission. See Permissions for the roles and API key permissions that include it.

Command line

The orl CLI wraps this endpoint:

Guided workflow: orl balance

orl balance
orl usage current get
GET
/v1/orgs/{orgId}/usage/current

Authorization

apiKey
headerAuthorizationBearer <token>

OpenRelay API key. Send it as Authorization: Bearer or_… (legacy vl_… keys still work).

Path Parameters

orgId*string

Response Body

OK

application/json
  1. response
usageCents*integer
usageHours*number
breakdown*array<>
burnPerHourCents?integer

sum of the locked rates of every open usage record in the org (live burn per hour)

projectedRunwayHours?number

hours until available balance hits the auto-stop floor at the current burn: (available - autoStopFloorCents) / burnPerHourCents; null when burn is 0 or the organization is balance-exempt (it is never auto-stopped), clamped to 0 when already at or below the floor

Formatdouble
autoStopFloorCents?integer

available-balance floor (cents) below which the org is auto-stopped

Example Request
curl -X GET 'https://api.openrelay.inc/v1/orgs/string/usage/current'
Example Response
{  "usageCents": 0,  "usageHours": 0,  "breakdown": [    {      "key": "string",      "hours": 0,      "cents": 0    }  ],  "burnPerHourCents": 0,  "projectedRunwayHours": 0.1,  "autoStopFloorCents": 0}

Overview

Current-period usage and cost breakdowns: this month's hours and cost by GPU model and tier, live burn rate and runway, and daily spend over a trailing window.

Get per-day spend over a trailing window GET

Returns the org's spend per UTC day for the last 1 to 90 days (default 7), split into GPU model, CPU, and Inference segments, plus the prior window's total. This is what the dashboard spend chart shows. Compute cost is split at UTC day boundaries and inference charges land on the day they were billed. Read-only: costs are priced the same way your bill is, never re-priced.