Get the caller's effective quotas

curl --request GET \
  --url https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/quotas/me \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/quotas/me', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/quotas/me"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

{
  "computed_at": "2026-01-15T10:00:00.000Z",
  "policy": "hard_block",
  "gauges": [
    {
      "key": "llm.rpm",
      "scope": "user",
      "window": "minute",
      "limit": 20,
      "used": 9,
      "percent": 45,
      "as_of": "2026-01-15T09:59:40.000Z"
    },
    {
      "key": "llm.monthly_tokens",
      "scope": "org",
      "window": "month",
      "limit": 10000000,
      "used": 6400000,
      "percent": 64
    }
  ]
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

Quotas

Get the caller's effective quotas

Effective LLM quota status for the calling user in their active organization: the per-user rate limits (llm.rpm, llm.tpm) and the organization monthly budgets (llm.monthly_tokens, llm.monthly_cost) with current usage. Only limits that are actually configured are returned as gauges.

The per-user limit is the most specific one configured: user override, then per-role limit, then the plan’s per-user default.

Usage figures are snapshots: rate gauges are refreshed on each LLM request (as_of = time of the last request, and a sliding window means the live value can only be lower), monthly usage is aggregated hourly.

Requires a user session: calls without a user identity (for example an org API key) get 401 UNAUTHORIZED. When the caller has no active organization, the response carries an empty gauges list.

Rate limiting. 60 requests per 60 seconds per user.

GET

quotas

Get the caller's effective quotas

curl --request GET \
  --url https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/quotas/me \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/quotas/me', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/quotas/me"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

{
  "computed_at": "2026-01-15T10:00:00.000Z",
  "policy": "hard_block",
  "gauges": [
    {
      "key": "llm.rpm",
      "scope": "user",
      "window": "minute",
      "limit": 20,
      "used": 9,
      "percent": 45,
      "as_of": "2026-01-15T09:59:40.000Z"
    },
    {
      "key": "llm.monthly_tokens",
      "scope": "org",
      "window": "month",
      "limit": 10000000,
      "used": 6400000,
      "percent": 64
    }
  ]
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

Authorizations

Authorization

string

header

required

User-bound credential carrying an identity: either a session JWT or a user access token (at:*) generated from the user settings UI. Send as Authorization: Bearer <token>. Org API keys (iak_*) are not accepted here - they carry no user identity. Use the x-prismeai-api-key header instead (see OrgApiKeyAuth).

Response

Quota status for the caller.

computed_at

string<date-time>

required

policy

string

required

Organization quota policy (hard_block by default, or soft_downgrade).

Example:

"hard_block"

gauges

object[]

required

Configured limits only. Per-user gauges have scope user, monthly budgets org.

Hide child attributes

gauges.key

enum<string>

required

Available options:

llm.rpm,

llm.tpm,

llm.monthly_tokens,

llm.monthly_cost

gauges.scope

enum<string>

required

Available options:

user,

org

gauges.window

enum<string>

required

Available options:

minute,

month

gauges.limit

number

required

Configured limit (requests, tokens or cost depending on key).

gauges.used

number

required

Current usage in the window (0 until a first request is recorded).

gauges.percent

number

required

used / limit as a rounded percentage.

gauges.as_of

string<date-time>

Time of the last recorded request (rate gauges only).

display

object

Organization display settings for the quota gauges (settings.quotas.display), when configured.

Introduction

Platform API

Agent Creator API

LLM Gateway API

Governance API

Knowledges API

Collections API

Get the caller's effective quotas

Authorizations

Response