Billing

All three endpoints below authenticate with your sk- API key — the same key you use for /v1/messages and /v1/chat/completions. The two /v1/dashboard/billing/* endpoints mirror OpenAI's legacy dashboard shape so existing balance-checker scripts and proxy UIs work unmodified; /api/usage/token/ is a BUZZ-native endpoint that breaks the quota down into remaining / used / granted.

Authentication

Both endpoints require a user API token (an sk--prefixed key created from the BUZZ console). They run through the relay token-auth chain, the same one used by /v1/messages and /v1/chat/completions.

No Buzz-User header required — the token already encodes the owner.

QuotaDisplayType: how numbers are calculated

BUZZ stores everything as raw integer "quota units" internally and converts to a human-friendly number only when serving these endpoints. The conversion depends on the site's QuotaDisplayType operation setting:

This means soft_limit_usd in the subscription response and total_usage in the usage response are not always USD. The field name is preserved for OpenAI compatibility, but the actual unit follows the site's display-type setting. Treat the unit as opaque and align it with whatever currency your site shows in the dashboard UI.

GET /v1/dashboard/billing/subscription

Returns the token's (or, when token-level stats are disabled, the user's) remaining-plus-used quota, formatted as if it were a "credit limit". This is what most balance-checker tools poll.

Source of numbers

• If the site has token-level stats enabled: quota = token.RemainQuota + token.UsedQuota, access_until = token.ExpiredTime.
• Otherwise: quota = user.Quota + user.UsedQuota, access_until = 0.
• If the token is unlimited, the response value is overridden to 100000000.
• If the token has no expiry, access_until is forced to 0.

Example request

curl -s 'https://buzzai.cc/v1/dashboard/billing/subscription' \
  -H "Authorization: Bearer sk-$BUZZ_TOKEN"

import os, requests

resp = requests.get(
    "https://buzzai.cc/v1/dashboard/billing/subscription",
    headers={"Authorization": f"Bearer sk-{os.environ['BUZZ_TOKEN']}"},
    timeout=10,
)
data = resp.json()
print(data["soft_limit_usd"], data["access_until"])

const resp = await fetch(
  "https://buzzai.cc/v1/dashboard/billing/subscription",
  { headers: { Authorization: `Bearer sk-${process.env.BUZZ_TOKEN}` } },
);
const data = await resp.json();
console.log(data.soft_limit_usd, data.access_until);

Live response

{
  "object": "billing_subscription",
  "has_payment_method": true,
  "soft_limit_usd": 1,
  "hard_limit_usd": 1,
  "system_hard_limit_usd": 1,
  "access_until": 0
}

Verified live on 2026-06-09 with a regular limited-quota token (USD display). The three limit fields share a single value; access_until = 0 because the site does not run token-level stats, so token expiry is not surfaced here.

Response fields

GET /v1/dashboard/billing/usage

Returns lifetime consumed quota for the calling token (or user). OpenAI's original endpoint is per-period; this BUZZ implementation returns a single cumulative number and ignores any date-range query parameters.

Source of numbers

• If the site has token-level stats enabled: quota = token.UsedQuota.
• Otherwise: quota = GetUserUsedQuota(userId).
• The same QuotaDisplayType conversion is applied to produce amount.
• Final result is multiplied by 100: total_usage = amount * 100. The codebase comment calls this "unit: 0.01 dollar" — i.e. cents when display is USD. With CNY display the field is cents-of-CNY * exchange rate; with Tokens display it is tokens * 100.

Example request

curl -s 'https://buzzai.cc/v1/dashboard/billing/usage' \
  -H "Authorization: Bearer sk-$BUZZ_TOKEN"

import os, requests

resp = requests.get(
    "https://buzzai.cc/v1/dashboard/billing/usage",
    headers={"Authorization": f"Bearer sk-{os.environ['BUZZ_TOKEN']}"},
    timeout=10,
)
total_cents = resp.json()["total_usage"]
print(f"used: {total_cents / 100:.2f}")  # divide by 100 to recover the display unit

const resp = await fetch(
  "https://buzzai.cc/v1/dashboard/billing/usage",
  { headers: { Authorization: `Bearer sk-${process.env.BUZZ_TOKEN}` } },
);
const { total_usage } = await resp.json();
console.log(`used: ${(total_usage / 100).toFixed(2)}`);

Live response

{
  "object": "list",
  "total_usage": 13.6228
}

Verified live on 2026-06-09 (same token as above). The number is "display-unit × 100" — divide by 100 to get the value you see in the dashboard (here ≈ $0.136 used).

Response fields

GET /api/usage/token/

A BUZZ-native endpoint that returns the calling token's quota broken into its three parts — what was granted, what has been used, and what remains — without any currency conversion. The numbers are raw quota units (the same integers stored internally; divide by QuotaPerUnit, default 500000, to get USD). This is the most direct way to read a single key's remaining balance.

Source of numbers

• total_granted = token.RemainQuota + token.UsedQuota
• total_used = token.UsedQuota
• total_available = token.RemainQuota
• expires_at = token.ExpiredTime, forced to 0 when the token never expires.
• For an unlimited token, unlimited_quota is true and the three quota numbers are 0 (there is no finite allowance to report).

Example request

curl -s 'https://buzzai.cc/api/usage/token/' \
  -H "Authorization: Bearer sk-$BUZZ_TOKEN"

import os, requests

resp = requests.get(
    "https://buzzai.cc/api/usage/token/",
    headers={"Authorization": f"Bearer sk-{os.environ['BUZZ_TOKEN']}"},
    timeout=10,
)
d = resp.json()["data"]
print(d["total_available"] / 500000, "USD remaining")  # divide by QuotaPerUnit

const resp = await fetch(
  "https://buzzai.cc/api/usage/token/",
  { headers: { Authorization: `Bearer sk-${process.env.BUZZ_TOKEN}` } },
);
const { data } = await resp.json();
console.log(data.total_available / 500000, "USD remaining");

Live response

{
  "code": true,
  "message": "ok",
  "data": {
    "object": "token_usage",
    "name": "claude",
    "total_granted": 500000,
    "total_used": 68114,
    "total_available": 431886,
    "unlimited_quota": false,
    "model_limits_enabled": false,
    "model_limits": {},
    "expires_at": 1781502010
  }
}

Verified live on 2026-06-09. total_granted = total_used + total_available (500000 = 68114 + 431886). Divide any of them by QuotaPerUnit (500000) to convert to USD — here ≈ $0.864 remaining of a $1.00 grant.

Response fields

Errors

See also

• GET /api/user/self — full profile (also includes the raw quota integer), but authenticates with an account access token + Buzz-User header, not an sk- key
• GET /api/token/ — manage sk- tokens
• Authentication guide — access tokens vs. sk- API keys