---
title: "What the platform has spent on models today, by provider"
method: GET
path: "/v1/admin/health/spend"
tags: ["meta"]
---

# What the platform has spent on models today, by provider

`GET /v1/admin/health/spend`

## Request

- Base URL: `https://api.hyperresearch.ai`
- URL: `https://api.hyperresearch.ai/v1/admin/health/spend`
- Auth: API key in cookie `hr_session`

Today's settled model spend against the platform-wide daily ceiling. This is OUR money, not a customer's: no workspace, account or query appears in it, and it is not a billing figure. `exhausted` is the circuit breaker — while it is true, new runs are refused with `platform_capacity` and runs already under way continue. One D1 read; no vendor is called.

## Response `200`

Today's platform spend

- PlatformSpendToday
  - `day` string, required: UTC calendar day this total covers.
  - `ceiling_cents` integer, required: `PLATFORM_DAILY_SPEND_CENTS`, or the built-in default when it is unset or unusable.
  - `spent_cents` integer, required
  - `spent_micros` integer, required: Millionths of a USD. The authoritative figure; model calls cost fractions of a cent and cents round.
  - `remaining_cents` integer, required
  - `exhausted` boolean, required: True once new runs are being refused with `platform_capacity`. Runs already in flight are unaffected.
  - `calls` integer, required
  - `providers` object[], required
    - `provider` string, required
    - `micros` integer, required
    - `cents` integer, required
    - `calls` integer, required
    - `updated_at` string, required

## Other responses

- `400`: Invalid request
- `401`: Authentication failed
- `403`: Insufficient scope or plan
- `404`: Not found
- `429`: Rate limited or over quota
- `500`: Internal error

---

[API](https://skmtc.dev/hyperresearch/apis/hyperresearch-cloud-api.md) · [All operations](https://skmtc.dev/hyperresearch/apis/hyperresearch-cloud-api/llms.txt) · [OpenAPI document](https://skmtc.dev/hyperresearch/apis/hyperresearch-cloud-api/revisions/726ef831ebf4?raw)